Skip to content

GitLab

Commit a75d2bda authored by mashun1's avatar mashun1
Browse files

evtexture

parents
Pipeline #1325 canceled with stages
Show whitespace changes
Inline Side-by-side
Showing with 3891 additions and 0 deletions
.gitignore 0 → 100644
View file @ a75d2bda
.eggs
*.egg-info
__pycache__
# datasets
datasets/images
datasets/zbl*
datasets/*h5
datasets/y10
datasets/*.mp4
datasets/*.avi
datasets/videos
datasets/*.zip
*.log
experiments/
others/rpg_vid2e/esim_py/build
# others/rpg_vid2e/esim_py/dist
others/rpg_vid2e/esim_py/esim_py.egg-info
results/
basicsr/version.py
\ No newline at end of file
EvTexture_test.ipynb 0 → 100644
View file @ a75d2bda
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"authorship_tag": "ABX9TyMGq0m8rLF5fC5HOy98jnxn",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/github/DachunKai/EvTexture/blob/main/EvTexture_test.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"source": [
"Download pretrained model and test sets, and config the environment"
],
"metadata": {
"id": "kc6noMW55u8z"
}
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"id": "o_5SAnuf5q49",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"outputId": "0122f2c9-fd2f-4e97-e5e1-8e29634d51b9"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Cloning into 'EvTexture'...\n",
"remote: Enumerating objects: 246, done.\u001b[K\n",
"remote: Counting objects: 100% (246/246), done.\u001b[K\n",
"remote: Compressing objects: 100% (179/179), done.\u001b[K\n",
"remote: Total 246 (delta 69), reused 216 (delta 46), pack-reused 0\u001b[K\n",
"Receiving objects: 100% (246/246), 16.45 MiB | 32.72 MiB/s, done.\n",
"Resolving deltas: 100% (69/69), done.\n",
"--2024-07-02 05:39:46-- https://github.com/DachunKai/EvTexture/releases/download/v0.0/EvTexture_REDS_BIx4.pth\n",
"Resolving github.com (github.com)... 140.82.114.4\n",
"Connecting to github.com (github.com)|140.82.114.4|:443... connected.\n",
"HTTP request sent, awaiting response... 302 Found\n",
"Location: https://objects.githubusercontent.com/github-production-release-asset-2e65be/802383145/f3d29890-39c7-4116-8a9b-99d9dd20358a?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=releaseassetproduction%2F20240702%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240702T053946Z&X-Amz-Expires=300&X-Amz-Signature=51959cb6b3569e8be331e4eb8d18d53926b123ca86c138fa18e3506fc192d22f&X-Amz-SignedHeaders=host&actor_id=0&key_id=0&repo_id=802383145&response-content-disposition=attachment%3B%20filename%3DEvTexture_REDS_BIx4.pth&response-content-type=application%2Foctet-stream [following]\n",
"--2024-07-02 05:39:46-- https://objects.githubusercontent.com/github-production-release-asset-2e65be/802383145/f3d29890-39c7-4116-8a9b-99d9dd20358a?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=releaseassetproduction%2F20240702%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240702T053946Z&X-Amz-Expires=300&X-Amz-Signature=51959cb6b3569e8be331e4eb8d18d53926b123ca86c138fa18e3506fc192d22f&X-Amz-SignedHeaders=host&actor_id=0&key_id=0&repo_id=802383145&response-content-disposition=attachment%3B%20filename%3DEvTexture_REDS_BIx4.pth&response-content-type=application%2Foctet-stream\n",
"Resolving objects.githubusercontent.com (objects.githubusercontent.com)... 185.199.108.133, 185.199.110.133, 185.199.109.133, ...\n",
"Connecting to objects.githubusercontent.com (objects.githubusercontent.com)|185.199.108.133|:443... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 71518689 (68M) [application/octet-stream]\n",
"Saving to: ‘/content/EvTexture/experiments/pretrained_models/EvTexture/EvTexture_REDS_BIx4.pth’\n",
"\n",
"/content/EvTexture/ 100%[===================>] 68.21M 222MB/s in 0.3s \n",
"\n",
"2024-07-02 05:39:46 (222 MB/s) - ‘/content/EvTexture/experiments/pretrained_models/EvTexture/EvTexture_REDS_BIx4.pth’ saved [71518689/71518689]\n",
"\n",
"--2024-07-02 05:39:46-- https://github.com/DachunKai/EvTexture/releases/download/v0.0/EvTexture_Vimeo90K_BIx4.pth\n",
"Resolving github.com (github.com)... 140.82.112.4\n",
"Connecting to github.com (github.com)|140.82.112.4|:443... connected.\n",
"HTTP request sent, awaiting response... 302 Found\n",
"Location: https://objects.githubusercontent.com/github-production-release-asset-2e65be/802383145/09197867-2b0d-4d7a-9890-0e0ff23e0d79?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=releaseassetproduction%2F20240702%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240702T053946Z&X-Amz-Expires=300&X-Amz-Signature=06547c1489048e934a918180a3deae53e6a5420857e1f669ad63f3897c22e22b&X-Amz-SignedHeaders=host&actor_id=0&key_id=0&repo_id=802383145&response-content-disposition=attachment%3B%20filename%3DEvTexture_Vimeo90K_BIx4.pth&response-content-type=application%2Foctet-stream [following]\n",
"--2024-07-02 05:39:46-- https://objects.githubusercontent.com/github-production-release-asset-2e65be/802383145/09197867-2b0d-4d7a-9890-0e0ff23e0d79?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=releaseassetproduction%2F20240702%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240702T053946Z&X-Amz-Expires=300&X-Amz-Signature=06547c1489048e934a918180a3deae53e6a5420857e1f669ad63f3897c22e22b&X-Amz-SignedHeaders=host&actor_id=0&key_id=0&repo_id=802383145&response-content-disposition=attachment%3B%20filename%3DEvTexture_Vimeo90K_BIx4.pth&response-content-type=application%2Foctet-stream\n",
"Resolving objects.githubusercontent.com (objects.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...\n",
"Connecting to objects.githubusercontent.com (objects.githubusercontent.com)|185.199.108.133|:443... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 71518689 (68M) [application/octet-stream]\n",
"Saving to: ‘/content/EvTexture/experiments/pretrained_models/EvTexture/EvTexture_Vimeo90K_BIx4.pth’\n",
"\n",
"/content/EvTexture/ 100%[===================>] 68.21M 185MB/s in 0.4s \n",
"\n",
"2024-07-02 05:39:47 (185 MB/s) - ‘/content/EvTexture/experiments/pretrained_models/EvTexture/EvTexture_Vimeo90K_BIx4.pth’ saved [71518689/71518689]\n",
"\n",
"--2024-07-02 05:39:47-- https://github.com/DachunKai/EvTexture/releases/download/v0.0/test_sets_REDS4_h5.zip\n",
"Resolving github.com (github.com)... 140.82.113.3\n",
"Connecting to github.com (github.com)|140.82.113.3|:443... connected.\n",
"HTTP request sent, awaiting response... 302 Found\n",
"Location: https://objects.githubusercontent.com/github-production-release-asset-2e65be/802383145/fbc06bc0-d1ab-444a-b793-fb67e9a7b452?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=releaseassetproduction%2F20240702%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240702T053947Z&X-Amz-Expires=300&X-Amz-Signature=681c48990365d555a9c0d65da6408973ab7b1ac9f97d8e4df77c2483113b7506&X-Amz-SignedHeaders=host&actor_id=0&key_id=0&repo_id=802383145&response-content-disposition=attachment%3B%20filename%3Dtest_sets_REDS4_h5.zip&response-content-type=application%2Foctet-stream [following]\n",
"--2024-07-02 05:39:47-- https://objects.githubusercontent.com/github-production-release-asset-2e65be/802383145/fbc06bc0-d1ab-444a-b793-fb67e9a7b452?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=releaseassetproduction%2F20240702%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240702T053947Z&X-Amz-Expires=300&X-Amz-Signature=681c48990365d555a9c0d65da6408973ab7b1ac9f97d8e4df77c2483113b7506&X-Amz-SignedHeaders=host&actor_id=0&key_id=0&repo_id=802383145&response-content-disposition=attachment%3B%20filename%3Dtest_sets_REDS4_h5.zip&response-content-type=application%2Foctet-stream\n",
"Resolving objects.githubusercontent.com (objects.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...\n",
"Connecting to objects.githubusercontent.com (objects.githubusercontent.com)|185.199.108.133|:443... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 1658084054 (1.5G) [application/octet-stream]\n",
"Saving to: ‘/content/EvTexture/datasets/test_sets_REDS4_h5.zip’\n",
"\n",
"/content/EvTexture/ 100%[===================>] 1.54G 195MB/s in 13s \n",
"\n",
"2024-07-02 05:40:00 (121 MB/s) - ‘/content/EvTexture/datasets/test_sets_REDS4_h5.zip’ saved [1658084054/1658084054]\n",
"\n",
"--2024-07-02 05:40:00-- https://github.com/DachunKai/EvTexture/releases/download/v0.0/test_sets_Vid4_h5.zip\n",
"Resolving github.com (github.com)... 140.82.114.3\n",
"Connecting to github.com (github.com)|140.82.114.3|:443... connected.\n",
"HTTP request sent, awaiting response... 302 Found\n",
"Location: https://objects.githubusercontent.com/github-production-release-asset-2e65be/802383145/f8bd1b73-42ec-4cb0-9162-40a74ceb4b62?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=releaseassetproduction%2F20240702%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240702T054000Z&X-Amz-Expires=300&X-Amz-Signature=fc60d2acd42829bdc4d52bd935e4305b06faec3a45fe6c189ef57094d633c1a2&X-Amz-SignedHeaders=host&actor_id=0&key_id=0&repo_id=802383145&response-content-disposition=attachment%3B%20filename%3Dtest_sets_Vid4_h5.zip&response-content-type=application%2Foctet-stream [following]\n",
"--2024-07-02 05:40:00-- https://objects.githubusercontent.com/github-production-release-asset-2e65be/802383145/f8bd1b73-42ec-4cb0-9162-40a74ceb4b62?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=releaseassetproduction%2F20240702%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240702T054000Z&X-Amz-Expires=300&X-Amz-Signature=fc60d2acd42829bdc4d52bd935e4305b06faec3a45fe6c189ef57094d633c1a2&X-Amz-SignedHeaders=host&actor_id=0&key_id=0&repo_id=802383145&response-content-disposition=attachment%3B%20filename%3Dtest_sets_Vid4_h5.zip&response-content-type=application%2Foctet-stream\n",
"Resolving objects.githubusercontent.com (objects.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...\n",
"Connecting to objects.githubusercontent.com (objects.githubusercontent.com)|185.199.108.133|:443... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 326545534 (311M) [application/octet-stream]\n",
"Saving to: ‘/content/EvTexture/datasets/test_sets_Vid4_h5.zip’\n",
"\n",
"/content/EvTexture/ 100%[===================>] 311.42M 230MB/s in 1.4s \n",
"\n",
"2024-07-02 05:40:02 (230 MB/s) - ‘/content/EvTexture/datasets/test_sets_Vid4_h5.zip’ saved [326545534/326545534]\n",
"\n",
"/content/EvTexture/datasets\n",
"Archive: test_sets_Vid4_h5.zip\n",
" creating: Vid4_h5/\n",
" creating: Vid4_h5/HR/\n",
" creating: Vid4_h5/HR/test/\n",
" inflating: Vid4_h5/HR/test/calendar.h5 \n",
" inflating: Vid4_h5/HR/test/city.h5 \n",
" inflating: Vid4_h5/HR/test/foliage.h5 \n",
" inflating: Vid4_h5/HR/test/walk.h5 \n",
" creating: Vid4_h5/LRx4/\n",
" creating: Vid4_h5/LRx4/test/\n",
" inflating: Vid4_h5/LRx4/test/calendar.h5 \n",
" inflating: Vid4_h5/LRx4/test/city.h5 \n",
" inflating: Vid4_h5/LRx4/test/foliage.h5 \n",
" inflating: Vid4_h5/LRx4/test/walk.h5 \n",
"Archive: test_sets_REDS4_h5.zip\n",
" creating: REDS4_h5/\n",
" creating: REDS4_h5/HR/\n",
" creating: REDS4_h5/HR/test/\n",
" inflating: REDS4_h5/HR/test/000.h5 \n",
" inflating: REDS4_h5/HR/test/011.h5 \n",
" inflating: REDS4_h5/HR/test/015.h5 \n",
" inflating: REDS4_h5/HR/test/020.h5 \n",
" creating: REDS4_h5/LRx4/\n",
" creating: REDS4_h5/LRx4/test/\n",
" inflating: REDS4_h5/LRx4/test/000.h5 \n",
" inflating: REDS4_h5/LRx4/test/011.h5 \n",
" inflating: REDS4_h5/LRx4/test/015.h5 \n",
" inflating: REDS4_h5/LRx4/test/020.h5 \n",
"/content/EvTexture\n",
"Collecting addict (from -r requirements.txt (line 1))\n",
" Downloading addict-2.4.0-py3-none-any.whl (3.8 kB)\n",
"Collecting argparse (from -r requirements.txt (line 2))\n",
" Downloading argparse-1.4.0-py2.py3-none-any.whl (23 kB)\n",
"Collecting einops (from -r requirements.txt (line 3))\n",
" Downloading einops-0.8.0-py3-none-any.whl (43 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m43.2/43.2 kB\u001b[0m \u001b[31m4.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: future in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 4)) (0.18.3)\n",
"Requirement already satisfied: h5py in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 5)) (3.9.0)\n",
"Collecting lpips (from -r requirements.txt (line 6))\n",
" Downloading lpips-0.1.4-py3-none-any.whl (53 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m53.8/53.8 kB\u001b[0m \u001b[31m6.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting lmdb (from -r requirements.txt (line 7))\n",
" Downloading lmdb-1.5.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (294 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m294.9/294.9 kB\u001b[0m \u001b[31m23.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: matplotlib in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 8)) (3.7.1)\n",
"Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 9)) (1.25.2)\n",
"Requirement already satisfied: opencv-python in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 10)) (4.8.0.76)\n",
"Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 11)) (2.0.3)\n",
"Requirement already satisfied: Pillow in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 12)) (9.4.0)\n",
"Requirement already satisfied: pyyaml in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 13)) (6.0.1)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 14)) (2.31.0)\n",
"Requirement already satisfied: scikit-image in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 15)) (0.19.3)\n",
"Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 16)) (1.11.4)\n",
"Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 17)) (67.7.2)\n",
"Collecting tb-nightly (from -r requirements.txt (line 18))\n",
" Downloading tb_nightly-2.18.0a20240701-py3-none-any.whl (5.5 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.5/5.5 MB\u001b[0m \u001b[31m66.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: tensorboard in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 19)) (2.15.2)\n",
"Collecting tensorboardX (from -r requirements.txt (line 20))\n",
" Downloading tensorboardX-2.6.2.2-py2.py3-none-any.whl (101 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m101.7/101.7 kB\u001b[0m \u001b[31m11.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: torch>=1.10.2 in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 21)) (2.3.0+cu121)\n",
"Requirement already satisfied: torchvision>=0.11.3 in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 22)) (0.18.0+cu121)\n",
"Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 23)) (4.66.4)\n",
"Collecting wandb (from -r requirements.txt (line 24))\n",
" Downloading wandb-0.17.3-py3-none-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (6.9 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.9/6.9 MB\u001b[0m \u001b[31m14.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting yapf (from -r requirements.txt (line 25))\n",
" Downloading yapf-0.40.2-py3-none-any.whl (254 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m254.7/254.7 kB\u001b[0m \u001b[31m27.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->-r requirements.txt (line 8)) (1.2.1)\n",
"Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib->-r requirements.txt (line 8)) (0.12.1)\n",
"Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->-r requirements.txt (line 8)) (4.53.0)\n",
"Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->-r requirements.txt (line 8)) (1.4.5)\n",
"Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->-r requirements.txt (line 8)) (24.1)\n",
"Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->-r requirements.txt (line 8)) (3.1.2)\n",
"Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib->-r requirements.txt (line 8)) (2.8.2)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->-r requirements.txt (line 11)) (2023.4)\n",
"Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas->-r requirements.txt (line 11)) (2024.1)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->-r requirements.txt (line 14)) (3.3.2)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->-r requirements.txt (line 14)) (3.7)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->-r requirements.txt (line 14)) (2.0.7)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->-r requirements.txt (line 14)) (2024.6.2)\n",
"Requirement already satisfied: networkx>=2.2 in /usr/local/lib/python3.10/dist-packages (from scikit-image->-r requirements.txt (line 15)) (3.3)\n",
"Requirement already satisfied: imageio>=2.4.1 in /usr/local/lib/python3.10/dist-packages (from scikit-image->-r requirements.txt (line 15)) (2.31.6)\n",
"Requirement already satisfied: tifffile>=2019.7.26 in /usr/local/lib/python3.10/dist-packages (from scikit-image->-r requirements.txt (line 15)) (2024.6.18)\n",
"Requirement already satisfied: PyWavelets>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-image->-r requirements.txt (line 15)) (1.6.0)\n",
"Requirement already satisfied: absl-py>=0.4 in /usr/local/lib/python3.10/dist-packages (from tb-nightly->-r requirements.txt (line 18)) (1.4.0)\n",
"Requirement already satisfied: grpcio>=1.48.2 in /usr/local/lib/python3.10/dist-packages (from tb-nightly->-r requirements.txt (line 18)) (1.64.1)\n",
"Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.10/dist-packages (from tb-nightly->-r requirements.txt (line 18)) (3.6)\n",
"Requirement already satisfied: protobuf!=4.24.0,<5.0.0,>=3.19.6 in /usr/local/lib/python3.10/dist-packages (from tb-nightly->-r requirements.txt (line 18)) (3.20.3)\n",
"Requirement already satisfied: six>1.9 in /usr/local/lib/python3.10/dist-packages (from tb-nightly->-r requirements.txt (line 18)) (1.16.0)\n",
"Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from tb-nightly->-r requirements.txt (line 18)) (0.7.2)\n",
"Requirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from tb-nightly->-r requirements.txt (line 18)) (3.0.3)\n",
"Requirement already satisfied: google-auth<3,>=1.6.3 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 19)) (2.27.0)\n",
"Requirement already satisfied: google-auth-oauthlib<2,>=0.5 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 19)) (1.2.0)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.2->-r requirements.txt (line 21)) (3.15.4)\n",
