Skip to content

GitLab

Commit 0f94318a authored by Zhe Chen's avatar Zhe Chen Committed by zhe chen
Browse files

[release] Add configs and models for cityscapes (#31) 

* add _base_ files

* support mapillary dataset

* reorganize ade20k configs

* move figs to docs

* release configs and models of cityscapes

* update README.md

* update load_from urls
parent 0f982e7a
Hide whitespace changes
Inline Side-by-side
Showing with 888 additions and 21 deletions
README.md
View file @ 0f94318a
......@@ -8,20 +8,22 @@
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/internimage-exploring-large-scale-vision/object-detection-on-pascal-voc-2012)](https://paperswithcode.com/sota/object-detection-on-pascal-voc-2012?p=internimage-exploring-large-scale-vision)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/internimage-exploring-large-scale-vision/object-detection-on-openimages-v6)](https://paperswithcode.com/sota/object-detection-on-openimages-v6?p=internimage-exploring-large-scale-vision)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/internimage-exploring-large-scale-vision/object-detection-on-crowdhuman-full-body)](https://paperswithcode.com/sota/object-detection-on-crowdhuman-full-body?p=internimage-exploring-large-scale-vision)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/internimage-exploring-large-scale-vision/2d-object-detection-on-bdd100k-val)](https://paperswithcode.com/sota/2d-object-detection-on-bdd100k-val?p=internimage-exploring-large-scale-vision)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/internimage-exploring-large-scale-vision/semantic-segmentation-on-ade20k)](https://paperswithcode.com/sota/semantic-segmentation-on-ade20k?p=internimage-exploring-large-scale-vision)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/internimage-exploring-large-scale-vision/semantic-segmentation-on-cityscapes)](https://paperswithcode.com/sota/semantic-segmentation-on-cityscapes?p=internimage-exploring-large-scale-vision)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/internimage-exploring-large-scale-vision/semantic-segmentation-on-cityscapes-val)](https://paperswithcode.com/sota/semantic-segmentation-on-cityscapes-val?p=internimage-exploring-large-scale-vision)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/internimage-exploring-large-scale-vision/semantic-segmentation-on-pascal-context)](https://paperswithcode.com/sota/semantic-segmentation-on-pascal-context?p=internimage-exploring-large-scale-vision)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/internimage-exploring-large-scale-vision/semantic-segmentation-on-coco-stuff-test)](https://paperswithcode.com/sota/semantic-segmentation-on-coco-stuff-test?p=internimage-exploring-large-scale-vision)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/bevformer-v2-adapting-modern-image-backbones/3d-object-detection-on-nuscenes-camera-only)](https://paperswithcode.com/sota/3d-object-detection-on-nuscenes-camera-only?p=bevformer-v2-adapting-modern-image-backbones)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/internimage-exploring-large-scale-vision/image-classification-on-inaturalist-2018)](https://paperswithcode.com/sota/image-classification-on-inaturalist-2018?p=internimage-exploring-large-scale-vision)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/internimage-exploring-large-scale-vision/image-classification-on-places365)](https://paperswithcode.com/sota/image-classification-on-places365?p=internimage-exploring-large-scale-vision)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/internimage-exploring-large-scale-vision/image-classification-on-places205)](https://paperswithcode.com/sota/image-classification-on-places205?p=internimage-exploring-large-scale-vision)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/internimage-exploring-large-scale-vision/2d-object-detection-on-bdd100k-val)](https://paperswithcode.com/sota/2d-object-detection-on-bdd100k-val?p=internimage-exploring-large-scale-vision)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/internimage-exploring-large-scale-vision/image-classification-on-imagenet)](https://paperswithcode.com/sota/image-classification-on-imagenet?p=internimage-exploring-large-scale-vision)
This repository is an official implementation of the [InternImage: Exploring Large-Scale Vision Foundation Models with
Deformable Convolutions](https://arxiv.org/abs/2211.05778).
[Paper](https://arxiv.org/abs/2211.05778) \| [Blog in Chinese](https://zhuanlan.zhihu.com/p/610772005)
[Paper](https://arxiv.org/abs/2211.05778) \| [Blog in Chinese](https://zhuanlan.zhihu.com/p/610772005) | [Documents](./docs/)
## News
- `Feb 28, 2023`: InternImage is accepted to CVPR 2023!
......@@ -46,12 +48,19 @@ It takes deformable convolution as the core operator to obtain large effective r
to reduces the strict inductive bias. Our model makes it possible to learn more stronger and robust models with large-scale parameters from massive data.
<div align=center>
<img src='./figs/arch.png' width=400>
<img src='./docs/figs/arch.png' width=400>
</div>
## Model Zoo
- Object Detection and Instance Segmentation: [COCO](detection/configs/mask_rcnn/)
- Semantic Segmentation: [ADE20K](segmentation/configs/ade20k/), [Cityscapes](segmentation/configs/cityscapes/)
## Main Results on ImageNet with Pretrained Models
**ImageNet-1K and ImageNet-22K Pretrained InternImage Models**
**ImageNet-1K and ImageNet-22K Pretrained Models**
| name | pretrain | resolution | acc@1 | #param | FLOPs | 22K model | 1K model |
| :------------: | :----------: | :--------: | :---: | :-----: | :---: | :-----------------: | :-----------------: |
......@@ -82,15 +91,15 @@ to reduces the strict inductive bias. Our model makes it possible to learn more
| backbone | resolution | single scale | multi scale | #param | FLOPs | Download |
| :------------: | :--------: | :----------: | :---------: | :-----: | :---: | :---: |
| InternImage-T | 512x512 | 47.9 | 48.1 | 59M | 944G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/seg_models/upernet_internimage_t_512_160k_ade20k.pth) \| [cfg](segmentation/configs/upernet/upernet_internimage_t_512_160k_ade20k.py) |
| InternImage-S | 512x512 | 50.1 | 50.9 | 80M | 1017G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/seg_models/upernet_internimage_s_512_160k_ade20k.pth) \| [cfg](segmentation/configs/upernet/upernet_internimage_s_512_160k_ade20k.py) |
| InternImage-B | 512x512 | 50.8 | 51.3 | 128M | 1185G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/seg_models/upernet_internimage_b_512_160k_ade20k.pth) \| [cfg](segmentation/configs/upernet/upernet_internimage_b_512_160k_ade20k.py) |
| InternImage-L | 640x640 | 53.9 | 54.1 | 256M | 2526G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/seg_models/upernet_internimage_l_640_160k_ade20k.pth) \| [cfg](segmentation/configs/upernet/upernet_internimage_l_640_160k_ade20k.py) |
| InternImage-XL | 640x640 | 55.0 | 55.3 | 368M | 3142G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/seg_models/upernet_internimage_xl_640_160k_ade20k.pth) \| [cfg](segmentation/configs/upernet/upernet_internimage_xl_640_160k_ade20k.py) |
| InternImage-T | 512x512 | 47.9 | 48.1 | 59M | 944G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/seg_models/upernet_internimage_t_512_160k_ade20k.pth) \| [cfg](segmentation/configs/ade20k/upernet_internimage_t_512_160k_ade20k.py) |
| InternImage-S | 512x512 | 50.1 | 50.9 | 80M | 1017G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/seg_models/upernet_internimage_s_512_160k_ade20k.pth) \| [cfg](segmentation/configs/ade20k/upernet_internimage_s_512_160k_ade20k.py) |
| InternImage-B | 512x512 | 50.8 | 51.3 | 128M | 1185G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/seg_models/upernet_internimage_b_512_160k_ade20k.pth) \| [cfg](segmentation/configs/ade20k/upernet_internimage_b_512_160k_ade20k.py) |
| InternImage-L | 640x640 | 53.9 | 54.1 | 256M | 2526G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/seg_models/upernet_internimage_l_640_160k_ade20k.pth) \| [cfg](segmentation/configs/ade20k/upernet_internimage_l_640_160k_ade20k.py) |
| InternImage-XL | 640x640 | 55.0 | 55.3 | 368M | 3142G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/seg_models/upernet_internimage_xl_640_160k_ade20k.pth) \| [cfg](segmentation/configs/ade20k/upernet_internimage_xl_640_160k_ade20k.py) |
## Main Results of FPS
| name | resolution | #params | FLOPs | Batch 1 FPS(TensorRT) |
| name | resolution | #param | FLOPs | Batch 1 FPS(TensorRT) |
| :------------: | :--------: | :-----: | :---: | :-------------------: |
| InternImage-T | 224x224 | 30M | 5G | 156 |
| InternImage-S | 224x224 | 50M | 8G | 129 |
......