"Requirement already satisfied: typing-extensions>=4.8.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.2->-r requirements.txt (line 21)) (4.12.2)\n",
"Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.2->-r requirements.txt (line 21)) (1.12.1)\n",
"Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.2->-r requirements.txt (line 21)) (3.1.4)\n",
"Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.2->-r requirements.txt (line 21)) (2023.6.0)\n",
"Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch>=1.10.2->-r requirements.txt (line 21))\n",
" Using cached nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)\n",
"Collecting nvidia-cuda-runtime-cu12==12.1.105 (from torch>=1.10.2->-r requirements.txt (line 21))\n",
" Using cached nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)\n",
"Collecting nvidia-cuda-cupti-cu12==12.1.105 (from torch>=1.10.2->-r requirements.txt (line 21))\n",
" Using cached nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)\n",
"Collecting nvidia-cudnn-cu12==8.9.2.26 (from torch>=1.10.2->-r requirements.txt (line 21))\n",
" Using cached nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)\n",
"Collecting nvidia-cublas-cu12==12.1.3.1 (from torch>=1.10.2->-r requirements.txt (line 21))\n",
" Using cached nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)\n",
"Collecting nvidia-cufft-cu12==11.0.2.54 (from torch>=1.10.2->-r requirements.txt (line 21))\n",
" Using cached nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)\n",
"Collecting nvidia-curand-cu12==10.3.2.106 (from torch>=1.10.2->-r requirements.txt (line 21))\n",
" Using cached nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)\n",
"Collecting nvidia-cusolver-cu12==11.4.5.107 (from torch>=1.10.2->-r requirements.txt (line 21))\n",
" Using cached nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)\n",
"Collecting nvidia-cusparse-cu12==12.1.0.106 (from torch>=1.10.2->-r requirements.txt (line 21))\n",
" Using cached nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)\n",
"Collecting nvidia-nccl-cu12==2.20.5 (from torch>=1.10.2->-r requirements.txt (line 21))\n",
" Using cached nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl (176.2 MB)\n",
"Collecting nvidia-nvtx-cu12==12.1.105 (from torch>=1.10.2->-r requirements.txt (line 21))\n",
" Using cached nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)\n",
"Requirement already satisfied: triton==2.3.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.2->-r requirements.txt (line 21)) (2.3.0)\n",
"Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.10.2->-r requirements.txt (line 21))\n",
" Downloading nvidia_nvjitlink_cu12-12.5.82-py3-none-manylinux2014_x86_64.whl (21.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.3/21.3 MB\u001b[0m \u001b[31m57.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: click!=8.0.0,>=7.1 in /usr/local/lib/python3.10/dist-packages (from wandb->-r requirements.txt (line 24)) (8.1.7)\n",
"Collecting docker-pycreds>=0.4.0 (from wandb->-r requirements.txt (line 24))\n",
" Downloading docker_pycreds-0.4.0-py2.py3-none-any.whl (9.0 kB)\n",
"Collecting gitpython!=3.1.29,>=1.0.0 (from wandb->-r requirements.txt (line 24))\n",
" Downloading GitPython-3.1.43-py3-none-any.whl (207 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m207.3/207.3 kB\u001b[0m \u001b[31m22.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: platformdirs in /usr/local/lib/python3.10/dist-packages (from wandb->-r requirements.txt (line 24)) (4.2.2)\n",
"Requirement already satisfied: psutil>=5.0.0 in /usr/local/lib/python3.10/dist-packages (from wandb->-r requirements.txt (line 24)) (5.9.5)\n",
"Collecting sentry-sdk>=1.0.0 (from wandb->-r requirements.txt (line 24))\n",
" Downloading sentry_sdk-2.7.1-py2.py3-none-any.whl (300 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m300.2/300.2 kB\u001b[0m \u001b[31m28.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting setproctitle (from wandb->-r requirements.txt (line 24))\n",
" Downloading setproctitle-1.3.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (30 kB)\n",
"Requirement already satisfied: importlib-metadata>=6.6.0 in /usr/local/lib/python3.10/dist-packages (from yapf->-r requirements.txt (line 25)) (8.0.0)\n",
"Requirement already satisfied: tomli>=2.0.1 in /usr/local/lib/python3.10/dist-packages (from yapf->-r requirements.txt (line 25)) (2.0.1)\n",
"Collecting gitdb<5,>=4.0.1 (from gitpython!=3.1.29,>=1.0.0->wandb->-r requirements.txt (line 24))\n",
" Downloading gitdb-4.0.11-py3-none-any.whl (62 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.7/62.7 kB\u001b[0m \u001b[31m7.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: cachetools<6.0,>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard->-r requirements.txt (line 19)) (5.3.3)\n",
"Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard->-r requirements.txt (line 19)) (0.4.0)\n",
"Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard->-r requirements.txt (line 19)) (4.9)\n",
"Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from google-auth-oauthlib<2,>=0.5->tensorboard->-r requirements.txt (line 19)) (1.3.1)\n",
"Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.10/dist-packages (from importlib-metadata>=6.6.0->yapf->-r requirements.txt (line 25)) (3.19.2)\n",
"Requirement already satisfied: MarkupSafe>=2.1.1 in /usr/local/lib/python3.10/dist-packages (from werkzeug>=1.0.1->tb-nightly->-r requirements.txt (line 18)) (2.1.5)\n",
"Requirement already satisfied: mpmath<1.4.0,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.10.2->-r requirements.txt (line 21)) (1.3.0)\n",
"Collecting smmap<6,>=3.0.1 (from gitdb<5,>=4.0.1->gitpython!=3.1.29,>=1.0.0->wandb->-r requirements.txt (line 24))\n",
" Downloading smmap-5.0.1-py3-none-any.whl (24 kB)\n",
"Requirement already satisfied: pyasn1<0.7.0,>=0.4.6 in /usr/local/lib/python3.10/dist-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard->-r requirements.txt (line 19)) (0.6.0)\n",
"Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.10/dist-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<2,>=0.5->tensorboard->-r requirements.txt (line 19)) (3.2.2)\n",
"Installing collected packages: lmdb, argparse, addict, tensorboardX, smmap, setproctitle, sentry-sdk, nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, einops, docker-pycreds, yapf, tb-nightly, nvidia-cusparse-cu12, nvidia-cudnn-cu12, gitdb, nvidia-cusolver-cu12, gitpython, wandb, lpips\n",
"Successfully installed addict-2.4.0 argparse-1.4.0 docker-pycreds-0.4.0 einops-0.8.0 gitdb-4.0.11 gitpython-3.1.43 lmdb-1.5.1 lpips-0.1.4 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.20.5 nvidia-nvjitlink-cu12-12.5.82 nvidia-nvtx-cu12-12.1.105 sentry-sdk-2.7.1 setproctitle-1.3.3 smmap-5.0.1 tb-nightly-2.18.0a20240701 tensorboardX-2.6.2.2 wandb-0.17.3 yapf-0.40.2\n"
]
},
{
"output_type": "display_data",
"data": {
"application/vnd.colab-display-data+json": {
"pip_warning": {
"packages": [
"argparse"
]
},
"id": "191881c6dcb3473da9b2729fd5585c87"
}
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"/usr/local/lib/python3.10/dist-packages/setuptools/__init__.py:84: _DeprecatedInstaller: setuptools.installer and fetch_build_eggs are deprecated.\n",
"!!\n",
"\n",
" ********************************************************************************\n",
" Requirements should be satisfied by a PEP 517 installer.\n",
" If you are using pip, you can try `pip install --use-pep517`.\n",
" ********************************************************************************\n",
"\n",
"!!\n",
" dist.fetch_build_eggs(dist.setup_requires)\n",
"running develop\n",
"/usr/local/lib/python3.10/dist-packages/setuptools/command/develop.py:40: EasyInstallDeprecationWarning: easy_install command is deprecated.\n",
"!!\n",
"\n",
" ********************************************************************************\n",
" Please avoid running ``setup.py`` and ``easy_install``.\n",
" Instead, use pypa/build, pypa/installer, pypa/build or\n",
" other standards-based tools.\n",
"\n",
" See https://github.com/pypa/setuptools/issues/917 for details.\n",
" ********************************************************************************\n",
"\n",
"!!\n",
" easy_install.initialize_options(self)\n",
"/usr/local/lib/python3.10/dist-packages/setuptools/_distutils/cmd.py:66: SetuptoolsDeprecationWarning: setup.py install is deprecated.\n",
"!!\n",
"\n",
" ********************************************************************************\n",
" Please avoid running ``setup.py`` directly.\n",
" Instead, use pypa/build, pypa/installer, pypa/build or\n",
" other standards-based tools.\n",
"\n",
" See https://blog.ganssle.io/articles/2021/10/setup-py-deprecated.html for details.\n",
" ********************************************************************************\n",
"\n",
"!!\n",
" self.initialize_options()\n",
"running egg_info\n",
"creating basicsr.egg-info\n",
"writing basicsr.egg-info/PKG-INFO\n",
"writing dependency_links to basicsr.egg-info/dependency_links.txt\n",
"writing requirements to basicsr.egg-info/requires.txt\n",
"writing top-level names to basicsr.egg-info/top_level.txt\n",
"writing manifest file 'basicsr.egg-info/SOURCES.txt'\n",
"reading manifest file 'basicsr.egg-info/SOURCES.txt'\n",
"adding license file 'LICENSE'\n",
"writing manifest file 'basicsr.egg-info/SOURCES.txt'\n",
"running build_ext\n",
"Creating /usr/local/lib/python3.10/dist-packages/basicsr.egg-link (link to .)\n",
"Adding basicsr 1.4.2 to easy-install.pth file\n",
"\n",
"Installed /content/EvTexture\n",
"Processing dependencies for basicsr==1.4.2\n",
"Searching for yapf==0.40.2\n",
"Best match: yapf 0.40.2\n",
"Adding yapf 0.40.2 to easy-install.pth file\n",
"Installing yapf script to /usr/local/bin\n",
"Installing yapf-diff script to /usr/local/bin\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for wandb==0.17.3\n",
"Best match: wandb 0.17.3\n",
"Adding wandb 0.17.3 to easy-install.pth file\n",
"Installing wandb script to /usr/local/bin\n",
"Installing wb script to /usr/local/bin\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for tqdm==4.66.4\n",
"Best match: tqdm 4.66.4\n",
"Adding tqdm 4.66.4 to easy-install.pth file\n",
"Installing tqdm script to /usr/local/bin\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for torchvision==0.18.0+cu121\n",
"Best match: torchvision 0.18.0+cu121\n",
"Adding torchvision 0.18.0+cu121 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for torch==2.3.0+cu121\n",
"Best match: torch 2.3.0+cu121\n",
"Adding torch 2.3.0+cu121 to easy-install.pth file\n",
"Installing convert-caffe2-to-onnx script to /usr/local/bin\n",
"Installing convert-onnx-to-caffe2 script to /usr/local/bin\n",
"Installing torchrun script to /usr/local/bin\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for tensorboardX==2.6.2.2\n",
"Best match: tensorboardX 2.6.2.2\n",
"Adding tensorboardX 2.6.2.2 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for tensorboard==2.15.2\n",
"Best match: tensorboard 2.15.2\n",
"Adding tensorboard 2.15.2 to easy-install.pth file\n",
"Installing tensorboard script to /usr/local/bin\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for tb-nightly==2.18.0a20240701\n",
"Best match: tb-nightly 2.18.0a20240701\n",
"Adding tb-nightly 2.18.0a20240701 to easy-install.pth file\n",
"Installing tensorboard script to /usr/local/bin\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for setuptools==67.7.2\n",
"Best match: setuptools 67.7.2\n",
"Adding setuptools 67.7.2 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for scipy==1.11.4\n",
"Best match: scipy 1.11.4\n",
"Adding scipy 1.11.4 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for scikit-image==0.19.3\n",
"Best match: scikit-image 0.19.3\n",
"Adding scikit-image 0.19.3 to easy-install.pth file\n",
"Installing skivi script to /usr/local/bin\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for requests==2.31.0\n",
"Best match: requests 2.31.0\n",
"Adding requests 2.31.0 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for PyYAML==6.0.1\n",
"Best match: PyYAML 6.0.1\n",
"Adding PyYAML 6.0.1 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for Pillow==9.4.0\n",
"Best match: Pillow 9.4.0\n",
"Adding Pillow 9.4.0 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for pandas==2.0.3\n",
"Best match: pandas 2.0.3\n",
"Adding pandas 2.0.3 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for opencv-python==4.8.0.76\n",
"Best match: opencv-python 4.8.0.76\n",
"Adding opencv-python 4.8.0.76 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for numpy==1.25.2\n",
"Best match: numpy 1.25.2\n",
"Adding numpy 1.25.2 to easy-install.pth file\n",
"Installing f2py script to /usr/local/bin\n",
"Installing f2py3 script to /usr/local/bin\n",
"Installing f2py3.10 script to /usr/local/bin\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for matplotlib==3.7.1\n",
"Best match: matplotlib 3.7.1\n",
"Adding matplotlib 3.7.1 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for lmdb==1.5.1\n",
"Best match: lmdb 1.5.1\n",
"Adding lmdb 1.5.1 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for lpips==0.1.4\n",
"Best match: lpips 0.1.4\n",
"Adding lpips 0.1.4 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for h5py==3.9.0\n",
"Best match: h5py 3.9.0\n",
"Adding h5py 3.9.0 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for future==0.18.3\n",
"Best match: future 0.18.3\n",
"Adding future 0.18.3 to easy-install.pth file\n",
"Installing futurize script to /usr/local/bin\n",
"Installing pasteurize script to /usr/local/bin\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for einops==0.8.0\n",
"Best match: einops 0.8.0\n",
"Adding einops 0.8.0 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for argparse==1.4.0\n",
"Best match: argparse 1.4.0\n",
"Adding argparse 1.4.0 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for addict==2.4.0\n",
"Best match: addict 2.4.0\n",
"Adding addict 2.4.0 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for tomli==2.0.1\n",
"Best match: tomli 2.0.1\n",
"Adding tomli 2.0.1 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for platformdirs==4.2.2\n",
"Best match: platformdirs 4.2.2\n",
"Adding platformdirs 4.2.2 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for importlib-metadata==8.0.0\n",
"Best match: importlib-metadata 8.0.0\n",
"Adding importlib-metadata 8.0.0 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for setproctitle==1.3.3\n",
"Best match: setproctitle 1.3.3\n",
"Adding setproctitle 1.3.3 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for sentry-sdk==2.7.1\n",
"Best match: sentry-sdk 2.7.1\n",
"Adding sentry-sdk 2.7.1 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for psutil==5.9.5\n",
"Best match: psutil 5.9.5\n",
"Adding psutil 5.9.5 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for protobuf==3.20.3\n",
"Best match: protobuf 3.20.3\n",
"Adding protobuf 3.20.3 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for GitPython==3.1.43\n",
"Best match: GitPython 3.1.43\n",
"Adding GitPython 3.1.43 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for docker-pycreds==0.4.0\n",
"Best match: docker-pycreds 0.4.0\n",
"Adding docker-pycreds 0.4.0 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for click==8.1.7\n",
"Best match: click 8.1.7\n",
"Adding click 8.1.7 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for triton==2.3.0\n",
"Best match: triton 2.3.0\n",
"Adding triton 2.3.0 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for nvidia-nvtx-cu12==12.1.105\n",
"Best match: nvidia-nvtx-cu12 12.1.105\n",
"Adding nvidia-nvtx-cu12 12.1.105 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for nvidia-nccl-cu12==2.20.5\n",
"Best match: nvidia-nccl-cu12 2.20.5\n",
"Adding nvidia-nccl-cu12 2.20.5 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for nvidia-cusparse-cu12==12.1.0.106\n",
"Best match: nvidia-cusparse-cu12 12.1.0.106\n",
"Adding nvidia-cusparse-cu12 12.1.0.106 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for nvidia-cusolver-cu12==11.4.5.107\n",
"Best match: nvidia-cusolver-cu12 11.4.5.107\n",
"Adding nvidia-cusolver-cu12 11.4.5.107 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for nvidia-curand-cu12==10.3.2.106\n",
"Best match: nvidia-curand-cu12 10.3.2.106\n",
"Adding nvidia-curand-cu12 10.3.2.106 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for nvidia-cufft-cu12==11.0.2.54\n",
"Best match: nvidia-cufft-cu12 11.0.2.54\n",
"Adding nvidia-cufft-cu12 11.0.2.54 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for nvidia-cublas-cu12==12.1.3.1\n",
"Best match: nvidia-cublas-cu12 12.1.3.1\n",
"Adding nvidia-cublas-cu12 12.1.3.1 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for nvidia-cudnn-cu12==8.9.2.26\n",
"Best match: nvidia-cudnn-cu12 8.9.2.26\n",
"Adding nvidia-cudnn-cu12 8.9.2.26 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for nvidia-cuda-cupti-cu12==12.1.105\n",
"Best match: nvidia-cuda-cupti-cu12 12.1.105\n",
"Adding nvidia-cuda-cupti-cu12 12.1.105 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for nvidia-cuda-runtime-cu12==12.1.105\n",
"Best match: nvidia-cuda-runtime-cu12 12.1.105\n",
"Adding nvidia-cuda-runtime-cu12 12.1.105 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for nvidia-cuda-nvrtc-cu12==12.1.105\n",
"Best match: nvidia-cuda-nvrtc-cu12 12.1.105\n",
"Adding nvidia-cuda-nvrtc-cu12 12.1.105 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for fsspec==2023.6.0\n",
"Best match: fsspec 2023.6.0\n",
"Adding fsspec 2023.6.0 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for jinja2==3.1.4\n",
"Best match: jinja2 3.1.4\n",
"Adding jinja2 3.1.4 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for networkx==3.3\n",
"Best match: networkx 3.3\n",
"Adding networkx 3.3 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for sympy==1.12.1\n",
"Best match: sympy 1.12.1\n",
"Adding sympy 1.12.1 to easy-install.pth file\n",
"Installing isympy script to /usr/local/bin\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for typing-extensions==4.12.2\n",