segmentation/README.md
View file @ 0f94318a
......@@ -4,6 +4,14 @@ This folder contains the implementation of the InternImage for semantic segmenta
Our segmentation code is developed on top of [MMSegmentation v0.27.0](https://github.com/open-mmlab/mmsegmentation/tree/v0.27.0).
## Model Zoo
- [x] [ADE20K](configs/ade20k/)
- [x] [Cityscapes](configs/cityscapes/)
- [ ] COCO-Stuff-164K
- [ ] COCO-Stuff-10K
- [ ] Pascal Context
- [ ] NYU Depth V2
## Usage
......@@ -29,7 +37,7 @@ conda activate internimage
For examples, to install torch==1.11 with CUDA==11.3:
```bash
pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113 -f https://download.pytorch.org/whl/torch_stable.html
pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113 -f https://download.pytorch.org/whl/torch_stable.html
```
- Install `timm==0.6.11` and `mmcv-full==1.5.0`:
......@@ -54,9 +62,9 @@ sh ./make.sh
python test.py
```
## Data Preparation
### Data Preparation
Prepare ADE20K according to the [guidelines](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/en/dataset_prepare.md#prepare-datasets) in MMSegmentation.
Prepare datasets according to the [guidelines](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/en/dataset_prepare.md#prepare-datasets) in MMSegmentation.
### Evaluation
......@@ -70,16 +78,16 @@ sh dist_test.sh <config-file> <checkpoint> <gpu-num> --eval mIoU
For example, to evaluate the `InternImage-T` with a single GPU:
```bash
python test.py configs/upernet/upernet_internimage_t_512_160k_ade20k.py checkpoint_dir/seg/upernet_internimage_t_512_160k_ade20k.pth --eval mIoU
python test.py configs/ade20k/upernet_internimage_t_512_160k_ade20k.py checkpoint_dir/seg/upernet_internimage_t_512_160k_ade20k.pth --eval mIoU
```
For example, to evaluate the `InternImage-B` with a single node with 8 GPUs:
```bash
sh dist_test.sh configs/upernet/upernet_internimage_b_512_160k_ade20k.py checkpoint_dir/seg/upernet_internimage_b_512_160k_ade20k.py 8 --eval mIoU
sh dist_test.sh configs/ade20k/upernet_internimage_b_512_160k_ade20k.py checkpoint_dir/seg/upernet_internimage_b_512_160k_ade20k.pth 8 --eval mIoU
```
### Training on ADE20K
### Training
To train an `InternImage` on ADE20K, run:
......@@ -87,16 +95,26 @@ To train an `InternImage` on ADE20K, run:
sh dist_train.sh <config-file> <gpu-num>
```
For example, to train `InternImage-T` with 8 GPU on 1 node, run:
For example, to train `InternImage-T` with 8 GPU on 1 node (total batch size 16), run:
```bash
sh dist_train.sh configs/upernet/upernet_internimage_t_512_160k_ade20k.py 8
sh dist_train.sh configs/ade20k/upernet_internimage_t_512_160k_ade20k.py 8
```
### Manage jobs with Srun
### Manage Jobs with Slurm
For example, to train `InternImage-XL` with 8 GPU on 1 node, run:
For example, to train `InternImage-XL` with 8 GPU on 1 node (total batch size 16), run:
```bash
GPUS=8 sh slurm_train.sh <partition> <job-name> configs/upernet/upernet_internimage_xl_640_160k_ade20k.py
GPUS=8 sh slurm_train.sh <partition> <job-name> configs/ade20k/upernet_internimage_xl_640_160k_ade20k.py
```
### Image Demo
To inference a single image like this:
```
CUDA_VISIBLE_DEVICES=0 python image_demo.py \
data/ade/ADEChallengeData2016/images/validation/ADE_val_00000591.jpg \
configs/ade20k/upernet_internimage_t_512_160k_ade20k.py \
checkpoint_dir/seg/upernet_internimage_t_512_160k_ade20k.pth \
--palette ade20k
```
segmentation/configs/_base_/datasets/chase_db1.py 0 → 100644
View file @ 0f94318a
# dataset settings
dataset_type = 'ChaseDB1Dataset'
data_root = 'data/CHASE_DB1'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
img_scale = (960, 999)
crop_size = (128, 128)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(type='Resize', img_scale=img_scale, ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=img_scale,
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75, 2.0],
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=4,
workers_per_gpu=4,
train=dict(
type='RepeatDataset',
times=40000,
dataset=dict(
type=dataset_type,
data_root=data_root,
img_dir='images/training',
ann_dir='annotations/training',
pipeline=train_pipeline)),
val=dict(
type=dataset_type,
data_root=data_root,
img_dir='images/validation',
ann_dir='annotations/validation',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
data_root=data_root,
img_dir='images/validation',