"Best match: typing-extensions 4.12.2\n",
"Adding typing-extensions 4.12.2 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for filelock==3.15.4\n",
"Best match: filelock 3.15.4\n",
"Adding filelock 3.15.4 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for packaging==24.1\n",
"Best match: packaging 24.1\n",
"Adding packaging 24.1 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for werkzeug==3.0.3\n",
"Best match: werkzeug 3.0.3\n",
"Adding werkzeug 3.0.3 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for tensorboard-data-server==0.7.2\n",
"Best match: tensorboard-data-server 0.7.2\n",
"Adding tensorboard-data-server 0.7.2 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for six==1.16.0\n",
"Best match: six 1.16.0\n",
"Adding six 1.16.0 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for Markdown==3.6\n",
"Best match: Markdown 3.6\n",
"Adding Markdown 3.6 to easy-install.pth file\n",
"Installing markdown_py script to /usr/local/bin\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for google-auth-oauthlib==1.2.0\n",
"Best match: google-auth-oauthlib 1.2.0\n",
"Adding google-auth-oauthlib 1.2.0 to easy-install.pth file\n",
"Installing google-oauthlib-tool script to /usr/local/bin\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for google-auth==2.27.0\n",
"Best match: google-auth 2.27.0\n",
"Adding google-auth 2.27.0 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for grpcio==1.64.1\n",
"Best match: grpcio 1.64.1\n",
"Adding grpcio 1.64.1 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for absl-py==1.4.0\n",
"Best match: absl-py 1.4.0\n",
"Adding absl-py 1.4.0 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for pywavelets==1.6.0\n",
"Best match: pywavelets 1.6.0\n",
"Adding pywavelets 1.6.0 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for tifffile==2024.6.18\n",
"Best match: tifffile 2024.6.18\n",
"Adding tifffile 2024.6.18 to easy-install.pth file\n",
"Installing lsm2bin script to /usr/local/bin\n",
"Installing tiff2fsspec script to /usr/local/bin\n",
"Installing tiffcomment script to /usr/local/bin\n",
"Installing tifffile script to /usr/local/bin\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for imageio==2.31.6\n",
"Best match: imageio 2.31.6\n",
"Adding imageio 2.31.6 to easy-install.pth file\n",
"Installing imageio_download_bin script to /usr/local/bin\n",
"Installing imageio_remove_bin script to /usr/local/bin\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for certifi==2024.6.2\n",
"Best match: certifi 2024.6.2\n",
"Adding certifi 2024.6.2 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for urllib3==2.0.7\n",
"Best match: urllib3 2.0.7\n",
"Adding urllib3 2.0.7 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for idna==3.7\n",
"Best match: idna 3.7\n",
"Adding idna 3.7 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for charset-normalizer==3.3.2\n",
"Best match: charset-normalizer 3.3.2\n",
"Adding charset-normalizer 3.3.2 to easy-install.pth file\n",
"Installing normalizer script to /usr/local/bin\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for tzdata==2024.1\n",
"Best match: tzdata 2024.1\n",
"Adding tzdata 2024.1 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for pytz==2023.4\n",
"Best match: pytz 2023.4\n",
"Adding pytz 2023.4 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for python-dateutil==2.8.2\n",
"Best match: python-dateutil 2.8.2\n",
"Adding python-dateutil 2.8.2 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for pyparsing==3.1.2\n",
"Best match: pyparsing 3.1.2\n",
"Adding pyparsing 3.1.2 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for kiwisolver==1.4.5\n",
"Best match: kiwisolver 1.4.5\n",
"Adding kiwisolver 1.4.5 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for fonttools==4.53.0\n",
"Best match: fonttools 4.53.0\n",
"Adding fonttools 4.53.0 to easy-install.pth file\n",
"Installing fonttools script to /usr/local/bin\n",
"Installing pyftmerge script to /usr/local/bin\n",
"Installing pyftsubset script to /usr/local/bin\n",
"Installing ttx script to /usr/local/bin\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for cycler==0.12.1\n",
"Best match: cycler 0.12.1\n",
"Adding cycler 0.12.1 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for contourpy==1.2.1\n",
"Best match: contourpy 1.2.1\n",
"Adding contourpy 1.2.1 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for zipp==3.19.2\n",
"Best match: zipp 3.19.2\n",
"Adding zipp 3.19.2 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for gitdb==4.0.11\n",
"Best match: gitdb 4.0.11\n",
"Adding gitdb 4.0.11 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for nvidia-nvjitlink-cu12==12.5.82\n",
"Best match: nvidia-nvjitlink-cu12 12.5.82\n",
"Adding nvidia-nvjitlink-cu12 12.5.82 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for MarkupSafe==2.1.5\n",
"Best match: MarkupSafe 2.1.5\n",
"Adding MarkupSafe 2.1.5 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for mpmath==1.3.0\n",
"Best match: mpmath 1.3.0\n",
"Adding mpmath 1.3.0 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for requests-oauthlib==1.3.1\n",
"Best match: requests-oauthlib 1.3.1\n",
"Adding requests-oauthlib 1.3.1 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for rsa==4.9\n",
"Best match: rsa 4.9\n",
"Adding rsa 4.9 to easy-install.pth file\n",
"Installing pyrsa-decrypt script to /usr/local/bin\n",
"Installing pyrsa-encrypt script to /usr/local/bin\n",
"Installing pyrsa-keygen script to /usr/local/bin\n",
"Installing pyrsa-priv2pub script to /usr/local/bin\n",
"Installing pyrsa-sign script to /usr/local/bin\n",
"Installing pyrsa-verify script to /usr/local/bin\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for pyasn1-modules==0.4.0\n",
"Best match: pyasn1-modules 0.4.0\n",
"Adding pyasn1-modules 0.4.0 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for cachetools==5.3.3\n",
"Best match: cachetools 5.3.3\n",
"Adding cachetools 5.3.3 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for smmap==5.0.1\n",
"Best match: smmap 5.0.1\n",
"Adding smmap 5.0.1 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for oauthlib==3.2.2\n",
"Best match: oauthlib 3.2.2\n",
"Adding oauthlib 3.2.2 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Searching for pyasn1==0.6.0\n",
"Best match: pyasn1 0.6.0\n",
"Adding pyasn1 0.6.0 to easy-install.pth file\n",
"\n",
"Using /usr/local/lib/python3.10/dist-packages\n",
"Finished processing dependencies for basicsr==1.4.2\n"
]
}
],
"source": [
"!git clone https://github.com/DachunKai/EvTexture\n",
"!mkdir -p /content/EvTexture/experiments/pretrained_models/EvTexture\n",
"\n",
"!wget https://github.com/DachunKai/EvTexture/releases/download/v0.0/EvTexture_REDS_BIx4.pth -O /content/EvTexture/experiments/pretrained_models/EvTexture/EvTexture_REDS_BIx4.pth\n",
"!wget https://github.com/DachunKai/EvTexture/releases/download/v0.0/EvTexture_Vimeo90K_BIx4.pth -O /content/EvTexture/experiments/pretrained_models/EvTexture/EvTexture_Vimeo90K_BIx4.pth\n",
"!wget https://github.com/DachunKai/EvTexture/releases/download/v0.0/test_sets_REDS4_h5.zip -O /content/EvTexture/datasets/test_sets_REDS4_h5.zip\n",
"!wget https://github.com/DachunKai/EvTexture/releases/download/v0.0/test_sets_Vid4_h5.zip -O /content/EvTexture/datasets/test_sets_Vid4_h5.zip\n",
"\n",
"%cd /content/EvTexture/datasets\n",
"!unzip -o test_sets_Vid4_h5.zip\n",
"!unzip -o test_sets_REDS4_h5.zip\n",
"\n",
"%cd /content/EvTexture\n",
"!pip install -r requirements.txt\n",
"!python setup.py develop"
]
},
{
"cell_type": "markdown",
"source": [
"Test on Vid4 Dataset"
],
"metadata": {
"id": "Oeq6TMXn57Cu"
}
},
{
"cell_type": "code",
"source": [
"%cd /content/EvTexture\n",
"!python basicsr/test.py -opt options/test/EvTexture/test_EvTexture_Vid4_BIx4.yml"
],
"metadata": {
"id": "uLgjmp5A59x2"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"Test on REDS4 Dataset"
],
"metadata": {
"id": "Bsviejz45_W-"
}
},
{
"cell_type": "code",
"source": [
"%cd /content/EvTexture\n",
"!python basicsr/test.py -opt options/test/EvTexture/test_EvTexture_REDS4_BIx4.yml"
],
"metadata": {
"id": "iCpZwdZS6BF9"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"The inference results will be saved under /content/EvTexture/results/EvTexture_Vid4_BIx4 and /content/EvTexture/results/EvTexture_REDS4_BIx4, respectively."
],
"metadata": {
"id": "hg6KCAD-6HZm"
}
}
]
}
\ No newline at end of file
LICENSE 0 → 100644
View file @ a75d2bda
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
README.md 0 → 100644
View file @ a75d2bda
# EvTexture
## 论文
**EvTexture: Event-driven Texture Enhancement for Video Super-Resolution**
* https://arxiv.org/abs/2406.13457
## 模型结构
EvTexture采用双向循环网络，其中特征向前和向后传播。
![alt text](readme_imgs/models.png)
## 算法原理
在每个时间戳，使用一个运动分支和一个并行的纹理分支，以明确增强纹理区域的恢复。
![alt text](readme_imgs/alg.png)
## 环境配置
### Docker（方法一）
docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-ubuntu20.04-dtk24.04.1-py3.10
docker run --shm-size 50g --network=host --name=evtexture --privileged --device=/dev/kfd --device=/dev/dri --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v 项目地址(绝对路径):/home/ -v /opt/hyhal:/opt/hyhal:ro -it <your IMAGE ID> bash
pip install -r requirements.txt
python setup.py develop
### Dockerfile（方法二）
docker build -t <IMAGE_NAME>:<TAG> .
docker run --shm-size 50g --network=host --name=evtexture --privileged --device=/dev/kfd --device=/dev/dri --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v 项目地址(绝对路径):/home/ -v /opt/hyhal:/opt/hyhal:ro -it <your IMAGE ID> bash
pip install -r requirements.txt
python setup.py develop
### Anaconda (方法三)
1、关于本项目DCU显卡所需的特殊深度学习库可从光合开发者社区下载安装：
https://developer.hpccube.com/tool/
DTK驱动：dtk24.04.1
python：python3.10
torch: 2.1.0
torchvision: 0.16.0
Tips：以上dtk驱动、python、torch等DCU相关工具版本需要严格一一对应
2、其它非特殊库参照requirements.txt安装
pip install -r requirements.txt
python setup.py develop
## 数据集
[OneDriver](https://1drv.ms/f/c/2d90e71fb9eb254f/EnMm8c2mP_FPv6lwt1jy01YB6bQhoPQ25vtzAhycYisERw?e=DiI2Ab) | [SCNet](http://113.200.138.88:18080/aidatasets/project-dependency/evtexture) 高速下载通道
### 数据处理
该部分仅展示整体流程，详细请参考[DataPreparation](datasets/DataPreparation.md)。
- 将原始视频转换为图像（参考`datasets/utils/video_to_img.py`）；
- 将图像转换为HWC格式numpy类型的数据并以h5结构存储在`/path/to/xx.h5/images`中;
- 将视频转换为事件，包含forward及backward，分别存储在`/path/to/xx.h5/voxels_f`及`/path/to/xx.h5/voxels_b`中。
以上步骤可参考`datasets/dataproparation.py`，注意，该脚本并非官方版本，使用前请仔细检查。执行下述命令准备相应的环境。
python -m pip install pybind11
export CMAKE_PREFIX_PATH=/usr/local/lib/python3.10/site-packages/pybind11/share/cmake/pybind11/:$CMAKE_PREFIX_PATH
sudo apt update
sudo apt install libopencv-dev
export CMAKE_PREFIX_PATH=/usr/lib/x86_64-linux-gnu/cmake/opencv4/:$CMAKE_PREFIX_PATH
下载 eigen3 https://gitlab.com/libeigen/eigen/-/releases/3.4.0 (zip版本)
unzip /path/to/eigen3.zip
cd /path/to/eigen3
mkdir build && cd build
cmake .. && make
make install
# 安装boost
sudo apt install build-essential libboost-system-dev libboost-thread-dev libboost-program-options-dev libboost-test-dev
sudo apt install libboost-all-dev
cd others/rpg_vid2e/esim_pyt && python setup.py install
注意：数据处理或下载完成后，需按照`basicsr/data/meta_info`中的文件格式创建相应的文件。
## 推理
export HIP_VISIBLE_DEVICES=0
# 1表示使用DCU数量
bash scripts/dist_test.sh 1 options/test/EvTexture/test_EvTexture_REDS4_BIx4.yml
bash scripts/dist_test.sh 1 options/test/EvTexture/test_EvTexture_Vid4_BIx4.yml
## result
原始视频
<video width="320" height="240" controls>
<source src="readme_imgs/ori_10y.avi" type="video/avi">
Your browser does not support the video tag.
</video>
修复后视频
<video width="320" height="240" controls>
<source src="readme_imgs/vid4_10y.avi" type="video/avi">
Your browser does not support the video tag.
</video>
### 精度
无
## 应用场景
### 算法类别
`视频超分`
### 热点应用行业
`安防,媒体,环境`
## 预训练权重
[OneDriver](https://1drv.ms/f/c/2d90e71fb9eb254f/EnMm8c2mP_FPv6lwt1jy01YB6bQhoPQ25vtzAhycYisERw?e=DiI2Ab) | [SCNet](http://113.200.138.88:18080/aimodels/findsource-dependency/evtexture) 高速下载通道
experiments/
└── pretrained_models
└── EvTexture
├── EvTexture_REDS_BIx4.pth
└── EvTexture_Vimeo90K_BIx4.pth
## 源码仓库及问题反馈
* https://developer.hpccube.com/codes/modelzoo/evtexture_pytorch
## 参考资料
* https://github.com/DachunKai/EvTexture/tree/main
README_official.md 0 → 100644
View file @ a75d2bda
# [EvTexture (ICML 2024)](https://icml.cc/virtual/2024/poster/34032)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/evtexture-event-driven-texture-enhancement/video-super-resolution-on-vid4-4x-upscaling)](https://paperswithcode.com/sota/video-super-resolution-on-vid4-4x-upscaling?p=evtexture-event-driven-texture-enhancement)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/evtexture-event-driven-texture-enhancement/video-super-resolution-on-reds4-4x-upscaling)](https://paperswithcode.com/sota/video-super-resolution-on-reds4-4x-upscaling?p=evtexture-event-driven-texture-enhancement)
Official Pytorch implementation for the "EvTexture: Event-driven Texture Enhancement for Video Super-Resolution" paper (ICML 2024).
<p align="center">
🌐 <a href="https://dachunkai.github.io/evtexture.github.io/" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2406.13457" target="_blank">Paper</a> | 🖼️ <a href="https://docs.google.com/presentation/d/1nbDb39TFb374DzBwdz5v20kIREUA0nBH/edit?usp=sharing" target="_blank">Poster</a> <br>
</p>
**Authors**: [Dachun Kai](https://github.com/DachunKai/)<sup>[:email:️](mailto:dachunkai@mail.ustc.edu.cn)</sup>, Jiayao Lu, [Yueyi Zhang](https://scholar.google.com.hk/citations?user=LatWlFAAAAAJ&hl=zh-CN&oi=ao)<sup>[:email:️](mailto:zhyuey@ustc.edu.cn)</sup>, [Xiaoyan Sun](https://scholar.google.com/citations?user=VRG3dw4AAAAJ&hl=zh-CN), *University of Science and Technology of China*
**Feel free to ask questions. If our work helps, please don't hesitate to give us a :star:!**
## :rocket: News
- [ ] Release training code
- [x] 2024/07/02: Release the colab file for a quick test
- [x] 2024/06/28: Release details to prepare datasets
- [x] 2024/06/08: Publish docker image
- [x] 2024/06/08: Release pretrained models and test sets for quick testing
- [x] 2024/06/07: Video demos released
- [x] 2024/05/25: Initialize the repository
- [x] 2024/05/02: :tada: :tada: Our paper was accepted in ICML'2024
## :bookmark: Table of Content
1. [Video Demos](#video-demos)
2. [Code](#code)
3. [Citation](#citation)
4. [Contact](#contact)
5. [License and Acknowledgement](#license-and-acknowledgement)
## :fire: Video Demos
A $4\times$ upsampling results on the [Vid4](https://paperswithcode.com/sota/video-super-resolution-on-vid4-4x-upscaling) and [REDS4](https://paperswithcode.com/dataset/reds) test sets.
https://github.com/DachunKai/EvTexture/assets/66354783/fcf48952-ea48-491c-a4fb-002bb2d04ad3
https://github.com/DachunKai/EvTexture/assets/66354783/ea3dd475-ba8f-411f-883d-385a5fdf7ff6
https://github.com/DachunKai/EvTexture/assets/66354783/e1e6b340-64b3-4d94-90ee-54f025f255fb
https://github.com/DachunKai/EvTexture/assets/66354783/01880c40-147b-4c02-8789-ced0c1bff9c4
## Code
### Installation
* Dependencies: [Miniconda](https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh), [CUDA Toolkit 11.1.1](https://developer.nvidia.com/cuda-11.1.1-download-archive), [torch 1.10.2+cu111](https://download.pytorch.org/whl/cu111/torch-1.10.2%2Bcu111-cp37-cp37m-linux_x86_64.whl), and [torchvision 0.11.3+cu111](https://download.pytorch.org/whl/cu111/torchvision-0.11.3%2Bcu111-cp37-cp37m-linux_x86_64.whl).
* Run in Conda
```bash
conda create -y -n evtexture python=3.7
conda activate evtexture
pip install torch-1.10.2+cu111-cp37-cp37m-linux_x86_64.whl
pip install torchvision-0.11.3+cu111-cp37-cp37m-linux_x86_64.whl
git clone https://github.com/DachunKai/EvTexture.git
cd EvTexture && pip install -r requirements.txt && python setup.py develop
```
* Run in Docker :clap:
Note: before running the Docker image, make sure to install nvidia-docker by following the [official instructions](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html).
[Option 1] Directly pull the published Docker image we have provided from [Alibaba Cloud](https://cr.console.aliyun.com/cn-hangzhou/instances).
```bash
docker pull registry.cn-hangzhou.aliyuncs.com/dachunkai/evtexture:latest
```
[Option 2] We also provide a [Dockerfile](https://github.com/DachunKai/EvTexture/blob/main/docker/Dockerfile) that you can use to build the image yourself.
```bash
cd EvTexture && docker build -t evtexture ./docker
```
The pulled or self-built Docker image containes a complete conda environment named `evtexture`. After running the image, you can mount your data and operate within this environment.
```bash
source activate evtexture && cd EvTexture && python setup.py develop
```
### Test
1. Download the pretrained models from ([Releases](https://github.com/DachunKai/EvTexture/releases) / [Onedrive](https://1drv.ms/f/c/2d90e71fb9eb254f/EnMm8c2mP_FPv6lwt1jy01YB6bQhoPQ25vtzAhycYisERw?e=DiI2Ab) / [Google Drive](https://drive.google.com/drive/folders/1oqOAZbroYW-yfyzIbLYPMJ2ZQmaaCXKy?usp=sharing) / [Baidu Cloud](https://pan.baidu.com/s/161bfWZGVH1UBCCka93ImqQ?pwd=n8hg)(n8hg)) and place them to `experiments/pretrained_models/EvTexture/`. The network architecture code is in [evtexture_arch.py](https://github.com/DachunKai/EvTexture/blob/main/basicsr/archs/evtexture_arch.py).
* *EvTexture_REDS_BIx4.pth*: trained on REDS dataset with BI degradation for $4\times$ SR scale.
* *EvTexture_Vimeo90K_BIx4.pth*: trained on Vimeo-90K dataset with BI degradation for $4\times$ SR scale.
2. Download the preprocessed test sets (including events) for REDS4 and Vid4 from ([Releases](https://github.com/DachunKai/EvTexture/releases) / [Onedrive](https://1drv.ms/f/c/2d90e71fb9eb254f/EnMm8c2mP_FPv6lwt1jy01YB6bQhoPQ25vtzAhycYisERw?e=DiI2Ab) / [Google Drive](https://drive.google.com/drive/folders/1oqOAZbroYW-yfyzIbLYPMJ2ZQmaaCXKy?usp=sharing) / [Baidu Cloud](https://pan.baidu.com/s/161bfWZGVH1UBCCka93ImqQ?pwd=n8hg)(n8hg)), and place them to `datasets/`.
* *Vid4_h5*: HDF5 files containing preprocessed test datasets for Vid4.
* *REDS4_h5*: HDF5 files containing preprocessed test datasets for REDS4.