ann_dir='annotations/validation',
pipeline=test_pipeline))
segmentation/configs/_base_/datasets/cityscapes.py 0 → 100644
View file @ 0f94318a
# dataset settings
dataset_type = 'CityscapesDataset'
data_root = 'data/cityscapes/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (512, 1024)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(type='Resize', img_scale=(2048, 1024), ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2048, 1024),
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
data_root=data_root,
img_dir='leftImg8bit/train',
ann_dir='gtFine/train',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
data_root=data_root,
img_dir='leftImg8bit/val',
ann_dir='gtFine/val',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
data_root=data_root,
img_dir='leftImg8bit/val',
ann_dir='gtFine/val',
pipeline=test_pipeline))
segmentation/configs/_base_/datasets/cityscapes_1024x1024.py 0 → 100644
View file @ 0f94318a
_base_ = './cityscapes.py'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (1024, 1024)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(type='Resize', img_scale=(2048, 1024), ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2048, 1024),
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
segmentation/configs/_base_/datasets/cityscapes_extra.py 0 → 100644
View file @ 0f94318a
# dataset settings
dataset_type = 'CityscapesDataset'
data_root = 'data/cityscapes/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (512, 1024)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(type='Resize', img_scale=(2048, 1024), ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2048, 1024),
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
data_root=data_root,
img_dir=['leftImg8bit/train', 'leftImg8bit/train_extra'],
ann_dir=['gtFine/train', 'refinement_final/train_extra'],
pipeline=train_pipeline),
val=dict(
type=dataset_type,
data_root=data_root,
img_dir='leftImg8bit/val',
ann_dir='gtFine/val',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
data_root=data_root,
img_dir='leftImg8bit/val',
ann_dir='gtFine/val',
pipeline=test_pipeline))
segmentation/configs/_base_/datasets/coco-stuff10k.py 0 → 100644
View file @ 0f94318a
# dataset settings
dataset_type = 'COCOStuffDataset'
data_root = 'data/coco_stuff10k'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (512, 512)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', reduce_zero_label=True),
dict(type='Resize', img_scale=(2048, 512), ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2048, 512),
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=4,
workers_per_gpu=4,
train=dict(
type=dataset_type,
data_root=data_root,
reduce_zero_label=True,
img_dir='images/train2014',
ann_dir='annotations/train2014',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
data_root=data_root,
reduce_zero_label=True,
img_dir='images/test2014',
ann_dir='annotations/test2014',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
data_root=data_root,
reduce_zero_label=True,
img_dir='images/test2014',
ann_dir='annotations/test2014',
pipeline=test_pipeline))
segmentation/configs/_base_/datasets/coco-stuff164k.py 0 → 100644
View file @ 0f94318a
# dataset settings
dataset_type = 'COCOStuffDataset'
data_root = 'data/coco_stuff164k'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (512, 512)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(type='Resize', img_scale=(2048, 512), ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2048, 512),
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=4,
workers_per_gpu=4,
train=dict(
type=dataset_type,
data_root=data_root,
img_dir='images/train2017',
ann_dir='annotations/train2017',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
data_root=data_root,
img_dir='images/val2017',
ann_dir='annotations/val2017',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
data_root=data_root,
img_dir='images/val2017',
ann_dir='annotations/val2017',
pipeline=test_pipeline))
segmentation/configs/_base_/datasets/drive.py 0 → 100644
View file @ 0f94318a
# dataset settings
dataset_type = 'DRIVEDataset'
data_root = 'data/DRIVE'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
img_scale = (584, 565)
crop_size = (64, 64)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(type='Resize', img_scale=img_scale, ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=img_scale,