3. Run the following command:
* Test on Vid4 for 4x VSR:
```bash
./scripts/dist_test.sh [num_gpus] options/test/EvTexture/test_EvTexture_Vid4_BIx4.yml
```
* Test on REDS4 for 4x VSR:
```bash
./scripts/dist_test.sh [num_gpus] options/test/EvTexture/test_EvTexture_REDS4_BIx4.yml
```
This will generate the inference results in `results/`. The output results on REDS4 and Vid4 can be downloaded from ([Releases](https://github.com/DachunKai/EvTexture/releases) / [Onedrive](https://1drv.ms/f/c/2d90e71fb9eb254f/EnMm8c2mP_FPv6lwt1jy01YB6bQhoPQ25vtzAhycYisERw?e=DiI2Ab) / [Google Drive](https://drive.google.com/drive/folders/1oqOAZbroYW-yfyzIbLYPMJ2ZQmaaCXKy?usp=sharing) / [Baidu Cloud](https://pan.baidu.com/s/161bfWZGVH1UBCCka93ImqQ?pwd=n8hg)(n8hg)).
### Data Preparation
* Both video and event data are required as input, as shown in the [snippet](https://github.com/DachunKai/EvTexture/blob/main/basicsr/archs/evtexture_arch.py#L70). We package each video and its event data into an [HDF5](https://docs.h5py.org/en/stable/quick.html#quick) file.
* Example: The structure of `calendar.h5` file from the Vid4 dataset is shown below.
```arduino
calendar.h5
├── images
│ ├── 000000 # frame, ndarray, [H, W, C]
│ ├── ...
├── voxels_f
│ ├── 000000 # forward event voxel, ndarray, [Bins, H, W]
│ ├── ...
├── voxels_b
│ ├── 000000 # backward event voxel, ndarray, [Bins, H, W]
│ ├── ...
```
* To simulate and generate the event voxels, refer to the dataset preparation details in [DataPreparation.md](https://github.com/DachunKai/EvTexture/blob/main/datasets/DataPreparation.md).
### Inference on your own video
> **:heart: Seeking Collaboration**: For issues [#6](https://github.com/DachunKai/EvTexture/issues/6) and [#7](https://github.com/DachunKai/EvTexture/issues/7), our method can indeed perform inference on videos without event data. The solution is to use an event camera simulator, such as [vid2e](https://github.com/uzh-rpg/rpg_vid2e), to generate event data from the video, and then input both the video data and the generated event data into our model. This part, however, may require extensive engineering work to package everything into a script, as detailed in [DataPreparation.md](https://github.com/DachunKai/EvTexture/blob/main/datasets/DataPreparation.md). We currently do not have enough time to undertake this task, so we are looking for collaborators to join us in this effort! :blush:
## :blush: Citation
If you find the code and pre-trained models useful for your research, please consider citing our paper. :smiley:
```
@inproceedings{kai2024evtexture,
title={Ev{T}exture: {E}vent-driven {T}exture {E}nhancement for {V}ideo {S}uper-{R}esolution},
author={Kai, Dachun and Lu, Jiayao and Zhang, Yueyi and Sun, Xiaoyan},
booktitle={International Conference on Machine Learning},
year={2024},
organization={PMLR}
}
```
## Contact
If you meet any problems, please describe them in issues or contact:
* Dachun Kai: <dachunkai@mail.ustc.edu.cn>
## License and Acknowledgement
This project is released under the Apache-2.0 license. Our work is built upon [BasicSR](https://github.com/XPixelGroup/BasicSR), which is an open source toolbox for image/video restoration tasks. Thanks to the inspirations and codes from [RAFT](https://github.com/princeton-vl/RAFT), [event_utils](https://github.com/TimoStoff/event_utils) and [EvTexture-jupyter](https://github.com/camenduru/EvTexture-jupyter).
basicsr/__init__.py 0 → 100644
View file @ a75d2bda
# https://github.com/xinntao/BasicSR
# flake8: noqa
from .archs import *
from .data import *
from .losses import *
from .metrics import *
from .models import *
from .ops import *
from .test import *
from .train import *
from .utils import *
from .version import __gitsha__, __version__
basicsr/archs/__init__.py 0 → 100644
View file @ a75d2bda
import importlib
from copy import deepcopy
from os import path as osp
from basicsr.utils import get_root_logger, scandir
from basicsr.utils.registry import ARCH_REGISTRY
__all__ = ['build_network']
# automatically scan and import arch modules for registry
# scan all the files under the 'archs' folder and collect files ending with '_arch.py'
arch_folder = osp.dirname(osp.abspath(__file__))
arch_filenames = [osp.splitext(osp.basename(v))[0] for v in scandir(arch_folder) if v.endswith('_arch.py')]
# import all the arch modules
_arch_modules = [importlib.import_module(f'basicsr.archs.{file_name}') for file_name in arch_filenames]
def build_network(opt):
opt = deepcopy(opt)
network_type = opt.pop('type')
net = ARCH_REGISTRY.get(network_type)(**opt)
logger = get_root_logger()
logger.info(f'Network [{net.__class__.__name__}] is created.')
return net
basicsr/archs/arch_util.py 0 → 100644
View file @ a75d2bda
import collections.abc
import math
import torch
import torchvision
import warnings
from distutils.version import LooseVersion
from itertools import repeat
from torch import nn as nn
from torch.nn import functional as F
from torch.nn import init as init
from torch.nn.modules.batchnorm import _BatchNorm
from basicsr.ops.dcn import ModulatedDeformConvPack, modulated_deform_conv
from basicsr.utils import get_root_logger
@torch.no_grad()
def default_init_weights(module_list, scale=1, bias_fill=0, **kwargs):
"""Initialize network weights.
Args:
module_list (list[nn.Module] | nn.Module): Modules to be initialized.
scale (float): Scale initialized weights, especially for residual
blocks. Default: 1.
bias_fill (float): The value to fill bias. Default: 0
kwargs (dict): Other arguments for initialization function.
"""
if not isinstance(module_list, list):
module_list = [module_list]
for module in module_list:
for m in module.modules():
if isinstance(m, nn.Conv2d):
init.kaiming_normal_(m.weight, **kwargs)
m.weight.data *= scale
if m.bias is not None:
m.bias.data.fill_(bias_fill)
elif isinstance(m, nn.Linear):
init.kaiming_normal_(m.weight, **kwargs)
m.weight.data *= scale
if m.bias is not None:
m.bias.data.fill_(bias_fill)
elif isinstance(m, _BatchNorm):
init.constant_(m.weight, 1)
if m.bias is not None:
m.bias.data.fill_(bias_fill)
def make_layer(basic_block, num_basic_block, **kwarg):
"""Make layers by stacking the same blocks.
Args:
basic_block (nn.module): nn.module class for basic block.
num_basic_block (int): number of blocks.
Returns:
nn.Sequential: Stacked blocks in nn.Sequential.
"""
layers = []
for _ in range(num_basic_block):
layers.append(basic_block(**kwarg))
return nn.Sequential(*layers)
class ResidualBlockNoBN(nn.Module):
"""Residual block without BN.
Args:
num_feat (int): Channel number of intermediate features.
Default: 64.
res_scale (float): Residual scale. Default: 1.
pytorch_init (bool): If set to True, use pytorch default init,
otherwise, use default_init_weights. Default: False.
"""
def __init__(self, num_feat=64, res_scale=1, pytorch_init=False):
super(ResidualBlockNoBN, self).__init__()
self.res_scale = res_scale
self.conv1 = nn.Conv2d(num_feat, num_feat, 3, 1, 1, bias=True)
self.conv2 = nn.Conv2d(num_feat, num_feat, 3, 1, 1, bias=True)
self.relu = nn.ReLU(inplace=True)
if not pytorch_init:
default_init_weights([self.conv1, self.conv2], 0.1)
def forward(self, x):
identity = x
out = self.conv2(self.relu(self.conv1(x)))
return identity + out * self.res_scale
class Upsample(nn.Sequential):
"""Upsample module.
Args:
scale (int): Scale factor. Supported scales: 2^n and 3.
num_feat (int): Channel number of intermediate features.
"""
def __init__(self, scale, num_feat):
m = []
if (scale & (scale - 1)) == 0: # scale = 2^n
for _ in range(int(math.log(scale, 2))):
m.append(nn.Conv2d(num_feat, 4 * num_feat, 3, 1, 1))
m.append(nn.PixelShuffle(2))
elif scale == 3:
m.append(nn.Conv2d(num_feat, 9 * num_feat, 3, 1, 1))
m.append(nn.PixelShuffle(3))
else:
raise ValueError(f'scale {scale} is not supported. Supported scales: 2^n and 3.')
super(Upsample, self).__init__(*m)
def flow_warp(x, flow, interp_mode='bilinear', padding_mode='zeros', align_corners=True):
"""Warp an image or feature map with optical flow.
Args:
x (Tensor): Tensor with size (n, c, h, w).
flow (Tensor): Tensor with size (n, h, w, 2), normal value.
interp_mode (str): 'nearest' or 'bilinear'. Default: 'bilinear'.
padding_mode (str): 'zeros' or 'border' or 'reflection'.
Default: 'zeros'.
align_corners (bool): Before pytorch 1.3, the default value is
align_corners=True. After pytorch 1.3, the default value is
align_corners=False. Here, we use the True as default.
Returns:
Tensor: Warped image or feature map.
"""
assert x.size()[-2:] == flow.size()[1:3]
_, _, h, w = x.size()
# create mesh grid
grid_y, grid_x = torch.meshgrid(torch.arange(0, h).type_as(x), torch.arange(0, w).type_as(x))
grid = torch.stack((grid_x, grid_y), 2).float() # W(x), H(y), 2
grid.requires_grad = False
vgrid = grid + flow
# scale grid to [-1,1]
vgrid_x = 2.0 * vgrid[:, :, :, 0] / max(w - 1, 1) - 1.0
vgrid_y = 2.0 * vgrid[:, :, :, 1] / max(h - 1, 1) - 1.0
vgrid_scaled = torch.stack((vgrid_x, vgrid_y), dim=3)
output = F.grid_sample(x, vgrid_scaled, mode=interp_mode, padding_mode=padding_mode, align_corners=align_corners)
# TODO, what if align_corners=False
return output
def resize_flow(flow, size_type, sizes, interp_mode='bilinear', align_corners=False):
"""Resize a flow according to ratio or shape.
Args:
flow (Tensor): Precomputed flow. shape [N, 2, H, W].
size_type (str): 'ratio' or 'shape'.
sizes (list[int | float]): the ratio for resizing or the final output
shape.
1) The order of ratio should be [ratio_h, ratio_w]. For
downsampling, the ratio should be smaller than 1.0 (i.e., ratio
< 1.0). For upsampling, the ratio should be larger than 1.0 (i.e.,
ratio > 1.0).
2) The order of output_size should be [out_h, out_w].
interp_mode (str): The mode of interpolation for resizing.
Default: 'bilinear'.
align_corners (bool): Whether align corners. Default: False.
Returns:
Tensor: Resized flow.
"""
_, _, flow_h, flow_w = flow.size()
if size_type == 'ratio':
output_h, output_w = int(flow_h * sizes[0]), int(flow_w * sizes[1])
elif size_type == 'shape':
output_h, output_w = sizes[0], sizes[1]
else:
raise ValueError(f'Size type should be ratio or shape, but got type {size_type}.')
input_flow = flow.clone()
ratio_h = output_h / flow_h
ratio_w = output_w / flow_w
input_flow[:, 0, :, :] *= ratio_w
input_flow[:, 1, :, :] *= ratio_h
resized_flow = F.interpolate(
input=input_flow, size=(output_h, output_w), mode=interp_mode, align_corners=align_corners)
return resized_flow
# TODO: may write a cpp file
def pixel_unshuffle(x, scale):
""" Pixel unshuffle.
Args:
x (Tensor): Input feature with shape (b, c, hh, hw).
scale (int): Downsample ratio.
Returns:
Tensor: the pixel unshuffled feature.
"""
b, c, hh, hw = x.size()
out_channel = c * (scale**2)
assert hh % scale == 0 and hw % scale == 0
h = hh // scale
w = hw // scale
x_view = x.view(b, c, h, scale, w, scale)
return x_view.permute(0, 1, 3, 5, 2, 4).reshape(b, out_channel, h, w)
class DCNv2Pack(ModulatedDeformConvPack):
"""Modulated deformable conv for deformable alignment.
Different from the official DCNv2Pack, which generates offsets and masks
from the preceding features, this DCNv2Pack takes another different
features to generate offsets and masks.
``Paper: Delving Deep into Deformable Alignment in Video Super-Resolution``
"""
def forward(self, x, feat):
out = self.conv_offset(feat)
o1, o2, mask = torch.chunk(out, 3, dim=1)
offset = torch.cat((o1, o2), dim=1)
mask = torch.sigmoid(mask)
offset_absmean = torch.mean(torch.abs(offset))
if offset_absmean > 50:
logger = get_root_logger()
logger.warning(f'Offset abs mean is {offset_absmean}, larger than 50.')
if LooseVersion(torchvision.__version__) >= LooseVersion('0.9.0'):
return torchvision.ops.deform_conv2d(x, offset, self.weight, self.bias, self.stride, self.padding,
self.dilation, mask)
else:
return modulated_deform_conv(x, offset, mask, self.weight, self.bias, self.stride, self.padding,
self.dilation, self.groups, self.deformable_groups)
def _no_grad_trunc_normal_(tensor, mean, std, a, b):
# From: https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/layers/weight_init.py
# Cut & paste from PyTorch official master until it's in a few official releases - RW
# Method based on https://people.sc.fsu.edu/~jburkardt/presentations/truncated_normal.pdf
def norm_cdf(x):
# Computes standard normal cumulative distribution function
return (1. + math.erf(x / math.sqrt(2.))) / 2.
if (mean < a - 2 * std) or (mean > b + 2 * std):
warnings.warn(
'mean is more than 2 std from [a, b] in nn.init.trunc_normal_. '
'The distribution of values may be incorrect.',
stacklevel=2)
with torch.no_grad():
# Values are generated by using a truncated uniform distribution and
# then using the inverse CDF for the normal distribution.
# Get upper and lower cdf values
low = norm_cdf((a - mean) / std)
up = norm_cdf((b - mean) / std)
# Uniformly fill tensor with values from [low, up], then translate to
# [2l-1, 2u-1].
tensor.uniform_(2 * low - 1, 2 * up - 1)
# Use inverse cdf transform for normal distribution to get truncated
# standard normal
tensor.erfinv_()
# Transform to proper mean, std
tensor.mul_(std * math.sqrt(2.))
tensor.add_(mean)
# Clamp to ensure it's in the proper range
tensor.clamp_(min=a, max=b)
return tensor
def trunc_normal_(tensor, mean=0., std=1., a=-2., b=2.):
r"""Fills the input Tensor with values drawn from a truncated
normal distribution.
From: https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/layers/weight_init.py
The values are effectively drawn from the
normal distribution :math:`\mathcal{N}(\text{mean}, \text{std}^2)`
with values outside :math:`[a, b]` redrawn until they are within
the bounds. The method used for generating the random values works
best when :math:`a \leq \text{mean} \leq b`.
Args:
tensor: an n-dimensional `torch.Tensor`
mean: the mean of the normal distribution
std: the standard deviation of the normal distribution
a: the minimum cutoff value
b: the maximum cutoff value
Examples:
>>> w = torch.empty(3, 5)
>>> nn.init.trunc_normal_(w)
"""
return _no_grad_trunc_normal_(tensor, mean, std, a, b)
# From PyTorch
def _ntuple(n):
def parse(x):
if isinstance(x, collections.abc.Iterable):
return x
return tuple(repeat(x, n))
return parse
to_1tuple = _ntuple(1)
to_2tuple = _ntuple(2)
to_3tuple = _ntuple(3)
to_4tuple = _ntuple(4)
to_ntuple = _ntuple
def closest_larger_multiple_of_minimum_size(size, minimum_size):
return int(math.ceil(size / minimum_size) * minimum_size)
class SizeAdapter(object):
"""Converts size of input to standard size.
Practical deep network works only with input images
which height and width are multiples of a minimum size.
This class allows to pass to the network images of arbitrary
size, by padding the input to the closest multiple
and unpadding the network's output to the original size.
"""
def __init__(self, minimum_size=64):
self._minimum_size = minimum_size
self._pixels_pad_to_width = None
self._pixels_pad_to_height = None
def _closest_larger_multiple_of_minimum_size(self, size):
return closest_larger_multiple_of_minimum_size(size, self._minimum_size)
def pad(self, network_input):
"""Returns "network_input" paded with zeros to the "standard" size.
The "standard" size correspond to the height and width that
are closest multiples of "minimum_size". The method pads
height and width and and saves padded values. These
values are then used by "unpad_output" method.
"""
height, width = network_input.size()[-2:]
self._pixels_pad_to_height = (self._closest_larger_multiple_of_minimum_size(height) - height)
self._pixels_pad_to_width = (self._closest_larger_multiple_of_minimum_size(width) - width)
return nn.ZeroPad2d((self._pixels_pad_to_width, 0, self._pixels_pad_to_height, 0))(network_input)
def unpad(self, network_output):
"""Returns "network_output" cropped to the original size.
The cropping is performed using values save by the "pad_input"
method.
"""
return network_output[..., self._pixels_pad_to_height:, self._pixels_pad_to_width:]
class SmallUpdateBlock(nn.Module):
def __init__(self, hidden_dim=64, input_dim=64 * 2):
super(SmallUpdateBlock, self).__init__()
self.gru = ConvGRU(hidden_dim=hidden_dim, input_dim=input_dim)
self.res_head = ConvResidualBlocks(num_in_ch=64, num_out_ch=64, num_block=5)
def forward(self, net, context, motion):
inp = torch.cat([context, motion], dim=1)
net = self.gru(net, inp)
delta_net = self.res_head(net)
return net, delta_net
class ConvGRU(nn.Module):
def __init__(self, hidden_dim=128, input_dim=192 + 128):
super(ConvGRU, self).__init__()
self.convz = nn.Conv2d(hidden_dim + input_dim, hidden_dim, 3, padding=1)
self.convr = nn.Conv2d(hidden_dim + input_dim, hidden_dim, 3, padding=1)
self.convq = nn.Conv2d(hidden_dim + input_dim, hidden_dim, 3, padding=1)
def forward(self, h, x):
hx = torch.cat([h, x], dim=1)
z = torch.sigmoid(self.convz(hx))
r = torch.sigmoid(self.convr(hx))
q = torch.tanh(self.convq(torch.cat([r * h, x], dim=1)))
h = (1 - z) * h + z * q
return h
class ConvResidualBlocks(nn.Module):
"""Conv and residual block used in BasicVSR.
Args:
num_in_ch (int): Number of input channels. Default: 3.
num_out_ch (int): Number of output channels. Default: 64.
num_block (int): Number of residual blocks. Default: 15.
"""
def __init__(self, num_in_ch=3, num_out_ch=64, num_block=15):
super().__init__()
self.main = nn.Sequential(
nn.Conv2d(num_in_ch, num_out_ch, 3, 1, 1, bias=True), nn.LeakyReLU(negative_slope=0.1, inplace=True),
make_layer(ResidualBlockNoBN, num_block, num_feat=num_out_ch))
def forward(self, fea):
return self.main(fea)
\ No newline at end of file
basicsr/archs/evtexture_arch.py 0 → 100644
View file @ a75d2bda
import torch
from torch import nn as nn
from torch.nn import functional as F
from basicsr.utils.registry import ARCH_REGISTRY
from .unet_arch import UNet
from .arch_util import flow_warp, ConvResidualBlocks, SmallUpdateBlock
from .spynet_arch import SpyNet
@ARCH_REGISTRY.register()
class EvTexture(nn.Module):
"""EvTexture: Event-driven Texture Enhancement for Video Super-Resolution (ICML 2024)
Note that: this class is for 4x VSR
Args:
num_feat (int): Number of channels. Default: 64.
num_block (int): Number of residual blocks for each branch. Default: 30
spynet_path (str): Path to the pretrained weights of SPyNet. Default: None.
"""
def __init__(self, num_feat=64, num_block=30, spynet_path=None):
super().__init__()
self.num_feat = num_feat
# RGB-based flowalignment
self.spynet = SpyNet(spynet_path)
self.cnet = ConvResidualBlocks(num_in_ch=3, num_out_ch=64, num_block=8)
# iterative texture enhancement module
self.enet = UNet(inChannels=1, outChannels=num_feat)
self.update_block = SmallUpdateBlock(hidden_dim=num_feat, input_dim=num_feat * 2)
self.fusion = nn.Conv2d(num_feat * 2, num_feat, 1, 1, 0, bias=True)
# propogation
self.backward_trunk = ConvResidualBlocks(num_feat + 3, num_feat, num_block)
self.forward_trunk = ConvResidualBlocks(num_feat * 2 + 3, num_feat, num_block)
# reconstruction
self.upconv1 = nn.Conv2d(num_feat, num_feat * 4, 3, 1, 1, bias=True)
self.upconv2 = nn.Conv2d(num_feat, num_feat * 4, 3, 1, 1, bias=True)
self.conv_hr = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
self.conv_last = nn.Conv2d(num_feat, 3, 3, 1, 1)
self.pixel_shuffle = nn.PixelShuffle(2)
# activation functions
self.lrelu = nn.LeakyReLU(negative_slope=0.1, inplace=True)
def get_flow(self, x):
b, n, c, h, w = x.size()
x_1 = x[:, :-1, :, :, :].reshape(-1, c, h, w)
x_2 = x[:, 1:, :, :, :].reshape(-1, c, h, w)
flows_backward = self.spynet(x_1, x_2).view(b, n - 1, 2, h, w)
flows_forward = self.spynet(x_2, x_1).view(b, n - 1, 2, h, w)
return flows_forward, flows_backward
# context feature extractor
def get_feat(self, x):
b, n, c, h, w = x.size()
feats_ = self.cnet(x.view(-1, c, h, w))
h, w = feats_.shape[2:]
feats_ = feats_.view(b, n, -1, h, w)
return feats_
def forward(self, imgs, voxels_f, voxels_b):
"""Forward function of EvTexture
Args:
imgs: Input frames with shape (b, n, c, h, w). n is the number of frames.
voxels_f: forward event voxel grids with shape (b, n-1 , c, h, w).
voxels_b: backward event voxel grids with shape (b, n-1 , c, h, w).
Output:
out_l: output frames with shape (b, n, c, 4h, 4w)
"""
flows_forward, flows_backward = self.get_flow(imgs)
feat_imgs = self.get_feat(imgs)
b, n, _, h, w = imgs.size()
bins = voxels_f.size()[2]
# backward branch
out_l = []
feat_prop = imgs.new_zeros(b, self.num_feat, h, w)
for i in range(n - 1, -1, -1):
x_i = imgs[:, i, :, :, :]
if i < n - 1:
# motion branch by rgb frames
flow = flows_backward[:, i, :, :, :]
feat_prop_coarse = flow_warp(feat_prop, flow.permute(0, 2, 3, 1))
# texture branch by event voxels
hidden_state = feat_prop.clone()
feat_img = feat_imgs[:, i, :, :, :] # [B, num_feat, H, W]
cur_voxel = voxels_f[:, i, :, :, :] # [B, Bins, H, W]
## iterative update block
feat_prop_fine = feat_prop.clone()
for j in range(bins - 1, -1, -1):
voxel_j = cur_voxel[:, j, :, :].unsqueeze(1) # [B, 1, H, W]
feat_motion = self.enet(voxel_j) # [B, num_feat, H, W], enet is UNet(inChannels=1, OurChannels=num_feat)
hidden_state, delta_feat = self.update_block(hidden_state, feat_img, feat_motion) # refine coarse hidden state
feat_prop_fine = feat_prop_fine + delta_feat
feat_prop = self.fusion(torch.cat([feat_prop_fine, feat_prop_coarse], dim=1))
feat_prop = torch.cat([x_i, feat_prop], dim=1)
feat_prop = self.backward_trunk(feat_prop)
out_l.insert(0, feat_prop)
# forward branch
feat_prop = torch.zeros_like(feat_prop)
for i in range(0, n):
x_i = imgs[:, i, :, :, :]
if i > 0:
# motion branch by rgb frames
flow = flows_forward[:, i - 1, :, :, :]
feat_prop_coarse = flow_warp(feat_prop, flow.permute(0, 2, 3, 1))
# texture branch by event voxels
hidden_state = feat_prop.clone()
feat_img = feat_imgs[:, i, :, :, :] # [B, num_feat, H, W]
cur_voxel = voxels_b[:, i - 1, :, :, :] # [B, Bins, H, W]
# iterative update block
feat_prop_fine = feat_prop.clone()
for j in range(bins - 1, -1, -1):
voxel_j = cur_voxel[:, j, :, :].unsqueeze(1) # [B, 1, H, W]
feat_motion = self.enet(voxel_j) # [B, num_feat, H, W], enet is UNet(inChannels=1, OurChannels=64)
hidden_state, delta_feat = self.update_block(hidden_state, feat_img, feat_motion)
feat_prop_fine = feat_prop_fine + delta_feat
feat_prop = self.fusion(torch.cat([feat_prop_fine, feat_prop_coarse], dim=1))
feat_prop = torch.cat([x_i, out_l[i], feat_prop], dim=1)
feat_prop = self.forward_trunk(feat_prop)
# upsample
out = self.lrelu(self.pixel_shuffle(self.upconv1(feat_prop)))
out = self.lrelu(self.pixel_shuffle(self.upconv2(out)))
out = self.lrelu(self.conv_hr(out))
out = self.conv_last(out)
base = F.interpolate(x_i, scale_factor=4, mode='bilinear', align_corners=False)
out += base
out_l[i] = out
return torch.stack(out_l, dim=1)
# @ARCH_REGISTRY.register()
# class EvTexture(nn.Module):
# """EvTexture: Event-driven Texture Enhancement for Video Super-Resolution (ICML 2024)
# Note that: this class is for 4x VSR
# Args:
# num_feat (int): Number of channels. Default: 64.
# num_block (int): Number of residual blocks for each branch. Default: 30
# spynet_path (str): Path to the pretrained weights of SPyNet. Default: None.
# """
# def __init__(self, num_feat=64, num_block=30, spynet_path=None):
# super().__init__()
# self.num_feat = num_feat
# # RGB-based flowalignment
# self.spynet = SpyNet(spynet_path)
# self.cnet = ConvResidualBlocks(num_in_ch=3, num_out_ch=64, num_block=8)
# # iterative texture enhancement module
# self.enet = UNet(inChannels=1, outChannels=num_feat)
# self.update_block = SmallUpdateBlock(hidden_dim=num_feat, input_dim=num_feat * 2)
# self.fusion = nn.Conv2d(num_feat * 2, num_feat, 1, 1, 0, bias=True)
# # propogation
# self.backward_trunk = ConvResidualBlocks(num_feat + 3, num_feat, num_block)
# self.forward_trunk = ConvResidualBlocks(num_feat * 2 + 3, num_feat, num_block)
# # reconstruction
# self.upconv1 = nn.Conv2d(num_feat, num_feat * 4, 3, 1, 1, bias=True)
# self.upconv2 = nn.Conv2d(num_feat, num_feat * 4, 3, 1, 1, bias=True)
# self.conv_hr = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
# self.conv_last = nn.Conv2d(num_feat, 3, 3, 1, 1)
# self.pixel_shuffle = nn.PixelShuffle(2)
# # activation functions
# self.lrelu = nn.LeakyReLU(negative_slope=0.1, inplace=True)
# def get_flow(self, x):
# # print(x.size())
# b, n, c, h, w = x.size()
# x_1 = x[:, :-1, :, :, :].reshape(-1, c, h, w)
# x_2 = x[:, 1:, :, :, :].reshape(-1, c, h, w)
# flows_backward = self.spynet(x_1, x_2).view(b, n - 1, 2, h, w)
# flows_forward = self.spynet(x_2, x_1).view(b, n - 1, 2, h, w)
# return flows_forward, flows_backward
# # context feature extractor
# def get_feat(self, x):
# b, n, c, h, w = x.size()
# feats_ = self.cnet(x.view(-1, c, h, w))
# h, w = feats_.shape[2:]
# feats_ = feats_.view(b, n, -1, h, w)
# return feats_
# def forward(self, imgs, voxels_f, voxels_b):
# """Forward function of EvTexture
# Args:
# imgs: Input frames with shape (b, n, c, h, w). n is the number of frames.
# voxels_f: forward event voxel grids with shape (b, n-1 , c, h, w).
# voxels_b: backward event voxel grids with shape (b, n-1 , c, h, w).
# Output:
# out_l: output frames with shape (b, n, c, 4h, 4w)
# """
# imgs = imgs.unsqueeze(0)
# voxels_f = voxels_f.unsqueeze(0)
# voxels_b = voxels_b.unsqueeze(0)
# flows_forward, flows_backward = self.get_flow(imgs)
# feat_imgs = self.get_feat(imgs)
# b, n, _, h, w = imgs.size()
# bins = voxels_f.size()[2]
# # backward branch
# out_l = []
# feat_prop = imgs.new_zeros(b, self.num_feat, h, w)
# for i in range(n - 1, -1, -1):
# x_i = imgs[:, i, :, :, :]
# if i < n - 1:
# # motion branch by rgb frames
# flow = flows_backward[:, i, :, :, :]
# feat_prop_coarse = flow_warp(feat_prop, flow.permute(0, 2, 3, 1))
# # texture branch by event voxels
# hidden_state = feat_prop.clone()
# feat_img = feat_imgs[:, i, :, :, :] # [B, num_feat, H, W]
# cur_voxel = voxels_f[:, i, :, :, :] # [B, Bins, H, W]
# ## iterative update block
# feat_prop_fine = feat_prop.clone()
# for j in range(bins - 1, -1, -1):
# voxel_j = cur_voxel[:, j, :, :].unsqueeze(1) # [B, 1, H, W]
# feat_motion = self.enet(voxel_j) # [B, num_feat, H, W], enet is UNet(inChannels=1, OurChannels=num_feat)
# hidden_state, delta_feat = self.update_block(hidden_state, feat_img, feat_motion) # refine coarse hidden state
# feat_prop_fine = feat_prop_fine + delta_feat
# feat_prop = self.fusion(torch.cat([feat_prop_fine, feat_prop_coarse], dim=1))
# feat_prop = torch.cat([x_i, feat_prop], dim=1)
# feat_prop = self.backward_trunk(feat_prop)
# out_l.insert(0, feat_prop)
# # forward branch
# feat_prop = torch.zeros_like(feat_prop)
# for i in range(0, n):
# x_i = imgs[:, i, :, :, :]
# if i > 0:
# # motion branch by rgb frames
# flow = flows_forward[:, i - 1, :, :, :]
# feat_prop_coarse = flow_warp(feat_prop, flow.permute(0, 2, 3, 1))
# # texture branch by event voxels
# hidden_state = feat_prop.clone()
# feat_img = feat_imgs[:, i, :, :, :] # [B, num_feat, H, W]
# cur_voxel = voxels_b[:, i - 1, :, :, :] # [B, Bins, H, W]
# # iterative update block
# feat_prop_fine = feat_prop.clone()
# for j in range(bins - 1, -1, -1):
# voxel_j = cur_voxel[:, j, :, :].unsqueeze(1) # [B, 1, H, W]
# feat_motion = self.enet(voxel_j) # [B, num_feat, H, W], enet is UNet(inChannels=1, OurChannels=64)
# hidden_state, delta_feat = self.update_block(hidden_state, feat_img, feat_motion)
# feat_prop_fine = feat_prop_fine + delta_feat
# feat_prop = self.fusion(torch.cat([feat_prop_fine, feat_prop_coarse], dim=1))
# feat_prop = torch.cat([x_i, out_l[i], feat_prop], dim=1)
# feat_prop = self.forward_trunk(feat_prop)
# # upsample
# out = self.lrelu(self.pixel_shuffle(self.upconv1(feat_prop)))
# out = self.lrelu(self.pixel_shuffle(self.upconv2(out)))
# out = self.lrelu(self.conv_hr(out))
# out = self.conv_last(out)
# base = F.interpolate(x_i, scale_factor=4, mode='bilinear', align_corners=False)
# out += base
# out_l[i] = out
# return torch.stack(out_l, dim=1)
\ No newline at end of file
basicsr/archs/spynet_arch.py 0 → 100644
View file @ a75d2bda
import math
import torch
from torch import nn as nn
from torch.nn import functional as F
from basicsr.utils.registry import ARCH_REGISTRY
from .arch_util import flow_warp
class BasicModule(nn.Module):
"""Basic Module for SpyNet.
"""
def __init__(self):
super(BasicModule, self).__init__()
self.basic_module = nn.Sequential(
nn.Conv2d(in_channels=8, out_channels=32, kernel_size=7, stride=1, padding=3), nn.ReLU(inplace=False),
nn.Conv2d(in_channels=32, out_channels=64, kernel_size=7, stride=1, padding=3), nn.ReLU(inplace=False),
nn.Conv2d(in_channels=64, out_channels=32, kernel_size=7, stride=1, padding=3), nn.ReLU(inplace=False),
nn.Conv2d(in_channels=32, out_channels=16, kernel_size=7, stride=1, padding=3), nn.ReLU(inplace=False),
nn.Conv2d(in_channels=16, out_channels=2, kernel_size=7, stride=1, padding=3))
def forward(self, tensor_input):
return self.basic_module(tensor_input)
@ARCH_REGISTRY.register()
class SpyNet(nn.Module):
"""SpyNet architecture.
Args:
load_path (str): path for pretrained SpyNet. Default: None.
"""
def __init__(self, load_path=None):
super(SpyNet, self).__init__()
self.basic_module = nn.ModuleList([BasicModule() for _ in range(6)])
if load_path:
self.load_state_dict(torch.load(load_path, map_location=lambda storage, loc: storage)['params'])
self.register_buffer('mean', torch.Tensor([0.485, 0.456, 0.406]).view(1, 3, 1, 1))
self.register_buffer('std', torch.Tensor([0.229, 0.224, 0.225]).view(1, 3, 1, 1))
def preprocess(self, tensor_input):
tensor_output = (tensor_input - self.mean) / self.std
return tensor_output
def process(self, ref, supp):
flow = []
ref = [self.preprocess(ref)]
supp = [self.preprocess(supp)]
for level in range(5):
ref.insert(0, F.avg_pool2d(input=ref[0], kernel_size=2, stride=2, count_include_pad=False))
supp.insert(0, F.avg_pool2d(input=supp[0], kernel_size=2, stride=2, count_include_pad=False))
flow = ref[0].new_zeros(
[ref[0].size(0), 2,
int(math.floor(ref[0].size(2) / 2.0)),
int(math.floor(ref[0].size(3) / 2.0))])
for level in range(len(ref)):
upsampled_flow = F.interpolate(input=flow, scale_factor=2, mode='bilinear', align_corners=True) * 2.0
if upsampled_flow.size(2) != ref[level].size(2):
upsampled_flow = F.pad(input=upsampled_flow, pad=[0, 0, 0, 1], mode='replicate')
if upsampled_flow.size(3) != ref[level].size(3):
upsampled_flow = F.pad(input=upsampled_flow, pad=[0, 1, 0, 0], mode='replicate')
flow = self.basic_module[level](torch.cat([
ref[level],
flow_warp(
supp[level], upsampled_flow.permute(0, 2, 3, 1), interp_mode='bilinear', padding_mode='border'),
upsampled_flow
], 1)) + upsampled_flow
return flow
def forward(self, ref, supp):
assert ref.size() == supp.size()
h, w = ref.size(2), ref.size(3)
w_floor = math.floor(math.ceil(w / 32.0) * 32.0)
h_floor = math.floor(math.ceil(h / 32.0) * 32.0)
ref = F.interpolate(input=ref, size=(h_floor, w_floor), mode='bilinear', align_corners=False)
supp = F.interpolate(input=supp, size=(h_floor, w_floor), mode='bilinear', align_corners=False)
flow = F.interpolate(input=self.process(ref, supp), size=(h, w), mode='bilinear', align_corners=False)
flow[:, 0, :, :] *= float(w) / float(w_floor)
flow[:, 1, :, :] *= float(h) / float(h_floor)
return flow
basicsr/archs/unet_arch.py 0 → 100644
View file @ a75d2bda
## Modified from timelens. https://github.com/uzh-rpg/rpg_timelens/blob/main/timelens/superslomo/unet.py
import torch
import torch.nn.functional as F
from basicsr.utils.registry import ARCH_REGISTRY
from .arch_util import SizeAdapter
from torch import nn
class up(nn.Module):
def __init__(self, inChannels, outChannels):
super(up, self).__init__()
self.conv1 = nn.Conv2d(inChannels, outChannels, 3, stride=1, padding=1)
self.conv2 = nn.Conv2d(2 * outChannels, outChannels, 3, stride=1, padding=1)
def forward(self, x, skpCn):
x = F.interpolate(x, scale_factor=2, mode="bilinear")
x = F.leaky_relu(self.conv1(x), negative_slope=0.1)
x = F.leaky_relu(self.conv2(torch.cat((x, skpCn), 1)), negative_slope=0.1)
return x
class down(nn.Module):
def __init__(self, inChannels, outChannels, filterSize):
super(down, self).__init__()
self.conv1 = nn.Conv2d(
inChannels,
outChannels,
filterSize,
stride=1,
padding=int((filterSize - 1) / 2),
)
self.conv2 = nn.Conv2d(
outChannels,
outChannels,
filterSize,
stride=1,
padding=int((filterSize - 1) / 2),
)
def forward(self, x):
x = F.avg_pool2d(x, 2)
x = F.leaky_relu(self.conv1(x), negative_slope=0.1)
x = F.leaky_relu(self.conv2(x), negative_slope=0.1)
return x
@ARCH_REGISTRY.register()
class UNet(nn.Module):
"""Modified version of Unet from SuperSloMo.
Difference :
1) there is an option to skip ReLU after the last convolution.