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75, 2.0],
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=4,
workers_per_gpu=4,
train=dict(
type='RepeatDataset',
times=40000,
dataset=dict(
type=dataset_type,
data_root=data_root,
img_dir='images/training',
ann_dir='annotations/training',
pipeline=train_pipeline)),
val=dict(
type=dataset_type,
data_root=data_root,
img_dir='images/validation',
ann_dir='annotations/validation',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
data_root=data_root,
img_dir='images/validation',
ann_dir='annotations/validation',
pipeline=test_pipeline))
segmentation/configs/_base_/datasets/hrf.py 0 → 100644
View file @ 0f94318a
# dataset settings
dataset_type = 'HRFDataset'
data_root = 'data/HRF'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
img_scale = (2336, 3504)
crop_size = (256, 256)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(type='Resize', img_scale=img_scale, ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=img_scale,
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75, 2.0],
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=4,
workers_per_gpu=4,
train=dict(
type='RepeatDataset',
times=40000,
dataset=dict(
type=dataset_type,
data_root=data_root,
img_dir='images/training',
ann_dir='annotations/training',
pipeline=train_pipeline)),
val=dict(
type=dataset_type,
data_root=data_root,
img_dir='images/validation',
ann_dir='annotations/validation',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
data_root=data_root,
img_dir='images/validation',
ann_dir='annotations/validation',
pipeline=test_pipeline))
segmentation/configs/_base_/datasets/loveda.py 0 → 100644
View file @ 0f94318a
# dataset settings
dataset_type = 'LoveDADataset'
data_root = 'data/loveDA'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (512, 512)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', reduce_zero_label=True),
dict(type='Resize', img_scale=(2048, 512), ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1024, 1024),
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=4,
workers_per_gpu=4,
train=dict(
type=dataset_type,
data_root=data_root,
img_dir='img_dir/train',
ann_dir='ann_dir/train',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
data_root=data_root,
img_dir='img_dir/val',
ann_dir='ann_dir/val',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
data_root=data_root,
img_dir='img_dir/val',
ann_dir='ann_dir/val',
pipeline=test_pipeline))
segmentation/configs/_base_/datasets/mapillary.py 0 → 100644
View file @ 0f94318a
# dataset settings
dataset_type = 'MapillaryDataset'
data_root = 'data/Mapillary/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (512, 1024)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(type='MapillaryHack'),
dict(type='Resize', img_scale=(2048, 1024), ratio_range=(0.5, 1.0)),
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2048, 1024),
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
data_root='data/Mapillary/',
img_dir=['training/images', 'validation/images'],
ann_dir=['training/labels', 'validation/labels'],
pipeline=train_pipeline),
val=dict(
type='CityscapesDataset',
data_root='data/cityscapes/',
img_dir='leftImg8bit/val',
ann_dir='gtFine/val',
pipeline=test_pipeline),
test=dict(
type='CityscapesDataset',
data_root='data/cityscapes/',
img_dir='leftImg8bit/val',
ann_dir='gtFine/val',
pipeline=test_pipeline))
segmentation/configs/_base_/datasets/mapillary_1024x1024.py 0 → 100644
View file @ 0f94318a
# dataset settings
dataset_type = 'MapillaryDataset'
data_root = 'data/Mapillary/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (1024, 1024)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(type='MapillaryHack'),
dict(type='Resize', img_scale=(2048, 1024), ratio_range=(0.5, 1.0)),
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2048, 1024),
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
data_root='data/Mapillary/',
img_dir=['training/images', 'validation/images'],
ann_dir=['training/labels', 'validation/labels'],
pipeline=train_pipeline),
val=dict(
type='CityscapesDataset',
data_root='data/cityscapes/',
img_dir='leftImg8bit/val',
ann_dir='gtFine/val',
pipeline=test_pipeline),
test=dict(
type='CityscapesDataset',
data_root='data/cityscapes/',
img_dir='leftImg8bit/val',
ann_dir='gtFine/val',
pipeline=test_pipeline))