2) there is a size adapter module that makes sure that input of all sizes
can be processed correctly. It is necessary because original
UNet can process only inputs with spatial dimensions divisible by 32.
"""
def __init__(self, inChannels, outChannels, ends_with_relu=True, load_path=None):
super(UNet, self).__init__()
self._ends_with_relu = ends_with_relu
self._size_adapter = SizeAdapter(minimum_size=32)
# 5-level
self.conv1 = nn.Conv2d(inChannels, 8, 7, stride=1, padding=3)
self.conv2 = nn.Conv2d(8, 8, 7, stride=1, padding=3)
self.down1 = down(8, 16, 5)
self.down2 = down(16, 32, 3)
self.down3 = down(32, 64, 3)
self.down4 = down(64, 128, 3)
self.down5 = down(128, 128, 3)
self.up1 = up(128, 128)
self.up2 = up(128, 64)
self.up3 = up(64, 32)
self.up4 = up(32, 16)
self.up5 = up(16, 8)
self.conv3 = nn.Conv2d(8, outChannels, 3, stride=1, padding=1)
if load_path:
self.load_state_dict(torch.load(load_path, map_location=lambda storage, loc: storage)['params_ema'])
def forward(self, x):
x = self._size_adapter.pad(x)
x = F.leaky_relu(self.conv1(x), negative_slope=0.1)
s1 = F.leaky_relu(self.conv2(x), negative_slope=0.1)
s2 = self.down1(s1)
s3 = self.down2(s2)
s4 = self.down3(s3)
s5 = self.down4(s4)
x = self.down5(s5)
x = self.up1(x, s5)
x = self.up2(x, s4)
x = self.up3(x, s3)
x = self.up4(x, s2)
x = self.up5(x, s1)
# Note that original code has relu et the end.
if self._ends_with_relu == True:
x = F.leaky_relu(self.conv3(x), negative_slope=0.1)
else:
x = self.conv3(x)
# Size adapter crops the output to the original size.
x = self._size_adapter.unpad(x)
return x
def patch_chunk_2x(input):
"""
input (Tensor): [B, C, H, W], and H, W are divisible by 2.
return:
result (Tensor): [B, 4C, H/2, H/W]
"""
result = []
split_h = torch.chunk(input, 2, -2)
for sli in split_h:
sli_w = torch.chunk(sli, 2, -1)
for i in range(2):
result.append(sli_w[i])
assert len(result) == 4
result = torch.cat(result, dim=1)
return result
if __name__ == '__main__':
net = UNet(1, 2)
input = torch.randn((4, 1, 64, 64))
out = net(input)
\ No newline at end of file
basicsr/archs/vgg_arch.py 0 → 100644
View file @ a75d2bda
import os
import torch
from collections import OrderedDict
from torch import nn as nn
from torchvision.models import vgg as vgg
from basicsr.utils.registry import ARCH_REGISTRY
VGG_PRETRAIN_PATH = 'experiments/pretrained_models/vgg19-dcbb9e9d.pth'
NAMES = {
'vgg11': [
'conv1_1', 'relu1_1', 'pool1', 'conv2_1', 'relu2_1', 'pool2', 'conv3_1', 'relu3_1', 'conv3_2', 'relu3_2',
'pool3', 'conv4_1', 'relu4_1', 'conv4_2', 'relu4_2', 'pool4', 'conv5_1', 'relu5_1', 'conv5_2', 'relu5_2',
'pool5'
],
'vgg13': [
'conv1_1', 'relu1_1', 'conv1_2', 'relu1_2', 'pool1', 'conv2_1', 'relu2_1', 'conv2_2', 'relu2_2', 'pool2',
'conv3_1', 'relu3_1', 'conv3_2', 'relu3_2', 'pool3', 'conv4_1', 'relu4_1', 'conv4_2', 'relu4_2', 'pool4',
'conv5_1', 'relu5_1', 'conv5_2', 'relu5_2', 'pool5'
],
'vgg16': [
'conv1_1', 'relu1_1', 'conv1_2', 'relu1_2', 'pool1', 'conv2_1', 'relu2_1', 'conv2_2', 'relu2_2', 'pool2',
'conv3_1', 'relu3_1', 'conv3_2', 'relu3_2', 'conv3_3', 'relu3_3', 'pool3', 'conv4_1', 'relu4_1', 'conv4_2',
'relu4_2', 'conv4_3', 'relu4_3', 'pool4', 'conv5_1', 'relu5_1', 'conv5_2', 'relu5_2', 'conv5_3', 'relu5_3',
'pool5'
],
'vgg19': [
'conv1_1', 'relu1_1', 'conv1_2', 'relu1_2', 'pool1', 'conv2_1', 'relu2_1', 'conv2_2', 'relu2_2', 'pool2',
'conv3_1', 'relu3_1', 'conv3_2', 'relu3_2', 'conv3_3', 'relu3_3', 'conv3_4', 'relu3_4', 'pool3', 'conv4_1',
'relu4_1', 'conv4_2', 'relu4_2', 'conv4_3', 'relu4_3', 'conv4_4', 'relu4_4', 'pool4', 'conv5_1', 'relu5_1',
'conv5_2', 'relu5_2', 'conv5_3', 'relu5_3', 'conv5_4', 'relu5_4', 'pool5'
]
}
def insert_bn(names):
"""Insert bn layer after each conv.
Args:
names (list): The list of layer names.
Returns:
list: The list of layer names with bn layers.
"""
names_bn = []
for name in names:
names_bn.append(name)
if 'conv' in name:
position = name.replace('conv', '')
names_bn.append('bn' + position)
return names_bn
@ARCH_REGISTRY.register()
class VGGFeatureExtractor(nn.Module):
"""VGG network for feature extraction.
In this implementation, we allow users to choose whether use normalization
in the input feature and the type of vgg network. Note that the pretrained
path must fit the vgg type.
Args:
layer_name_list (list[str]): Forward function returns the corresponding
features according to the layer_name_list.
Example: {'relu1_1', 'relu2_1', 'relu3_1'}.
vgg_type (str): Set the type of vgg network. Default: 'vgg19'.
use_input_norm (bool): If True, normalize the input image. Importantly,
the input feature must in the range [0, 1]. Default: True.
range_norm (bool): If True, norm images with range [-1, 1] to [0, 1].
Default: False.
requires_grad (bool): If true, the parameters of VGG network will be
optimized. Default: False.
remove_pooling (bool): If true, the max pooling operations in VGG net
will be removed. Default: False.
pooling_stride (int): The stride of max pooling operation. Default: 2.
"""
def __init__(self,
layer_name_list,
vgg_type='vgg19',
use_input_norm=True,
range_norm=False,
requires_grad=False,
remove_pooling=False,
pooling_stride=2):
super(VGGFeatureExtractor, self).__init__()
self.layer_name_list = layer_name_list
self.use_input_norm = use_input_norm
self.range_norm = range_norm
self.names = NAMES[vgg_type.replace('_bn', '')]
if 'bn' in vgg_type:
self.names = insert_bn(self.names)
# only borrow layers that will be used to avoid unused params
max_idx = 0
for v in layer_name_list:
idx = self.names.index(v)
if idx > max_idx:
max_idx = idx
if os.path.exists(VGG_PRETRAIN_PATH):
vgg_net = getattr(vgg, vgg_type)(pretrained=False)
state_dict = torch.load(VGG_PRETRAIN_PATH, map_location=lambda storage, loc: storage)
vgg_net.load_state_dict(state_dict)
else:
vgg_net = getattr(vgg, vgg_type)(pretrained=True)
features = vgg_net.features[:max_idx + 1]
modified_net = OrderedDict()
for k, v in zip(self.names, features):
if 'pool' in k:
# if remove_pooling is true, pooling operation will be removed
if remove_pooling:
continue
else:
# in some cases, we may want to change the default stride
modified_net[k] = nn.MaxPool2d(kernel_size=2, stride=pooling_stride)
else:
modified_net[k] = v
self.vgg_net = nn.Sequential(modified_net)
if not requires_grad:
self.vgg_net.eval()
for param in self.parameters():
param.requires_grad = False
else:
self.vgg_net.train()
for param in self.parameters():
param.requires_grad = True
if self.use_input_norm:
# the mean is for image with range [0, 1]
self.register_buffer('mean', torch.Tensor([0.485, 0.456, 0.406]).view(1, 3, 1, 1))
# the std is for image with range [0, 1]
self.register_buffer('std', torch.Tensor([0.229, 0.224, 0.225]).view(1, 3, 1, 1))
def forward(self, x):
"""Forward function.
Args:
x (Tensor): Input tensor with shape (n, c, h, w).
Returns:
Tensor: Forward results.
"""
if self.range_norm:
x = (x + 1) / 2
if self.use_input_norm:
x = (x - self.mean) / self.std
output = {}
for key, layer in self.vgg_net._modules.items():
x = layer(x)
if key in self.layer_name_list:
output[key] = x.clone()
return output
basicsr/data/__init__.py 0 → 100644
View file @ a75d2bda
import importlib
import numpy as np
import random
import torch
import torch.utils.data
from copy import deepcopy
from functools import partial
from os import path as osp
from basicsr.data.prefetch_dataloader import PrefetchDataLoader
from basicsr.utils import get_root_logger, scandir
from basicsr.utils.dist_util import get_dist_info
from basicsr.utils.registry import DATASET_REGISTRY
__all__ = ['build_dataset', 'build_dataloader']
# automatically scan and import dataset modules for registry
# scan all the files under the data folder with '_dataset' in file names
data_folder = osp.dirname(osp.abspath(__file__))
dataset_filenames = [osp.splitext(osp.basename(v))[0] for v in scandir(data_folder) if v.endswith('_dataset.py')]
# import all the dataset modules
_dataset_modules = [importlib.import_module(f'basicsr.data.{file_name}') for file_name in dataset_filenames]
def build_dataset(dataset_opt):
"""Build dataset from options.
Args:
dataset_opt (dict): Configuration for dataset. It must contain:
name (str): Dataset name.
type (str): Dataset type.
"""
dataset_opt = deepcopy(dataset_opt)
dataset = DATASET_REGISTRY.get(dataset_opt['type'])(dataset_opt)
logger = get_root_logger()
logger.info(f'Dataset [{dataset.__class__.__name__}] - {dataset_opt["name"]} is built.')
return dataset
def build_dataloader(dataset, dataset_opt, num_gpu=1, dist=False, sampler=None, seed=None):
"""Build dataloader.
Args:
dataset (torch.utils.data.Dataset): Dataset.
dataset_opt (dict): Dataset options. It contains the following keys:
phase (str): 'train' or 'val'.
num_worker_per_gpu (int): Number of workers for each GPU.
batch_size_per_gpu (int): Training batch size for each GPU.
num_gpu (int): Number of GPUs. Used only in the train phase.
Default: 1.
dist (bool): Whether in distributed training. Used only in the train
phase. Default: False.
sampler (torch.utils.data.sampler): Data sampler. Default: None.
seed (int | None): Seed. Default: None
"""
phase = dataset_opt['phase']
rank, _ = get_dist_info()
if phase == 'train':
if dist: # distributed training
batch_size = dataset_opt['batch_size_per_gpu']
num_workers = dataset_opt['num_worker_per_gpu']
else: # non-distributed training
multiplier = 1 if num_gpu == 0 else num_gpu
batch_size = dataset_opt['batch_size_per_gpu'] * multiplier
num_workers = dataset_opt['num_worker_per_gpu'] * multiplier
dataloader_args = dict(
dataset=dataset,
batch_size=batch_size,
shuffle=False,
num_workers=num_workers,
sampler=sampler,
drop_last=True)
if sampler is None:
dataloader_args['shuffle'] = True
dataloader_args['worker_init_fn'] = partial(
worker_init_fn, num_workers=num_workers, rank=rank, seed=seed) if seed is not None else None
elif phase in ['val', 'test']: # validation
dataloader_args = dict(dataset=dataset, batch_size=1, shuffle=False, num_workers=0)
else:
raise ValueError(f"Wrong dataset phase: {phase}. Supported ones are 'train', 'val' and 'test'.")
dataloader_args['pin_memory'] = dataset_opt.get('pin_memory', False)
dataloader_args['persistent_workers'] = dataset_opt.get('persistent_workers', False)
prefetch_mode = dataset_opt.get('prefetch_mode')
if prefetch_mode == 'cpu': # CPUPrefetcher
num_prefetch_queue = dataset_opt.get('num_prefetch_queue', 1)
logger = get_root_logger()
logger.info(f'Use {prefetch_mode} prefetch dataloader: num_prefetch_queue = {num_prefetch_queue}')
return PrefetchDataLoader(num_prefetch_queue=num_prefetch_queue, **dataloader_args)
else:
# prefetch_mode=None: Normal dataloader
# prefetch_mode='cuda': dataloader for CUDAPrefetcher
return torch.utils.data.DataLoader(**dataloader_args)
def worker_init_fn(worker_id, num_workers, rank, seed):
# Set the worker seed to num_workers * rank + worker_id + seed
worker_seed = num_workers * rank + worker_id + seed
np.random.seed(worker_seed)
random.seed(worker_seed)
basicsr/data/data_sampler.py 0 → 100644
View file @ a75d2bda
import math
import torch
from torch.utils.data.sampler import Sampler
class EnlargedSampler(Sampler):
"""Sampler that restricts data loading to a subset of the dataset.
Modified from torch.utils.data.distributed.DistributedSampler
Support enlarging the dataset for iteration-based training, for saving
time when restart the dataloader after each epoch
Args:
dataset (torch.utils.data.Dataset): Dataset used for sampling.
num_replicas (int | None): Number of processes participating in
the training. It is usually the world_size.
rank (int | None): Rank of the current process within num_replicas.
ratio (int): Enlarging ratio. Default: 1.
"""
def __init__(self, dataset, num_replicas, rank, ratio=1):
self.dataset = dataset
self.num_replicas = num_replicas
self.rank = rank
self.epoch = 0
self.num_samples = math.ceil(len(self.dataset) * ratio / self.num_replicas)
self.total_size = self.num_samples * self.num_replicas
def __iter__(self):
# deterministically shuffle based on epoch
g = torch.Generator()
g.manual_seed(self.epoch)
indices = torch.randperm(self.total_size, generator=g).tolist()
dataset_size = len(self.dataset)
indices = [v % dataset_size for v in indices]
# subsample
indices = indices[self.rank:self.total_size:self.num_replicas]
assert len(indices) == self.num_samples
return iter(indices)
def __len__(self):
return self.num_samples
def set_epoch(self, epoch):
self.epoch = epoch
basicsr/data/data_util.py 0 → 100644
View file @ a75d2bda
import cv2
import numpy as np
import torch
from os import path as osp
from torch.nn import functional as F
from basicsr.data.transforms import mod_crop
from basicsr.utils import img2tensor, scandir
def read_img_seq(path, require_mod_crop=False, scale=1, return_imgname=False):
"""Read a sequence of images from a given folder path.
Args:
path (list[str] | str): List of image paths or image folder path.
require_mod_crop (bool): Require mod crop for each image.
Default: False.
scale (int): Scale factor for mod_crop. Default: 1.
return_imgname(bool): Whether return image names. Default False.
Returns:
Tensor: size (t, c, h, w), RGB, [0, 1].
list[str]: Returned image name list.
"""
if isinstance(path, list):
img_paths = path
else:
img_paths = sorted(list(scandir(path, full_path=True)))
imgs = [cv2.imread(v).astype(np.float32) / 255. for v in img_paths]
if require_mod_crop:
imgs = [mod_crop(img, scale) for img in imgs]
imgs = img2tensor(imgs, bgr2rgb=True, float32=True)
imgs = torch.stack(imgs, dim=0)
if return_imgname:
imgnames = [osp.splitext(osp.basename(path))[0] for path in img_paths]
return imgs, imgnames
else:
return imgs
def generate_frame_indices(crt_idx, max_frame_num, num_frames, padding='reflection'):
"""Generate an index list for reading `num_frames` frames from a sequence
of images.
Args:
crt_idx (int): Current center index.
max_frame_num (int): Max number of the sequence of images (from 1).
num_frames (int): Reading num_frames frames.
padding (str): Padding mode, one of
'replicate' | 'reflection' | 'reflection_circle' | 'circle'
Examples: current_idx = 0, num_frames = 5
The generated frame indices under different padding mode:
replicate: [0, 0, 0, 1, 2]
reflection: [2, 1, 0, 1, 2]
reflection_circle: [4, 3, 0, 1, 2]
circle: [3, 4, 0, 1, 2]
Returns:
list[int]: A list of indices.
"""
assert num_frames % 2 == 1, 'num_frames should be an odd number.'
assert padding in ('replicate', 'reflection', 'reflection_circle', 'circle'), f'Wrong padding mode: {padding}.'
max_frame_num = max_frame_num - 1 # start from 0
num_pad = num_frames // 2
indices = []
for i in range(crt_idx - num_pad, crt_idx + num_pad + 1):
if i < 0:
if padding == 'replicate':
pad_idx = 0
elif padding == 'reflection':
pad_idx = -i
elif padding == 'reflection_circle':
pad_idx = crt_idx + num_pad - i
else:
pad_idx = num_frames + i
elif i > max_frame_num:
if padding == 'replicate':
pad_idx = max_frame_num
elif padding == 'reflection':
pad_idx = max_frame_num * 2 - i
elif padding == 'reflection_circle':
pad_idx = (crt_idx - num_pad) - (i - max_frame_num)
else:
pad_idx = i - num_frames
else:
pad_idx = i
indices.append(pad_idx)
return indices
def paired_paths_from_lmdb(folders, keys):
"""Generate paired paths from lmdb files.
Contents of lmdb. Taking the `lq.lmdb` for example, the file structure is:
::
lq.lmdb
├── data.mdb
├── lock.mdb
├── meta_info.txt
The data.mdb and lock.mdb are standard lmdb files and you can refer to
https://lmdb.readthedocs.io/en/release/ for more details.
The meta_info.txt is a specified txt file to record the meta information
of our datasets. It will be automatically created when preparing
datasets by our provided dataset tools.
Each line in the txt file records
1)image name (with extension),
2)image shape,
3)compression level, separated by a white space.
Example: `baboon.png (120,125,3) 1`
We use the image name without extension as the lmdb key.
Note that we use the same key for the corresponding lq and gt images.
Args:
folders (list[str]): A list of folder path. The order of list should
be [input_folder, gt_folder].
keys (list[str]): A list of keys identifying folders. The order should
be in consistent with folders, e.g., ['lq', 'gt'].
Note that this key is different from lmdb keys.
Returns:
list[str]: Returned path list.
"""
assert len(folders) == 2, ('The len of folders should be 2 with [input_folder, gt_folder]. '
f'But got {len(folders)}')
assert len(keys) == 2, f'The len of keys should be 2 with [input_key, gt_key]. But got {len(keys)}'
input_folder, gt_folder = folders
input_key, gt_key = keys
if not (input_folder.endswith('.lmdb') and gt_folder.endswith('.lmdb')):
raise ValueError(f'{input_key} folder and {gt_key} folder should both in lmdb '
f'formats. But received {input_key}: {input_folder}; '
f'{gt_key}: {gt_folder}')
# ensure that the two meta_info files are the same
with open(osp.join(input_folder, 'meta_info.txt')) as fin:
input_lmdb_keys = [line.split('.')[0] for line in fin]
with open(osp.join(gt_folder, 'meta_info.txt')) as fin:
gt_lmdb_keys = [line.split('.')[0] for line in fin]
if set(input_lmdb_keys) != set(gt_lmdb_keys):
raise ValueError(f'Keys in {input_key}_folder and {gt_key}_folder are different.')
else:
paths = []
for lmdb_key in sorted(input_lmdb_keys):
paths.append(dict([(f'{input_key}_path', lmdb_key), (f'{gt_key}_path', lmdb_key)]))
return paths
def paired_paths_from_meta_info_file(folders, keys, meta_info_file, filename_tmpl):
"""Generate paired paths from an meta information file.
Each line in the meta information file contains the image names and
image shape (usually for gt), separated by a white space.
Example of an meta information file:
```
0001_s001.png (480,480,3)
0001_s002.png (480,480,3)
```
Args:
folders (list[str]): A list of folder path. The order of list should
be [input_folder, gt_folder].
keys (list[str]): A list of keys identifying folders. The order should
be in consistent with folders, e.g., ['lq', 'gt'].
meta_info_file (str): Path to the meta information file.
filename_tmpl (str): Template for each filename. Note that the
template excludes the file extension. Usually the filename_tmpl is
for files in the input folder.
Returns:
list[str]: Returned path list.
"""
assert len(folders) == 2, ('The len of folders should be 2 with [input_folder, gt_folder]. '
f'But got {len(folders)}')
assert len(keys) == 2, f'The len of keys should be 2 with [input_key, gt_key]. But got {len(keys)}'
input_folder, gt_folder = folders
input_key, gt_key = keys
with open(meta_info_file, 'r') as fin:
gt_names = [line.strip().split(' ')[0] for line in fin]
paths = []
for gt_name in gt_names:
basename, ext = osp.splitext(osp.basename(gt_name))
input_name = f'{filename_tmpl.format(basename)}{ext}'
input_path = osp.join(input_folder, input_name)
gt_path = osp.join(gt_folder, gt_name)
paths.append(dict([(f'{input_key}_path', input_path), (f'{gt_key}_path', gt_path)]))
return paths
def paired_paths_from_folder(folders, keys, filename_tmpl):
"""Generate paired paths from folders.
Args:
folders (list[str]): A list of folder path. The order of list should
be [input_folder, gt_folder].
keys (list[str]): A list of keys identifying folders. The order should
be in consistent with folders, e.g., ['lq', 'gt'].
filename_tmpl (str): Template for each filename. Note that the
template excludes the file extension. Usually the filename_tmpl is
for files in the input folder.
Returns:
list[str]: Returned path list.
"""
assert len(folders) == 2, ('The len of folders should be 2 with [input_folder, gt_folder]. '
f'But got {len(folders)}')
assert len(keys) == 2, f'The len of keys should be 2 with [input_key, gt_key]. But got {len(keys)}'
input_folder, gt_folder = folders
input_key, gt_key = keys
input_paths = list(scandir(input_folder))
gt_paths = list(scandir(gt_folder))
assert len(input_paths) == len(gt_paths), (f'{input_key} and {gt_key} datasets have different number of images: '
f'{len(input_paths)}, {len(gt_paths)}.')
paths = []
for gt_path in gt_paths:
basename, ext = osp.splitext(osp.basename(gt_path))
input_name = f'{filename_tmpl.format(basename)}{ext}'
input_path = osp.join(input_folder, input_name)
assert input_name in input_paths, f'{input_name} is not in {input_key}_paths.'
gt_path = osp.join(gt_folder, gt_path)
paths.append(dict([(f'{input_key}_path', input_path), (f'{gt_key}_path', gt_path)]))
return paths
def paths_from_folder(folder):
"""Generate paths from folder.
Args:
folder (str): Folder path.
Returns:
list[str]: Returned path list.
"""
paths = list(scandir(folder))
paths = [osp.join(folder, path) for path in paths]
return paths
def paths_from_lmdb(folder):
"""Generate paths from lmdb.
Args:
folder (str): Folder path.
Returns:
list[str]: Returned path list.
"""
if not folder.endswith('.lmdb'):
raise ValueError(f'Folder {folder}folder should in lmdb format.')
with open(osp.join(folder, 'meta_info.txt')) as fin:
paths = [line.split('.')[0] for line in fin]
return paths
def generate_gaussian_kernel(kernel_size=13, sigma=1.6):
"""Generate Gaussian kernel used in `duf_downsample`.
Args:
kernel_size (int): Kernel size. Default: 13.
sigma (float): Sigma of the Gaussian kernel. Default: 1.6.
Returns:
np.array: The Gaussian kernel.
"""
from scipy.ndimage import filters as filters
kernel = np.zeros((kernel_size, kernel_size))
# set element at the middle to one, a dirac delta
kernel[kernel_size // 2, kernel_size // 2] = 1
# gaussian-smooth the dirac, resulting in a gaussian filter
return filters.gaussian_filter(kernel, sigma)
def duf_downsample(x, kernel_size=13, scale=4):
"""Downsamping with Gaussian kernel used in the DUF official code.
Args:
x (Tensor): Frames to be downsampled, with shape (b, t, c, h, w).
kernel_size (int): Kernel size. Default: 13.
scale (int): Downsampling factor. Supported scale: (2, 3, 4).
Default: 4.
Returns:
Tensor: DUF downsampled frames.
"""
assert scale in (2, 3, 4), f'Only support scale (2, 3, 4), but got {scale}.'
squeeze_flag = False
if x.ndim == 4:
squeeze_flag = True
x = x.unsqueeze(0)
b, t, c, h, w = x.size()
x = x.view(-1, 1, h, w)
pad_w, pad_h = kernel_size // 2 + scale * 2, kernel_size // 2 + scale * 2
x = F.pad(x, (pad_w, pad_w, pad_h, pad_h), 'reflect')
gaussian_filter = generate_gaussian_kernel(kernel_size, 0.4 * scale)
gaussian_filter = torch.from_numpy(gaussian_filter).type_as(x).unsqueeze(0).unsqueeze(0)
x = F.conv2d(x, gaussian_filter, stride=scale)
x = x[:, :, 2:-2, 2:-2]
x = x.view(b, t, c, x.size(2), x.size(3))
if squeeze_flag:
x = x.squeeze(0)
return x
basicsr/data/degradations.py 0 → 100644
View file @ a75d2bda
import cv2
import math
import numpy as np
import random
import torch
from scipy import special
from scipy.stats import multivariate_normal
from torchvision.transforms.functional_tensor import rgb_to_grayscale
# -------------------------------------------------------------------- #
# --------------------------- blur kernels --------------------------- #
# -------------------------------------------------------------------- #
# --------------------------- util functions --------------------------- #
def sigma_matrix2(sig_x, sig_y, theta):
"""Calculate the rotated sigma matrix (two dimensional matrix).
Args:
sig_x (float):
sig_y (float):
theta (float): Radian measurement.
Returns:
ndarray: Rotated sigma matrix.
"""
d_matrix = np.array([[sig_x**2, 0], [0, sig_y**2]])
u_matrix = np.array([[np.cos(theta), -np.sin(theta)], [np.sin(theta), np.cos(theta)]])
return np.dot(u_matrix, np.dot(d_matrix, u_matrix.T))
def mesh_grid(kernel_size):
"""Generate the mesh grid, centering at zero.
Args:
kernel_size (int):
Returns:
xy (ndarray): with the shape (kernel_size, kernel_size, 2)
xx (ndarray): with the shape (kernel_size, kernel_size)
yy (ndarray): with the shape (kernel_size, kernel_size)
"""
ax = np.arange(-kernel_size // 2 + 1., kernel_size // 2 + 1.)
xx, yy = np.meshgrid(ax, ax)
xy = np.hstack((xx.reshape((kernel_size * kernel_size, 1)), yy.reshape(kernel_size * kernel_size,
1))).reshape(kernel_size, kernel_size, 2)
return xy, xx, yy
def pdf2(sigma_matrix, grid):
"""Calculate PDF of the bivariate Gaussian distribution.
Args:
sigma_matrix (ndarray): with the shape (2, 2)
grid (ndarray): generated by :func:`mesh_grid`,
with the shape (K, K, 2), K is the kernel size.
Returns:
kernel (ndarrray): un-normalized kernel.
"""
inverse_sigma = np.linalg.inv(sigma_matrix)
kernel = np.exp(-0.5 * np.sum(np.dot(grid, inverse_sigma) * grid, 2))
return kernel
def cdf2(d_matrix, grid):
"""Calculate the CDF of the standard bivariate Gaussian distribution.
Used in skewed Gaussian distribution.
Args:
d_matrix (ndarrasy): skew matrix.
grid (ndarray): generated by :func:`mesh_grid`,
with the shape (K, K, 2), K is the kernel size.
Returns:
cdf (ndarray): skewed cdf.
"""
rv = multivariate_normal([0, 0], [[1, 0], [0, 1]])
grid = np.dot(grid, d_matrix)
cdf = rv.cdf(grid)
return cdf
def bivariate_Gaussian(kernel_size, sig_x, sig_y, theta, grid=None, isotropic=True):
"""Generate a bivariate isotropic or anisotropic Gaussian kernel.
In the isotropic mode, only `sig_x` is used. `sig_y` and `theta` is ignored.
Args:
kernel_size (int):
sig_x (float):
sig_y (float):
theta (float): Radian measurement.
grid (ndarray, optional): generated by :func:`mesh_grid`,
with the shape (K, K, 2), K is the kernel size. Default: None
isotropic (bool):
Returns:
kernel (ndarray): normalized kernel.
"""
if grid is None:
grid, _, _ = mesh_grid(kernel_size)
if isotropic:
sigma_matrix = np.array([[sig_x**2, 0], [0, sig_x**2]])
else:
sigma_matrix = sigma_matrix2(sig_x, sig_y, theta)
kernel = pdf2(sigma_matrix, grid)
kernel = kernel / np.sum(kernel)
return kernel
def bivariate_generalized_Gaussian(kernel_size, sig_x, sig_y, theta, beta, grid=None, isotropic=True):
"""Generate a bivariate generalized Gaussian kernel.
``Paper: Parameter Estimation For Multivariate Generalized Gaussian Distributions``
In the isotropic mode, only `sig_x` is used. `sig_y` and `theta` is ignored.
Args:
kernel_size (int):
sig_x (float):
sig_y (float):
theta (float): Radian measurement.
beta (float): shape parameter, beta = 1 is the normal distribution.
grid (ndarray, optional): generated by :func:`mesh_grid`,
with the shape (K, K, 2), K is the kernel size. Default: None
Returns:
kernel (ndarray): normalized kernel.
"""
if grid is None:
grid, _, _ = mesh_grid(kernel_size)
if isotropic:
sigma_matrix = np.array([[sig_x**2, 0], [0, sig_x**2]])
else:
sigma_matrix = sigma_matrix2(sig_x, sig_y, theta)
inverse_sigma = np.linalg.inv(sigma_matrix)
kernel = np.exp(-0.5 * np.power(np.sum(np.dot(grid, inverse_sigma) * grid, 2), beta))
kernel = kernel / np.sum(kernel)
return kernel
def bivariate_plateau(kernel_size, sig_x, sig_y, theta, beta, grid=None, isotropic=True):
"""Generate a plateau-like anisotropic kernel.
1 / (1+x^(beta))
Reference: https://stats.stackexchange.com/questions/203629/is-there-a-plateau-shaped-distribution
In the isotropic mode, only `sig_x` is used. `sig_y` and `theta` is ignored.
Args:
kernel_size (int):
sig_x (float):
sig_y (float):
theta (float): Radian measurement.
beta (float): shape parameter, beta = 1 is the normal distribution.
grid (ndarray, optional): generated by :func:`mesh_grid`,
with the shape (K, K, 2), K is the kernel size. Default: None
Returns:
kernel (ndarray): normalized kernel.
"""
if grid is None:
grid, _, _ = mesh_grid(kernel_size)
if isotropic:
sigma_matrix = np.array([[sig_x**2, 0], [0, sig_x**2]])
else:
sigma_matrix = sigma_matrix2(sig_x, sig_y, theta)
inverse_sigma = np.linalg.inv(sigma_matrix)
kernel = np.reciprocal(np.power(np.sum(np.dot(grid, inverse_sigma) * grid, 2), beta) + 1)
kernel = kernel / np.sum(kernel)
return kernel
def random_bivariate_Gaussian(kernel_size,
sigma_x_range,
sigma_y_range,
rotation_range,
noise_range=None,
isotropic=True):
"""Randomly generate bivariate isotropic or anisotropic Gaussian kernels.
In the isotropic mode, only `sigma_x_range` is used. `sigma_y_range` and `rotation_range` is ignored.
Args:
kernel_size (int):
sigma_x_range (tuple): [0.6, 5]
sigma_y_range (tuple): [0.6, 5]
rotation range (tuple): [-math.pi, math.pi]
noise_range(tuple, optional): multiplicative kernel noise,
[0.75, 1.25]. Default: None
Returns:
kernel (ndarray):
"""
assert kernel_size % 2 == 1, 'Kernel size must be an odd number.'
assert sigma_x_range[0] < sigma_x_range[1], 'Wrong sigma_x_range.'
sigma_x = np.random.uniform(sigma_x_range[0], sigma_x_range[1])
if isotropic is False:
assert sigma_y_range[0] < sigma_y_range[1], 'Wrong sigma_y_range.'
assert rotation_range[0] < rotation_range[1], 'Wrong rotation_range.'
sigma_y = np.random.uniform(sigma_y_range[0], sigma_y_range[1])
rotation = np.random.uniform(rotation_range[0], rotation_range[1])
else:
sigma_y = sigma_x
rotation = 0
kernel = bivariate_Gaussian(kernel_size, sigma_x, sigma_y, rotation, isotropic=isotropic)
# add multiplicative noise
if noise_range is not None:
assert noise_range[0] < noise_range[1], 'Wrong noise range.'
noise = np.random.uniform(noise_range[0], noise_range[1], size=kernel.shape)
kernel = kernel * noise
kernel = kernel / np.sum(kernel)
return kernel
def random_bivariate_generalized_Gaussian(kernel_size,
sigma_x_range,
sigma_y_range,
rotation_range,
beta_range,
noise_range=None,
isotropic=True):
"""Randomly generate bivariate generalized Gaussian kernels.
In the isotropic mode, only `sigma_x_range` is used. `sigma_y_range` and `rotation_range` is ignored.
Args:
kernel_size (int):
sigma_x_range (tuple): [0.6, 5]
sigma_y_range (tuple): [0.6, 5]
rotation range (tuple): [-math.pi, math.pi]
beta_range (tuple): [0.5, 8]
noise_range(tuple, optional): multiplicative kernel noise,
[0.75, 1.25]. Default: None
Returns:
kernel (ndarray):
"""
assert kernel_size % 2 == 1, 'Kernel size must be an odd number.'
assert sigma_x_range[0] < sigma_x_range[1], 'Wrong sigma_x_range.'
sigma_x = np.random.uniform(sigma_x_range[0], sigma_x_range[1])
if isotropic is False:
assert sigma_y_range[0] < sigma_y_range[1], 'Wrong sigma_y_range.'
assert rotation_range[0] < rotation_range[1], 'Wrong rotation_range.'
sigma_y = np.random.uniform(sigma_y_range[0], sigma_y_range[1])
rotation = np.random.uniform(rotation_range[0], rotation_range[1])
else:
sigma_y = sigma_x
rotation = 0
# assume beta_range[0] < 1 < beta_range[1]
if np.random.uniform() < 0.5:
beta = np.random.uniform(beta_range[0], 1)
else:
beta = np.random.uniform(1, beta_range[1])
kernel = bivariate_generalized_Gaussian(kernel_size, sigma_x, sigma_y, rotation, beta, isotropic=isotropic)
# add multiplicative noise
if noise_range is not None:
assert noise_range[0] < noise_range[1], 'Wrong noise range.'
noise = np.random.uniform(noise_range[0], noise_range[1], size=kernel.shape)
kernel = kernel * noise
kernel = kernel / np.sum(kernel)
return kernel
def random_bivariate_plateau(kernel_size,
sigma_x_range,
sigma_y_range,
rotation_range,
beta_range,
noise_range=None,
isotropic=True):
"""Randomly generate bivariate plateau kernels.
In the isotropic mode, only `sigma_x_range` is used. `sigma_y_range` and `rotation_range` is ignored.
Args:
kernel_size (int):
sigma_x_range (tuple): [0.6, 5]
sigma_y_range (tuple): [0.6, 5]
rotation range (tuple): [-math.pi/2, math.pi/2]
beta_range (tuple): [1, 4]
noise_range(tuple, optional): multiplicative kernel noise,
[0.75, 1.25]. Default: None
Returns:
kernel (ndarray):
"""
assert kernel_size % 2 == 1, 'Kernel size must be an odd number.'
assert sigma_x_range[0] < sigma_x_range[1], 'Wrong sigma_x_range.'
sigma_x = np.random.uniform(sigma_x_range[0], sigma_x_range[1])
if isotropic is False:
assert sigma_y_range[0] < sigma_y_range[1], 'Wrong sigma_y_range.'
assert rotation_range[0] < rotation_range[1], 'Wrong rotation_range.'
sigma_y = np.random.uniform(sigma_y_range[0], sigma_y_range[1])
rotation = np.random.uniform(rotation_range[0], rotation_range[1])
else:
sigma_y = sigma_x
rotation = 0
# TODO: this may be not proper
if np.random.uniform() < 0.5:
beta = np.random.uniform(beta_range[0], 1)
else:
beta = np.random.uniform(1, beta_range[1])
kernel = bivariate_plateau(kernel_size, sigma_x, sigma_y, rotation, beta, isotropic=isotropic)
# add multiplicative noise
if noise_range is not None:
assert noise_range[0] < noise_range[1], 'Wrong noise range.'
noise = np.random.uniform(noise_range[0], noise_range[1], size=kernel.shape)
kernel = kernel * noise
kernel = kernel / np.sum(kernel)
return kernel
def random_mixed_kernels(kernel_list,
kernel_prob,
kernel_size=21,
sigma_x_range=(0.6, 5),
sigma_y_range=(0.6, 5),
rotation_range=(-math.pi, math.pi),
betag_range=(0.5, 8),
betap_range=(0.5, 8),
noise_range=None):
"""Randomly generate mixed kernels.