segmentation/configs/_base_/datasets/nyu_depth_v2.py 0 → 100644
View file @ 0f94318a
# dataset settings
dataset_type = 'NYUDepthV2Dataset'
data_root = 'data/nyu_depth_v2/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (480, 480)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', reduce_zero_label=True),
dict(type='Resize', img_scale=(640, 480), ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(640, 480),
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=4,
workers_per_gpu=4,
train=dict(
type=dataset_type,
data_root=data_root,
img_dir='image',
ann_dir='label40',
split='train.txt',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
data_root=data_root,
img_dir='image',
ann_dir='label40',
split='test.txt',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
data_root=data_root,
img_dir='image',
ann_dir='label40',
split='test.txt',
pipeline=test_pipeline))
segmentation/configs/_base_/datasets/pascal_context.py 0 → 100644
View file @ 0f94318a
# dataset settings
dataset_type = 'PascalContextDataset'
data_root = 'data/VOCdevkit/VOC2010/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
img_scale = (520, 520)
crop_size = (480, 480)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(type='Resize', img_scale=img_scale, ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=img_scale,
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=4,
workers_per_gpu=4,
train=dict(
type=dataset_type,
data_root=data_root,
img_dir='JPEGImages',
ann_dir='SegmentationClassContext',
split='ImageSets/SegmentationContext/train.txt',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
data_root=data_root,
img_dir='JPEGImages',
ann_dir='SegmentationClassContext',
split='ImageSets/SegmentationContext/val.txt',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
data_root=data_root,
img_dir='JPEGImages',
ann_dir='SegmentationClassContext',
split='ImageSets/SegmentationContext/val.txt',
pipeline=test_pipeline))
segmentation/configs/_base_/datasets/pascal_context_59.py 0 → 100644
View file @ 0f94318a
# dataset settings
dataset_type = 'PascalContextDataset59'
data_root = 'data/VOCdevkit/VOC2010/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
img_scale = (520, 520)
crop_size = (480, 480)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', reduce_zero_label=True),
dict(type='Resize', img_scale=img_scale, ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=img_scale,
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=4,
workers_per_gpu=4,
train=dict(
type=dataset_type,
data_root=data_root,
img_dir='JPEGImages',
ann_dir='SegmentationClassContext',
split='ImageSets/SegmentationContext/train.txt',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
data_root=data_root,
img_dir='JPEGImages',
ann_dir='SegmentationClassContext',
split='ImageSets/SegmentationContext/val.txt',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
data_root=data_root,
img_dir='JPEGImages',
ann_dir='SegmentationClassContext',
split='ImageSets/SegmentationContext/val.txt',
pipeline=test_pipeline))
segmentation/configs/_base_/datasets/pascal_voc12.py 0 → 100644
View file @ 0f94318a
# dataset settings
dataset_type = 'PascalVOCDataset'
data_root = 'data/VOCdevkit/VOC2012'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (512, 512)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(type='Resize', img_scale=(2048, 512), ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2048, 512),
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=4,
workers_per_gpu=4,
train=dict(
type=dataset_type,
data_root=data_root,
img_dir='JPEGImages',
ann_dir='SegmentationClass',
split='ImageSets/Segmentation/train.txt',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
data_root=data_root,
img_dir='JPEGImages',
ann_dir='SegmentationClass',
split='ImageSets/Segmentation/val.txt',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
data_root=data_root,
img_dir='JPEGImages',
ann_dir='SegmentationClass',
split='ImageSets/Segmentation/val.txt',
pipeline=test_pipeline))
segmentation/configs/_base_/datasets/pascal_voc12_aug.py 0 → 100644
View file @ 0f94318a
_base_ = './pascal_voc12.py'
# dataset settings
data = dict(
train=dict(
ann_dir=['SegmentationClass', 'SegmentationClassAug'],
split=[
'ImageSets/Segmentation/train.txt',
'ImageSets/Segmentation/aug.txt'
]))
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