Args:
kernel_list (tuple): a list name of kernel types,
support ['iso', 'aniso', 'skew', 'generalized', 'plateau_iso',
'plateau_aniso']
kernel_prob (tuple): corresponding kernel probability for each
kernel type
kernel_size (int):
sigma_x_range (tuple): [0.6, 5]
sigma_y_range (tuple): [0.6, 5]
rotation range (tuple): [-math.pi, math.pi]
beta_range (tuple): [0.5, 8]
noise_range(tuple, optional): multiplicative kernel noise,
[0.75, 1.25]. Default: None
Returns:
kernel (ndarray):
"""
kernel_type = random.choices(kernel_list, kernel_prob)[0]
if kernel_type == 'iso':
kernel = random_bivariate_Gaussian(
kernel_size, sigma_x_range, sigma_y_range, rotation_range, noise_range=noise_range, isotropic=True)
elif kernel_type == 'aniso':
kernel = random_bivariate_Gaussian(
kernel_size, sigma_x_range, sigma_y_range, rotation_range, noise_range=noise_range, isotropic=False)
elif kernel_type == 'generalized_iso':
kernel = random_bivariate_generalized_Gaussian(
kernel_size,
sigma_x_range,
sigma_y_range,
rotation_range,
betag_range,
noise_range=noise_range,
isotropic=True)
elif kernel_type == 'generalized_aniso':
kernel = random_bivariate_generalized_Gaussian(
kernel_size,
sigma_x_range,
sigma_y_range,
rotation_range,
betag_range,
noise_range=noise_range,
isotropic=False)
elif kernel_type == 'plateau_iso':
kernel = random_bivariate_plateau(
kernel_size, sigma_x_range, sigma_y_range, rotation_range, betap_range, noise_range=None, isotropic=True)
elif kernel_type == 'plateau_aniso':
kernel = random_bivariate_plateau(
kernel_size, sigma_x_range, sigma_y_range, rotation_range, betap_range, noise_range=None, isotropic=False)
return kernel
np.seterr(divide='ignore', invalid='ignore')
def circular_lowpass_kernel(cutoff, kernel_size, pad_to=0):
"""2D sinc filter
Reference: https://dsp.stackexchange.com/questions/58301/2-d-circularly-symmetric-low-pass-filter
Args:
cutoff (float): cutoff frequency in radians (pi is max)
kernel_size (int): horizontal and vertical size, must be odd.
pad_to (int): pad kernel size to desired size, must be odd or zero.
"""
assert kernel_size % 2 == 1, 'Kernel size must be an odd number.'
kernel = np.fromfunction(
lambda x, y: cutoff * special.j1(cutoff * np.sqrt(
(x - (kernel_size - 1) / 2)**2 + (y - (kernel_size - 1) / 2)**2)) / (2 * np.pi * np.sqrt(
(x - (kernel_size - 1) / 2)**2 + (y - (kernel_size - 1) / 2)**2)), [kernel_size, kernel_size])
kernel[(kernel_size - 1) // 2, (kernel_size - 1) // 2] = cutoff**2 / (4 * np.pi)
kernel = kernel / np.sum(kernel)
if pad_to > kernel_size:
pad_size = (pad_to - kernel_size) // 2
kernel = np.pad(kernel, ((pad_size, pad_size), (pad_size, pad_size)))
return kernel
# ------------------------------------------------------------- #
# --------------------------- noise --------------------------- #
# ------------------------------------------------------------- #
# ----------------------- Gaussian Noise ----------------------- #
def generate_gaussian_noise(img, sigma=10, gray_noise=False):
"""Generate Gaussian noise.
Args:
img (Numpy array): Input image, shape (h, w, c), range [0, 1], float32.
sigma (float): Noise scale (measured in range 255). Default: 10.
Returns:
(Numpy array): Returned noisy image, shape (h, w, c), range[0, 1],
float32.
"""
if gray_noise:
noise = np.float32(np.random.randn(*(img.shape[0:2]))) * sigma / 255.
noise = np.expand_dims(noise, axis=2).repeat(3, axis=2)
else:
noise = np.float32(np.random.randn(*(img.shape))) * sigma / 255.
return noise
def add_gaussian_noise(img, sigma=10, clip=True, rounds=False, gray_noise=False):
"""Add Gaussian noise.
Args:
img (Numpy array): Input image, shape (h, w, c), range [0, 1], float32.
sigma (float): Noise scale (measured in range 255). Default: 10.
Returns:
(Numpy array): Returned noisy image, shape (h, w, c), range[0, 1],
float32.
"""
noise = generate_gaussian_noise(img, sigma, gray_noise)
out = img + noise
if clip and rounds:
out = np.clip((out * 255.0).round(), 0, 255) / 255.
elif clip:
out = np.clip(out, 0, 1)
elif rounds:
out = (out * 255.0).round() / 255.
return out
def generate_gaussian_noise_pt(img, sigma=10, gray_noise=0):
"""Add Gaussian noise (PyTorch version).
Args:
img (Tensor): Shape (b, c, h, w), range[0, 1], float32.
scale (float | Tensor): Noise scale. Default: 1.0.
Returns:
(Tensor): Returned noisy image, shape (b, c, h, w), range[0, 1],
float32.
"""
b, _, h, w = img.size()
if not isinstance(sigma, (float, int)):
sigma = sigma.view(img.size(0), 1, 1, 1)
if isinstance(gray_noise, (float, int)):
cal_gray_noise = gray_noise > 0
else:
gray_noise = gray_noise.view(b, 1, 1, 1)
cal_gray_noise = torch.sum(gray_noise) > 0
if cal_gray_noise:
noise_gray = torch.randn(*img.size()[2:4], dtype=img.dtype, device=img.device) * sigma / 255.
noise_gray = noise_gray.view(b, 1, h, w)
# always calculate color noise
noise = torch.randn(*img.size(), dtype=img.dtype, device=img.device) * sigma / 255.
if cal_gray_noise:
noise = noise * (1 - gray_noise) + noise_gray * gray_noise
return noise
def add_gaussian_noise_pt(img, sigma=10, gray_noise=0, clip=True, rounds=False):
"""Add Gaussian noise (PyTorch version).
Args:
img (Tensor): Shape (b, c, h, w), range[0, 1], float32.
scale (float | Tensor): Noise scale. Default: 1.0.
Returns:
(Tensor): Returned noisy image, shape (b, c, h, w), range[0, 1],
float32.
"""
noise = generate_gaussian_noise_pt(img, sigma, gray_noise)
out = img + noise
if clip and rounds:
out = torch.clamp((out * 255.0).round(), 0, 255) / 255.
elif clip:
out = torch.clamp(out, 0, 1)
elif rounds:
out = (out * 255.0).round() / 255.
return out
# ----------------------- Random Gaussian Noise ----------------------- #
def random_generate_gaussian_noise(img, sigma_range=(0, 10), gray_prob=0):
sigma = np.random.uniform(sigma_range[0], sigma_range[1])
if np.random.uniform() < gray_prob:
gray_noise = True
else:
gray_noise = False
return generate_gaussian_noise(img, sigma, gray_noise)
def random_add_gaussian_noise(img, sigma_range=(0, 1.0), gray_prob=0, clip=True, rounds=False):
noise = random_generate_gaussian_noise(img, sigma_range, gray_prob)
out = img + noise
if clip and rounds:
out = np.clip((out * 255.0).round(), 0, 255) / 255.
elif clip:
out = np.clip(out, 0, 1)
elif rounds:
out = (out * 255.0).round() / 255.
return out
def random_generate_gaussian_noise_pt(img, sigma_range=(0, 10), gray_prob=0):
sigma = torch.rand(
img.size(0), dtype=img.dtype, device=img.device) * (sigma_range[1] - sigma_range[0]) + sigma_range[0]
gray_noise = torch.rand(img.size(0), dtype=img.dtype, device=img.device)
gray_noise = (gray_noise < gray_prob).float()
return generate_gaussian_noise_pt(img, sigma, gray_noise)
def random_add_gaussian_noise_pt(img, sigma_range=(0, 1.0), gray_prob=0, clip=True, rounds=False):
noise = random_generate_gaussian_noise_pt(img, sigma_range, gray_prob)
out = img + noise
if clip and rounds:
out = torch.clamp((out * 255.0).round(), 0, 255) / 255.
elif clip:
out = torch.clamp(out, 0, 1)
elif rounds:
out = (out * 255.0).round() / 255.
return out
# ----------------------- Poisson (Shot) Noise ----------------------- #
def generate_poisson_noise(img, scale=1.0, gray_noise=False):
"""Generate poisson noise.
Reference: https://github.com/scikit-image/scikit-image/blob/main/skimage/util/noise.py#L37-L219
Args:
img (Numpy array): Input image, shape (h, w, c), range [0, 1], float32.
scale (float): Noise scale. Default: 1.0.
gray_noise (bool): Whether generate gray noise. Default: False.
Returns:
(Numpy array): Returned noisy image, shape (h, w, c), range[0, 1],
float32.
"""
if gray_noise:
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# round and clip image for counting vals correctly
img = np.clip((img * 255.0).round(), 0, 255) / 255.
vals = len(np.unique(img))
vals = 2**np.ceil(np.log2(vals))
out = np.float32(np.random.poisson(img * vals) / float(vals))
noise = out - img
if gray_noise:
noise = np.repeat(noise[:, :, np.newaxis], 3, axis=2)
return noise * scale
def add_poisson_noise(img, scale=1.0, clip=True, rounds=False, gray_noise=False):
"""Add poisson noise.
Args:
img (Numpy array): Input image, shape (h, w, c), range [0, 1], float32.
scale (float): Noise scale. Default: 1.0.
gray_noise (bool): Whether generate gray noise. Default: False.
Returns:
(Numpy array): Returned noisy image, shape (h, w, c), range[0, 1],
float32.
"""
noise = generate_poisson_noise(img, scale, gray_noise)
out = img + noise
if clip and rounds:
out = np.clip((out * 255.0).round(), 0, 255) / 255.
elif clip:
out = np.clip(out, 0, 1)
elif rounds:
out = (out * 255.0).round() / 255.
return out
def generate_poisson_noise_pt(img, scale=1.0, gray_noise=0):
"""Generate a batch of poisson noise (PyTorch version)
Args:
img (Tensor): Input image, shape (b, c, h, w), range [0, 1], float32.
scale (float | Tensor): Noise scale. Number or Tensor with shape (b).
Default: 1.0.
gray_noise (float | Tensor): 0-1 number or Tensor with shape (b).
0 for False, 1 for True. Default: 0.
Returns:
(Tensor): Returned noisy image, shape (b, c, h, w), range[0, 1],
float32.
"""
b, _, h, w = img.size()
if isinstance(gray_noise, (float, int)):
cal_gray_noise = gray_noise > 0
else:
gray_noise = gray_noise.view(b, 1, 1, 1)
cal_gray_noise = torch.sum(gray_noise) > 0
if cal_gray_noise:
img_gray = rgb_to_grayscale(img, num_output_channels=1)
# round and clip image for counting vals correctly
img_gray = torch.clamp((img_gray * 255.0).round(), 0, 255) / 255.
# use for-loop to get the unique values for each sample
vals_list = [len(torch.unique(img_gray[i, :, :, :])) for i in range(b)]
vals_list = [2**np.ceil(np.log2(vals)) for vals in vals_list]
vals = img_gray.new_tensor(vals_list).view(b, 1, 1, 1)
out = torch.poisson(img_gray * vals) / vals
noise_gray = out - img_gray
noise_gray = noise_gray.expand(b, 3, h, w)
# always calculate color noise
# round and clip image for counting vals correctly
img = torch.clamp((img * 255.0).round(), 0, 255) / 255.
# use for-loop to get the unique values for each sample
vals_list = [len(torch.unique(img[i, :, :, :])) for i in range(b)]
vals_list = [2**np.ceil(np.log2(vals)) for vals in vals_list]
vals = img.new_tensor(vals_list).view(b, 1, 1, 1)
out = torch.poisson(img * vals) / vals
noise = out - img
if cal_gray_noise:
noise = noise * (1 - gray_noise) + noise_gray * gray_noise
if not isinstance(scale, (float, int)):
scale = scale.view(b, 1, 1, 1)
return noise * scale
def add_poisson_noise_pt(img, scale=1.0, clip=True, rounds=False, gray_noise=0):
"""Add poisson noise to a batch of images (PyTorch version).
Args:
img (Tensor): Input image, shape (b, c, h, w), range [0, 1], float32.
scale (float | Tensor): Noise scale. Number or Tensor with shape (b).
Default: 1.0.
gray_noise (float | Tensor): 0-1 number or Tensor with shape (b).
0 for False, 1 for True. Default: 0.
Returns:
(Tensor): Returned noisy image, shape (b, c, h, w), range[0, 1],
float32.
"""
noise = generate_poisson_noise_pt(img, scale, gray_noise)
out = img + noise
if clip and rounds:
out = torch.clamp((out * 255.0).round(), 0, 255) / 255.
elif clip:
out = torch.clamp(out, 0, 1)
elif rounds:
out = (out * 255.0).round() / 255.
return out
# ----------------------- Random Poisson (Shot) Noise ----------------------- #
def random_generate_poisson_noise(img, scale_range=(0, 1.0), gray_prob=0):
scale = np.random.uniform(scale_range[0], scale_range[1])
if np.random.uniform() < gray_prob:
gray_noise = True
else:
gray_noise = False
return generate_poisson_noise(img, scale, gray_noise)
def random_add_poisson_noise(img, scale_range=(0, 1.0), gray_prob=0, clip=True, rounds=False):
noise = random_generate_poisson_noise(img, scale_range, gray_prob)
out = img + noise
if clip and rounds:
out = np.clip((out * 255.0).round(), 0, 255) / 255.
elif clip:
out = np.clip(out, 0, 1)
elif rounds:
out = (out * 255.0).round() / 255.
return out
def random_generate_poisson_noise_pt(img, scale_range=(0, 1.0), gray_prob=0):
scale = torch.rand(
img.size(0), dtype=img.dtype, device=img.device) * (scale_range[1] - scale_range[0]) + scale_range[0]
gray_noise = torch.rand(img.size(0), dtype=img.dtype, device=img.device)
gray_noise = (gray_noise < gray_prob).float()
return generate_poisson_noise_pt(img, scale, gray_noise)
def random_add_poisson_noise_pt(img, scale_range=(0, 1.0), gray_prob=0, clip=True, rounds=False):
noise = random_generate_poisson_noise_pt(img, scale_range, gray_prob)
out = img + noise
if clip and rounds:
out = torch.clamp((out * 255.0).round(), 0, 255) / 255.
elif clip:
out = torch.clamp(out, 0, 1)
elif rounds:
out = (out * 255.0).round() / 255.
return out
# ------------------------------------------------------------------------ #
# --------------------------- JPEG compression --------------------------- #
# ------------------------------------------------------------------------ #
def add_jpg_compression(img, quality=90):
"""Add JPG compression artifacts.
Args:
img (Numpy array): Input image, shape (h, w, c), range [0, 1], float32.
quality (float): JPG compression quality. 0 for lowest quality, 100 for
best quality. Default: 90.
Returns:
(Numpy array): Returned image after JPG, shape (h, w, c), range[0, 1],
float32.
"""
img = np.clip(img, 0, 1)
encode_param = [int(cv2.IMWRITE_JPEG_QUALITY), quality]
_, encimg = cv2.imencode('.jpg', img * 255., encode_param)
img = np.float32(cv2.imdecode(encimg, 1)) / 255.
return img
def random_add_jpg_compression(img, quality_range=(90, 100)):
"""Randomly add JPG compression artifacts.
Args:
img (Numpy array): Input image, shape (h, w, c), range [0, 1], float32.
quality_range (tuple[float] | list[float]): JPG compression quality
range. 0 for lowest quality, 100 for best quality.
Default: (90, 100).
Returns:
(Numpy array): Returned image after JPG, shape (h, w, c), range[0, 1],
float32.
"""
quality = np.random.uniform(quality_range[0], quality_range[1])
return add_jpg_compression(img, quality)
basicsr/data/meta_info/meta_info_CED_h5_test.txt 0 → 100644
View file @ a75d2bda
people_dynamic_wave.h5 759
indoors_foosball_2.h5 269
simple_wires_2.h5 552
people_dynamic_dancing.h5 1175
people_dynamic_jumping.h5 792
simple_fruit_fast.h5 933
outdoor_jumping_infrared_2.h5 665
simple_carpet_fast.h5 602
people_dynamic_armroll.h5 792
indoors_kitchen_2.h5 635
people_dynamic_sitting.h5 1075
basicsr/data/meta_info/meta_info_CED_h5_train.txt 0 → 100644
View file @ a75d2bda
simple_rabbits.h5 742
simple_objects_dynamic.h5 1613
simple_color_keyboard_2.h5 160
simple_objects.h5 570
simple_wires_1.h5 370
simple_color_keyboard_3.h5 528
simple_jenga_1.h5 387
simple_color_keyboard_1.h5 263
simple_carpet.h5 1343
simple_flowers_infrared.h5 1039
simple_jenga_2.h5 848
simple_jenga_destroy.h5 355
simple_fruit.h5 891
indoors_foosball_1.h5 193
indoors_window_autoexposure.h5 706
indoors_corridor.h5 1008
indoors_kitchen_1.h5 422
indoors_kitchen_fast.h5 763
indoors_office.h5 1247
indoors_flying_room.h5 1062
indoors_foosball_3.h5 311
indoors_window.h5 766
indoors_dark_25ms.h5 529
indoors_very_dark_250ms.h5 94
indoors_dark_100ms.h5 266
indoors_very_dark_25ms.h5 603
calib_fluorescent_infrared.h5 263
calib_low.h5 217
calib_outdoor_density.h5 286
calib_outdoor.h5 286
calib_fluorescent_dynamic.h5 286
calib_fluorescent_density_infrared.h5 282
calib_fluorescent.h5 286
calib_outdoor_infrared.h5 286
calib_fluorescent_density.h5 286
calib_outdoor_hdr_infrared.h5 286
calib_outdoor_dynamic.h5 286
calib_low_density.h5 217
driving_city_4.h5 17503
driving_tunnel.h5 1498
driving_city_sun_2.h5 7734
driving_country_sun_2.h5 1180
driving_city_3.h5 6383
driving_country.h5 1088
driving_country_sun_1.h5 1722
driving_city_2.h5 6139
driving_city_5.h5 10541
driving_city_1.h5 9384
driving_city_sun_1.h5 1230
driving_tunnel_sun.h5 795
outdoor_jumping_1_infrared.h5 527
outdoor_shadow_1_infrared.h5 572
outdoor_shadow_density_infrared.h5 446
people_static_wave.h5 763
people_static_wave_clockwise.h5 716
people_static_air_guitar.h5 718
people_static_clap.h5 723
people_static_dancing_multiple_2.h5 321
people_static_dancing.h5 1041
people_static_jumping.h5 707
people_dynamic_wave_clockwise.h5 822
people_static_jogging.h5 731
people_static_wave_counterclockwise.h5 713
people_static_sitting.h5 1332
people_dynamic_dancing_multiple.h5 1844
people_dynamic_wave_counterclockwise.h5 827
people_dynamic_clap.h5 783
people_dynamic_jogging.h5 803
people_static_arm_roll.h5 707
people_static_dancing_multiple_1.h5 667
people_dynamic_air_guitar.h5 886
people_dynamic_selfie.h5 811
people_static_dancing_multiple_3.h5 267
basicsr/data/meta_info/meta_info_REDS_10y_h5_test.txt 0 → 100644
View file @ a75d2bda
test.h5 90
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment