Skip to content

GitLab

Commit 3a6df602 authored by chenzk's avatar chenzk
Browse files

v1.0

parents
Pipeline #1196 canceled with stages
Show whitespace changes
Inline Side-by-side
Showing with 1535 additions and 0 deletions
.gitignore 0 → 100644
View file @ 3a6df602
wandb
coreml
pretrain
**/__pycache__
pretrain
ignore
*.zip
checkpoints
trt
\ No newline at end of file
LICENSE 0 → 100644
View file @ 3a6df602
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 @ 3a6df602
# RepViT
RepViT在iPhone 12上以1ms的延迟实现了超过80%的top-1准确率，为当前多个SOTA实例分割算法的backbone。
## 论文
`RepViT: Revisiting Mobile CNN From ViT Perspective`
- https://arxiv.org/pdf/2307.09283
## 模型结构
RepViT以MobileNetV3-L为base进行算法优化，从一个标准的轻量级CNN开始，结合轻量级vit的架构设计，使得既具备CNN小计算量又具备vit架构的优势。
<div align=center>
<img src="./doc/structure.png"/>
</div>
## 算法原理
RepViT与其它图像分类算法一样，将图片数据送入模型后，依次通过预处理、特征提取，然后经过全连接层预测出图片类别。
<div align=center>
<img src="./doc/algorithm.png"/>
</div>
## 环境配置
```
mv repvit_pytorch RepViT # 去框架名后缀
```
### Docker（方法一）
```
docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-centos7.6-dtk24.04-py310
# <your IMAGE ID>为以上拉取的docker的镜像ID替换，本镜像为：c85ed27005f2
docker run -it --shm-size=32G -v $PWD/RepViT:/home/RepViT -v /opt/hyhal:/opt/hyhal:ro --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name repvit <your IMAGE ID> bash
cd /home/RepViT
pip install -r requirements.txt # requirements.txt
```
### Dockerfile（方法二）
```
cd RepViT/docker
docker build --no-cache -t repvit:latest .
docker run --shm-size=32G --name repvit -v /opt/hyhal:/opt/hyhal:ro --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video -v $PWD/../../RepViT:/home/RepViT -it repvit bash
# 若遇到Dockerfile启动的方式安装环境需要长时间等待，可注释掉里面的pip安装，启动容器后再安装python库：pip install -r requirements.txt。
```
### 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
python:python3.10
torch:2.1.0
torchvision:0.16.0
onnxruntime:1.15.0
```
`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 # requirements.txt
```
## 数据集
`cifar100`
- http://www.cs.toronto.edu/~kriz/cifar-100-python.tar.gz
下载解压即可使用，文件大小约161Mb，训练数据目录结构如下：
```
cifar100/cifar-100-python
├── train
├── test
├── meta
└── file.txt~
```
## 训练
### 单机多卡
```
# 以数据集CIFAR为基础进行算法效果提升
# 关闭wandb用wandb disabled
python -m torch.distributed.launch --nproc_per_node=4 --master_port 12356 --use_env main.py --model repvit_m0_9 --data-path ./cifar100 --data-set CIFAR --epochs 300 --dist-eval --distillation-type none
```
更多资料可参考源项目的[`README_origin`](./README_origin.md)
## result
### 精度
数据集：cifar100，max epoch为300，推理框架：pytorch。
| device | top-1 acc |
|:---------:|:---------:|
| DCU K100 | 81.84% |
| GPU V100S | 81.72% |
## 应用场景
### 算法类别
`图像分类`
### 热点应用行业
`制造,电商,医疗,能源,教育`
## 源码仓库及问题反馈
- http://developer.hpccube.com/codes/modelzoo/repvit_pytorch.git
## 参考资料
- https://github.com/THU-MIG/RepViT.git
README_origin.md 0 → 100644
View file @ 3a6df602
# [RepViT-SAM: Towards Real-Time Segmenting Anything](https://arxiv.org/abs/2312.05760)
# [RepViT: Revisiting Mobile CNN From ViT Perspective](https://arxiv.org/abs/2307.09283)
Official PyTorch implementation of **RepViT-SAM** and **RepViT**. CVPR 2024.
<p align="center">
<img src="sam/figures/comparison.png" width=80%> <br>
Models are deployed on iPhone 12 with Core ML Tools to get latency.
</p>
<p align="center">
<img src="figures/latency.png" width=70%> <br>
Models are trained on ImageNet-1K and deployed on iPhone 12 with Core ML Tools to get latency.
</p>
[RepViT-SAM: Towards Real-Time Segmenting Anything](https://arxiv.org/abs/2312.05760).\
Ao Wang, Hui Chen, Zijia Lin, Jungong Han, and Guiguang Ding\
[[`arXiv`](https://arxiv.org/abs/2312.05760)] [[`Project Page`](https://jameslahm.github.io/repvit-sam)]
<details>
<summary>
<font size="+1">Abstract</font>
</summary>
Segment Anything Model (SAM) has shown impressive zero-shot transfer performance for various computer vision tasks recently. However, its heavy computation costs remain daunting for practical applications. MobileSAM proposes to replace the heavyweight image encoder in SAM with TinyViT by employing distillation, which results in a significant reduction in computational requirements. However, its deployment on resource-constrained mobile devices still encounters challenges due to the substantial memory and computational overhead caused by self-attention mechanisms. Recently, RepViT achieves the state-of-the-art performance and latency trade-off on mobile devices by incorporating efficient architectural designs of ViTs into CNNs. Here, to achieve real-time segmenting anything on mobile devices, following, we replace the heavyweight image encoder in SAM with RepViT model, ending up with the RepViT-SAM model. Extensive experiments show that RepViT-SAM can enjoy significantly better zero-shot transfer capability than MobileSAM, along with nearly $10\times$ faster inference speed.
</details>
<br/>
[RepViT: Revisiting Mobile CNN From ViT Perspective](https://arxiv.org/abs/2307.09283).\
Ao Wang, Hui Chen, Zijia Lin, Jungong Han, and Guiguang Ding\
[[`arXiv`](https://arxiv.org/abs/2307.09283)]
<details>
<summary>
<font size="+1">Abstract</font>
</summary>
Recently, lightweight Vision Transformers (ViTs) demonstrate superior performance and lower latency compared with lightweight Convolutional Neural Networks (CNNs) on resource-constrained mobile devices. This improvement is usually attributed to the multi-head self-attention module, which enables the model to learn global representations. However, the architectural disparities between lightweight ViTs and lightweight CNNs have not been adequately examined. In this study, we revisit the efficient design of lightweight CNNs and emphasize their potential for mobile devices. We incrementally enhance the mobile-friendliness of a standard lightweight CNN, specifically MobileNetV3, by integrating the efficient architectural choices of lightweight ViTs. This ends up with a new family of pure lightweight CNNs, namely RepViT. Extensive experiments show that RepViT outperforms existing state-of-the-art lightweight ViTs and exhibits favorable latency in various vision tasks. On ImageNet, RepViT achieves over 80\% top-1 accuracy with 1ms latency on an iPhone 12, which is the first time for a lightweight model, to the best of our knowledge. Our largest model, RepViT-M2.3, obtains 83.7\% accuracy with only 2.3ms latency.
</details>
<br/>
<br/>
**UPDATES** 🔥
- 2023/12/17: [Grounding-SAM](https://github.com/IDEA-Research/Grounded-Segment-Anything/tree/main) supports RepViT-SAM with [Grounded-RepViT-SAM](https://github.com/IDEA-Research/Grounded-Segment-Anything/tree/main/EfficientSAM#run-grounded-repvit-sam-demo). Thanks!
- 2023/12/11: RepViT-SAM has been released. Please refer to [RepViT-SAM](./sam/README.md).
- 2023/12/11: RepViT-M0.6 has been released, achieving 74.1% with ~0.6ms latency. Its checkpoint is [here](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m0_6_distill_300e.pth)
- 2023/09/28: RepViT-M0.9/1.0/1.1/1.5/2.3 models have been released.
- 2023/07/27: RepViT models have been integrated into timm. See https://github.com/huggingface/pytorch-image-models/pull/1876.
<br/>
## Classification on ImageNet-1K
### Models
| Model | Top-1 (300 / 450)| #params | MACs | Latency | Ckpt | Core ML | Log |
|:---------------|:----:|:---:|:--:|:--:|:--:|:--:|:--:|
| M0.9 | 78.7 / 79.1 | 5.1M | 0.8G | 0.9ms | [300e](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m0_9_distill_300e.pth) / [450e](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m0_9_distill_450e.pth) | [300e](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m0_9_distiall_300e_224.mlmodel) / [450e](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m0_9_distiall_450e_224.mlmodel) | [300e](./logs/repvit_m0_9_distill_300e.txt) / [450e](./logs/repvit_m0_9_distill_450e.txt) |
| M1.0 | 80.0 / 80.3 | 6.8M | 1.1G | 1.0ms | [300e](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m1_0_distill_300e.pth) / [450e](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m1_0_distill_450e.pth) | [300e](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m1_0_distiall_300e_224.mlmodel) / [450e](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m1_0_distiall_450e_224.mlmodel) | [300e](./logs/repvit_m1_0_distill_300e.txt) / [450e](./logs/repvit_m1_0_distill_450e.txt) |
| M1.1 | 80.7 / 81.2 | 8.2M | 1.3G | 1.1ms | [300e](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m1_1_distill_300e.pth) / [450e](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m1_1_distill_450e.pth) | [300e](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m1_1_distiall_300e_224.mlmodel) / [450e](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m1_1_distiall_450e_224.mlmodel) | [300e](./logs/repvit_m1_1_distill_300e.txt) / [450e](./logs/repvit_m1_1_distill_450e.txt) |
| M1.5 | 82.3 / 82.5 | 14.0M | 2.3G | 1.5ms | [300e](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m1_5_distill_300e.pth) / [450e](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m1_5_distill_450e.pth) | [300e](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m1_5_distiall_300e_224.mlmodel) / [450e](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m1_5_distiall_450e_224.mlmodel) | [300e](./logs/repvit_m1_5_distill_300e.txt) / [450e](./logs/repvit_m1_5_distill_450e.txt) |
| M2.3 | 83.3 / 83.7 | 22.9M | 4.5G | 2.3ms | [300e](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m2_3_distill_300e.pth) / [450e](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m2_3_distill_450e.pth) | [300e](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m2_3_distiall_300e_224.mlmodel) / [450e](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m2_3_distiall_450e_224.mlmodel) | [300e](./logs/repvit_m2_3_distill_300e.txt) / [450e](./logs/repvit_m2_3_distill_450e.txt) |
Tips: Convert a training-time RepViT into the inference-time structure
```
from timm.models import create_model
import utils
model = create_model('repvit_m0_9')
utils.replace_batchnorm(model)
```
## Latency Measurement
The latency reported in RepViT for iPhone 12 (iOS 16) uses the benchmark tool from [XCode 14](https://developer.apple.com/videos/play/wwdc2022/10027/).
For example, here is a latency measurement of RepViT-M0.9:
![](./figures/repvit_m0_9_latency.png)
Tips: export the model to Core ML model
```
python export_coreml.py --model repvit_m0_9 --ckpt pretrain/repvit_m0_9_distill_300e.pth
```
Tips: measure the throughput on GPU
```
python speed_gpu.py --model repvit_m0_9
```
## ImageNet
### Prerequisites
`conda` virtual environment is recommended.
```
conda create -n repvit python=3.8
pip install -r requirements.txt
```
### Data preparation
Download and extract ImageNet train and val images from http://image-net.org/. The training and validation data are expected to be in the `train` folder and `val` folder respectively:
```
|-- /path/to/imagenet/
|-- train
|-- val
```
### Training
To train RepViT-M0.9 on an 8-GPU machine:
```
python -m torch.distributed.launch --nproc_per_node=8 --master_port 12346 --use_env main.py --model repvit_m0_9 --data-path ~/imagenet --dist-eval
```
Tips: specify your data path and model name!
### Testing
For example, to test RepViT-M0.9:
```
python main.py --eval --model repvit_m0_9 --resume pretrain/repvit_m0_9_distill_300e.pth --data-path ~/imagenet
```
## Downstream Tasks
[Object Detection and Instance Segmentation](detection/README.md)<br>
[Semantic Segmentation](segmentation/README.md)
## Acknowledgement
Classification (ImageNet) code base is partly built with [LeViT](https://github.com/facebookresearch/LeViT), [PoolFormer](https://github.com/sail-sg/poolformer) and [EfficientFormer](https://github.com/snap-research/EfficientFormer).
The detection and segmentation pipeline is from [MMCV](https://github.com/open-mmlab/mmcv) ([MMDetection](https://github.com/open-mmlab/mmdetection) and [MMSegmentation](https://github.com/open-mmlab/mmsegmentation)).
Thanks for the great implementations!
## Citation
If our code or models help your work, please cite our paper:
```BibTeX
@misc{wang2023repvit,
title={RepViT: Revisiting Mobile CNN From ViT Perspective},
author={Ao Wang and Hui Chen and Zijia Lin and Jungong Han and Guiguang Ding},
year={2023},
eprint={2307.09283},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
@misc{wang2023repvitsam,
title={RepViT-SAM: Towards Real-Time Segmenting Anything},
author={Ao Wang and Hui Chen and Zijia Lin and Jungong Han and Guiguang Ding},
year={2023},
eprint={2312.05760},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
data/datasets.py 0 → 100644
View file @ 3a6df602
'''
Build trainining/testing datasets
'''
import os
import json
from torchvision import datasets, transforms
from torchvision.datasets.folder import ImageFolder, default_loader
import torch
from timm.data.constants import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD
from timm.data import create_transform
try:
from timm.data import TimmDatasetTar
except ImportError:
# for higher version of timm
from timm.data import ImageDataset as TimmDatasetTar
class INatDataset(ImageFolder):
def __init__(self, root, train=True, year=2018, transform=None, target_transform=None,
category='name', loader=default_loader):
self.transform = transform
self.loader = loader
self.target_transform = target_transform
self.year = year
# assert category in ['kingdom','phylum','class','order','supercategory','family','genus','name']
path_json = os.path.join(
root, f'{"train" if train else "val"}{year}.json')
with open(path_json) as json_file:
data = json.load(json_file)
with open(os.path.join(root, 'categories.json')) as json_file:
data_catg = json.load(json_file)
path_json_for_targeter = os.path.join(root, f"train{year}.json")
with open(path_json_for_targeter) as json_file:
data_for_targeter = json.load(json_file)
targeter = {}
indexer = 0
for elem in data_for_targeter['annotations']:
king = []
king.append(data_catg[int(elem['category_id'])][category])
if king[0] not in targeter.keys():
targeter[king[0]] = indexer
indexer += 1
self.nb_classes = len(targeter)
self.samples = []
for elem in data['images']:
cut = elem['file_name'].split('/')
target_current = int(cut[2])
path_current = os.path.join(root, cut[0], cut[2], cut[3])
categors = data_catg[target_current]
target_current_true = targeter[categors[category]]
self.samples.append((path_current, target_current_true))
# __getitem__ and __len__ inherited from ImageFolder
def build_dataset(is_train, args):
transform = build_transform(is_train, args)
if args.data_set == 'CIFAR':
dataset = datasets.CIFAR100(
args.data_path, train=is_train, transform=transform)
nb_classes = 100
elif args.data_set == 'IMNET':
prefix = 'train' if is_train else 'val'
data_dir = os.path.join(args.data_path, f'{prefix}.tar')
if os.path.exists(data_dir):
dataset = TimmDatasetTar(data_dir, transform=transform)
else:
root = os.path.join(args.data_path, 'train' if is_train else 'val')
dataset = datasets.ImageFolder(root, transform=transform)
nb_classes = 1000
elif args.data_set == 'IMNETEE':
root = os.path.join(args.data_path, 'train' if is_train else 'val')
dataset = datasets.ImageFolder(root, transform=transform)
nb_classes = 10
elif args.data_set == 'FLOWERS':
root = os.path.join(args.data_path, 'train' if is_train else 'test')
dataset = datasets.ImageFolder(root, transform=transform)
if is_train:
dataset = torch.utils.data.ConcatDataset(
[dataset for _ in range(100)])
nb_classes = 102
elif args.data_set == 'INAT':
dataset = INatDataset(args.data_path, train=is_train, year=2018,
category=args.inat_category, transform=transform)
nb_classes = dataset.nb_classes
elif args.data_set == 'INAT19':
dataset = INatDataset(args.data_path, train=is_train, year=2019,
category=args.inat_category, transform=transform)
nb_classes = dataset.nb_classes
return dataset, nb_classes
def build_transform(is_train, args):
resize_im = args.input_size > 32
if is_train:
# this should always dispatch to transforms_imagenet_train
transform = create_transform(
input_size=args.input_size,
is_training=True,
color_jitter=args.color_jitter,
auto_augment=args.aa,
interpolation=args.train_interpolation,
re_prob=args.reprob,
re_mode=args.remode,
re_count=args.recount,
)
if not resize_im:
# replace RandomResizedCropAndInterpolation with
# RandomCrop
transform.transforms[0] = transforms.RandomCrop(
args.input_size, padding=4)
return transform
t = []
if args.finetune:
t.append(
transforms.Resize((args.input_size, args.input_size),
interpolation=3)
)
else:
if resize_im:
size = int((256 / 224) * args.input_size)
t.append(
# to maintain same ratio w.r.t. 224 images
transforms.Resize(size, interpolation=3),
)
t.append(transforms.CenterCrop(args.input_size))
t.append(transforms.ToTensor())
t.append(transforms.Normalize(IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD))
return transforms.Compose(t)
data/samplers.py 0 → 100644
View file @ 3a6df602
'''
Build samplers for data loading
'''
import torch
import torch.distributed as dist
import math
class RASampler(torch.utils.data.Sampler):
"""Sampler that restricts data loading to a subset of the dataset for distributed,
with repeated augmentation.
It ensures that different each augmented version of a sample will be visible to a
different process (GPU)
Heavily based on torch.utils.data.DistributedSampler
"""
def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True):
if num_replicas is None:
if not dist.is_available():
raise RuntimeError(
"Requires distributed package to be available")
num_replicas = dist.get_world_size()
if rank is None:
if not dist.is_available():
raise RuntimeError(
"Requires distributed package to be available")
rank = dist.get_rank()
self.dataset = dataset
self.num_replicas = num_replicas
self.rank = rank
self.epoch = 0
self.num_samples = int(
math.ceil(len(self.dataset) * 3.0 / self.num_replicas))
self.total_size = self.num_samples * self.num_replicas
# self.num_selected_samples = int(math.ceil(len(self.dataset) / self.num_replicas))
self.num_selected_samples = int(math.floor(
len(self.dataset) // 256 * 256 / self.num_replicas))
self.shuffle = shuffle
def __iter__(self):
# deterministically shuffle based on epoch
g = torch.Generator()
g.manual_seed(self.epoch)
if self.shuffle:
indices = torch.randperm(len(self.dataset), generator=g).tolist()
else:
indices = list(range(len(self.dataset)))
# add extra samples to make it evenly divisible
indices = [ele for ele in indices for i in range(3)]
indices += indices[:(self.total_size - len(indices))]
assert len(indices) == self.total_size
# subsample
indices = indices[self.rank:self.total_size:self.num_replicas]
assert len(indices) == self.num_samples
return iter(indices[:self.num_selected_samples])
def __len__(self):
return self.num_selected_samples
def set_epoch(self, epoch):
self.epoch = epoch
data/threeaugment.py 0 → 100644
View file @ 3a6df602
"""
3Augment implementation from (https://github.com/facebookresearch/deit/blob/main/augment.py)
Data-augmentation (DA) based on dino DA (https://github.com/facebookresearch/dino)
and timm DA(https://github.com/rwightman/pytorch-image-models)
Can be called by adding "--ThreeAugment" to the command line
"""
import torch
from torchvision import transforms
from timm.data.transforms import str_to_pil_interp, RandomResizedCropAndInterpolation, ToNumpy, ToTensor
import numpy as np
from torchvision import datasets, transforms
import random
from PIL import ImageFilter, ImageOps
import torchvision.transforms.functional as TF
class GaussianBlur(object):
"""
Apply Gaussian Blur to the PIL image.
"""
def __init__(self, p=0.1, radius_min=0.1, radius_max=2.):
self.prob = p
self.radius_min = radius_min
self.radius_max = radius_max
def __call__(self, img):
do_it = random.random() <= self.prob
if not do_it:
return img
img = img.filter(
ImageFilter.GaussianBlur(
radius=random.uniform(self.radius_min, self.radius_max)
)
)
return img
class Solarization(object):
"""
Apply Solarization to the PIL image.
"""
def __init__(self, p=0.2):
self.p = p
def __call__(self, img):
if random.random() < self.p:
return ImageOps.solarize(img)
else:
return img
class gray_scale(object):
"""
Apply Solarization to the PIL image.
"""
def __init__(self, p=0.2):
self.p = p
self.transf = transforms.Grayscale(3)
def __call__(self, img):
if random.random() < self.p:
return self.transf(img)
else:
return img
class horizontal_flip(object):
"""
Apply Solarization to the PIL image.
"""
def __init__(self, p=0.2,activate_pred=False):
self.p = p
self.transf = transforms.RandomHorizontalFlip(p=1.0)
def __call__(self, img):
if random.random() < self.p:
return self.transf(img)
else:
return img
def new_data_aug_generator(args = None):
img_size = args.input_size
remove_random_resized_crop = False
mean, std = [0.485, 0.456, 0.406], [0.229, 0.224, 0.225]
primary_tfl = []
scale=(0.08, 1.0)
interpolation='bicubic'
if remove_random_resized_crop:
primary_tfl = [
transforms.Resize(img_size, interpolation=3),
transforms.RandomCrop(img_size, padding=4,padding_mode='reflect'),
transforms.RandomHorizontalFlip()
]
else:
primary_tfl = [
RandomResizedCropAndInterpolation(
img_size, scale=scale, interpolation=interpolation),
transforms.RandomHorizontalFlip()
]
secondary_tfl = [transforms.RandomChoice([gray_scale(p=1.0),
Solarization(p=1.0),
GaussianBlur(p=1.0)])]
if args.color_jitter is not None and not args.color_jitter==0:
secondary_tfl.append(transforms.ColorJitter(args.color_jitter, args.color_jitter, args.color_jitter))
final_tfl = [
transforms.ToTensor(),
transforms.Normalize(
mean=torch.tensor(mean),
std=torch.tensor(std))
]
return transforms.Compose(primary_tfl+secondary_tfl+final_tfl)
detection/.gitignore 0 → 100644
View file @ 3a6df602
work_dirs
pretrain
data
det_pretrain
\ No newline at end of file
detection/README.md 0 → 100644
View file @ 3a6df602
# Object Detection and Instance Segmentation
Detection and instance segmentation on MS COCO 2017 is implemented based on [MMDetection](https://github.com/open-mmlab/mmdetection).
## Models
| Model | $AP^b$ | $AP_{50}^b$ | $AP_{75}^b$ | $AP^m$ | $AP_{50}^m$ | $AP_{75}^m$ | Latency | Ckpt | Log |
|:---------------|:----:|:---:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
| RepViT-M1.1 | 39.8 | 61.9 | 43.5 | 37.2 | 58.8 | 40.1 | 4.9ms | [M1.1](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m1_1_coco.pth) | [M1.1](./logs/repvit_m1_1_coco.json) |
| RepViT-M1.5 | 41.6 | 63.2 | 45.3 | 38.6 | 60.5 | 41.5 | 6.4ms | [M1.5](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m1_5_coco.pth) | [M1.5](./logs/repvit_m1_5_coco.json) |
| RepViT-M2.3 | 44.6 | 66.1 | 48.8 | 40.8 | 63.6 | 43.9 | 9.9ms | [M2.3](https://github.com/THU-MIG/RepViT/releases/download/v1.0/repvit_m2_3_coco.pth) | [M2.3](./logs/repvit_m2_3_coco.json) |
## Installation
Install [mmcv-full](https://github.com/open-mmlab/mmcv) and [MMDetection v2.28.2](https://github.com/open-mmlab/mmdetection/tree/v2.28.2),
Later versions should work as well.
The easiest way is to install via [MIM](https://github.com/open-mmlab/mim)
```
pip install -U openmim
mim install mmcv-full==1.7.1
mim install mmdet==2.28.2
```
## Data preparation
Prepare COCO 2017 dataset according to the [instructions in MMDetection](https://github.com/open-mmlab/mmdetection/blob/master/docs/en/1_exist_data_model.md#test-existing-models-on-standard-datasets).
The dataset should be organized as
```
detection
├── data
│ ├── coco
│ │ ├── annotations
│ │ ├── train2017
│ │ ├── val2017
│ │ ├── test2017
```
## Testing
We provide a multi-GPU testing script, specify config file, checkpoint, and number of GPUs to use:
```
./dist_test.sh config_file path/to/checkpoint #GPUs --eval bbox segm
```
For example, to test RepViT-M1.1 on COCO 2017 on an 8-GPU machine,
```
./dist_test.sh configs/mask_rcnn_repvit_m1_1_fpn_1x_coco.py path/to/repvit_m1_1_coco.pth 8 --eval bbox segm
```
## Training
Download ImageNet-1K pretrained weights into `./pretrain`
We provide PyTorch distributed data parallel (DDP) training script `dist_train.sh`, for example, to train RepViT-M1.1 on an 8-GPU machine:
```
./dist_train.sh configs/mask_rcnn_repvit_m1_1_fpn_1x_coco.py 8
```
Tips: specify configs and #GPUs!
detection/checkpoint.py 0 → 100644
View file @ 3a6df602
# Copyright (c) OpenMMLab. All rights reserved.
import io
import os
import os.path as osp
import pkgutil
import re
import time
import warnings
from collections import OrderedDict
from importlib import import_module
from tempfile import TemporaryDirectory
import torch
import torchvision
from torch.optim import Optimizer
from torch.utils import model_zoo
import mmcv
from mmcv.parallel import is_module_wrapper
from mmcv.runner.dist_utils import get_dist_info
ENV_MMCV_HOME = 'MMCV_HOME'
ENV_XDG_CACHE_HOME = 'XDG_CACHE_HOME'
DEFAULT_CACHE_DIR = '~/.cache'
def load_state_dict(module, state_dict, strict=False, logger=None):
"""Load state_dict to a module.
This method is modified from :meth:`torch.nn.Module.load_state_dict`.
Default value for ``strict`` is set to ``False`` and the message for
param mismatch will be shown even if strict is False.
Args:
module (Module): Module that receives the state_dict.
state_dict (OrderedDict): Weights.
strict (bool): whether to strictly enforce that the keys
in :attr:`state_dict` match the keys returned by this module's
:meth:`~torch.nn.Module.state_dict` function. Default: ``False``.
logger (:obj:`logging.Logger`, optional): Logger to log the error
message. If not specified, print function will be used.
"""
unexpected_keys = []
all_missing_keys = []
err_msg = []
metadata = getattr(state_dict, '_metadata', None)
state_dict = state_dict.copy()
if metadata is not None:
state_dict._metadata = metadata
# use _load_from_state_dict to enable checkpoint version control
def load(module, prefix=''):
# recursively check parallel module in case that the model has a
# complicated structure, e.g., nn.Module(nn.Module(DDP))
if is_module_wrapper(module):
module = module.module
local_metadata = {} if metadata is None else metadata.get(
prefix[:-1], {})
module._load_from_state_dict(state_dict, prefix, local_metadata, True,
all_missing_keys, unexpected_keys,
err_msg)
for name, child in module._modules.items():
if child is not None:
load(child, prefix + name + '.')
load(module)
load = None # break load->load reference cycle
# ignore "num_batches_tracked" of BN layers
missing_keys = [
key for key in all_missing_keys if 'num_batches_tracked' not in key
]
if unexpected_keys:
err_msg.append('unexpected key in source '
f'state_dict: {", ".join(unexpected_keys)}\n')
if missing_keys:
err_msg.append(
f'missing keys in source state_dict: {", ".join(missing_keys)}\n')
rank, _ = get_dist_info()
if len(err_msg) > 0 and rank == 0:
err_msg.insert(
0, 'The model and loaded state dict do not match exactly\n')
err_msg = '\n'.join(err_msg)
if strict:
raise RuntimeError(err_msg)
elif logger is not None:
logger.warning(err_msg)
else:
print(err_msg)
class CheckpointLoader:
"""A general checkpoint loader to manage all schemes."""
_schemes = {}
@classmethod
def _register_scheme(cls, prefixes, loader, force=False):
if isinstance(prefixes, str):
prefixes = [prefixes]
else:
assert isinstance(prefixes, (list, tuple))
for prefix in prefixes:
if (prefix not in cls._schemes) or force:
cls._schemes[prefix] = loader
else:
raise KeyError(
f'{prefix} is already registered as a loader backend, '
'add "force=True" if you want to override it')
# sort, longer prefixes take priority
cls._schemes = OrderedDict(
sorted(cls._schemes.items(), key=lambda t: t[0], reverse=True))
@classmethod
def register_scheme(cls, prefixes, loader=None, force=False):
"""Register a loader to CheckpointLoader.
This method can be used as a normal class method or a decorator.
Args:
prefixes (str or list[str] or tuple[str]):
The prefix of the registered loader.
loader (function, optional): The loader function to be registered.
When this method is used as a decorator, loader is None.
Defaults to None.
force (bool, optional): Whether to override the loader
if the prefix has already been registered. Defaults to False.
"""
if loader is not None:
cls._register_scheme(prefixes, loader, force=force)
return
def _register(loader_cls):
cls._register_scheme(prefixes, loader_cls, force=force)
return loader_cls
return _register
@classmethod
def _get_checkpoint_loader(cls, path):
"""Finds a loader that supports the given path. Falls back to the local
loader if no other loader is found.
Args:
path (str): checkpoint path
Returns:
loader (function): checkpoint loader
"""
for p in cls._schemes:
if path.startswith(p):
return cls._schemes[p]
@classmethod
def load_checkpoint(cls, filename, map_location=None, logger=None):
"""load checkpoint through URL scheme path.
Args:
filename (str): checkpoint file name with given prefix
map_location (str, optional): Same as :func:`torch.load`.
Default: None
logger (:mod:`logging.Logger`, optional): The logger for message.
Default: None
Returns:
dict or OrderedDict: The loaded checkpoint.
"""
checkpoint_loader = cls._get_checkpoint_loader(filename)
class_name = checkpoint_loader.__name__
mmcv.print_log(
f'load checkpoint from {class_name[10:]} path: {filename}', logger)
return checkpoint_loader(filename, map_location)
def _load_checkpoint(filename, map_location=None, logger=None):
"""Load checkpoint from somewhere (modelzoo, file, url).
Args:
filename (str): Accept local filepath, URL, ``torchvision://xxx``,
``open-mmlab://xxx``. Please refer to ``docs/model_zoo.md`` for
details.
map_location (str, optional): Same as :func:`torch.load`.
Default: None.
logger (:mod:`logging.Logger`, optional): The logger for error message.
Default: None
Returns:
dict or OrderedDict: The loaded checkpoint. It can be either an
OrderedDict storing model weights or a dict containing other
information, which depends on the checkpoint.
"""
return CheckpointLoader.load_checkpoint(filename, map_location, logger)
def load_checkpoint(model,
filename,
map_location=None,
strict=False,
logger=None,
revise_keys=[(r'^module\.', '')]):
"""Load checkpoint from a file or URI.
Args:
model (Module): Module to load checkpoint.
filename (str): Accept local filepath, URL, ``torchvision://xxx``,
``open-mmlab://xxx``. Please refer to ``docs/model_zoo.md`` for
details.
map_location (str): Same as :func:`torch.load`.
strict (bool): Whether to allow different params for the model and
checkpoint.
logger (:mod:`logging.Logger` or None): The logger for error message.
revise_keys (list): A list of customized keywords to modify the
state_dict in checkpoint. Each item is a (pattern, replacement)
pair of the regular expression operations. Default: strip
the prefix 'module.' by [(r'^module\\.', '')].
Returns:
dict or OrderedDict: The loaded checkpoint.
"""
checkpoint = _load_checkpoint(filename, map_location, logger)
# OrderedDict is a subclass of dict
if not isinstance(checkpoint, dict):
raise RuntimeError(
f'No state_dict found in checkpoint file {filename}')
# get state_dict from checkpoint
import pdb; pdb.set_trace()
if 'state_dict' in checkpoint:
state_dict = checkpoint['state_dict']
elif 'model' in checkpoint:
state_dict = checkpoint['model']
else:
state_dict = checkpoint
# strip prefix of state_dict
metadata = getattr(state_dict, '_metadata', OrderedDict())
for p, r in revise_keys:
state_dict = OrderedDict(
{re.sub(p, r, k): v
for k, v in state_dict.items()})
# Keep metadata in state_dict
state_dict._metadata = metadata
# load state_dict
load_state_dict(model, state_dict, strict, logger)
return checkpoint
detection/configs/_base_/datasets/cityscapes_detection.py 0 → 100644
View file @ 3a6df602
# 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)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='Resize', img_scale=[(2048, 800), (2048, 1024)], keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2048, 1024),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=1,
workers_per_gpu=2,
train=dict(
type='RepeatDataset',
times=8,
dataset=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_train.json',
img_prefix=data_root + 'leftImg8bit/train/',
pipeline=train_pipeline)),
val=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_val.json',
img_prefix=data_root + 'leftImg8bit/val/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_test.json',
img_prefix=data_root + 'leftImg8bit/test/',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric='bbox')
detection/configs/_base_/datasets/cityscapes_instance.py 0 → 100644
View file @ 3a6df602
# 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)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(
type='Resize', img_scale=[(2048, 800), (2048, 1024)], keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(2048, 1024),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=1,
workers_per_gpu=2,
train=dict(
type='RepeatDataset',
times=8,
dataset=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_train.json',
img_prefix=data_root + 'leftImg8bit/train/',
pipeline=train_pipeline)),
val=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_val.json',
img_prefix=data_root + 'leftImg8bit/val/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root +
'annotations/instancesonly_filtered_gtFine_test.json',
img_prefix=data_root + 'leftImg8bit/test/',
pipeline=test_pipeline))
evaluation = dict(metric=['bbox', 'segm'])
detection/configs/_base_/datasets/coco_detection.py 0 → 100644
View file @ 3a6df602
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
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,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric='bbox')
detection/configs/_base_/datasets/coco_instance.py 0 → 100644
View file @ 3a6df602
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
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,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
evaluation = dict(metric=['bbox', 'segm'])
detection/configs/_base_/datasets/coco_instance_semantic.py 0 → 100644
View file @ 3a6df602
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='LoadAnnotations', with_bbox=True, with_mask=True, with_seg=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='SegRescale', scale_factor=1 / 8),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_semantic_seg']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
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,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
seg_prefix=data_root + 'stuffthingmaps/train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
evaluation = dict(metric=['bbox', 'segm'])
detection/configs/_base_/datasets/deepfashion.py 0 → 100644
View file @ 3a6df602
# dataset settings
dataset_type = 'DeepFashionDataset'
data_root = 'data/DeepFashion/In-shop/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='Resize', img_scale=(750, 1101), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(750, 1101),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=1,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/DeepFashion_segmentation_query.json',
img_prefix=data_root + 'Img/',
pipeline=train_pipeline,
data_root=data_root),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/DeepFashion_segmentation_query.json',
img_prefix=data_root + 'Img/',
pipeline=test_pipeline,
data_root=data_root),
test=dict(
type=dataset_type,
ann_file=data_root +
'annotations/DeepFashion_segmentation_gallery.json',
img_prefix=data_root + 'Img/',
pipeline=test_pipeline,
data_root=data_root))
evaluation = dict(interval=5, metric=['bbox', 'segm'])
detection/configs/_base_/datasets/lvis_v0.5_instance.py 0 → 100644
View file @ 3a6df602
# dataset settings
_base_ = 'coco_instance.py'
dataset_type = 'LVISV05Dataset'
data_root = 'data/lvis_v0.5/'
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
_delete_=True,
type='ClassBalancedDataset',
oversample_thr=1e-3,
dataset=dict(
type=dataset_type,
ann_file=data_root + 'annotations/lvis_v0.5_train.json',
img_prefix=data_root + 'train2017/')),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/lvis_v0.5_val.json',
img_prefix=data_root + 'val2017/'),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/lvis_v0.5_val.json',
img_prefix=data_root + 'val2017/'))
evaluation = dict(metric=['bbox', 'segm'])
detection/configs/_base_/datasets/lvis_v1_instance.py 0 → 100644
View file @ 3a6df602
# dataset settings
_base_ = 'coco_instance.py'
dataset_type = 'LVISV1Dataset'
data_root = 'data/lvis_v1/'
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
_delete_=True,
type='ClassBalancedDataset',
oversample_thr=1e-3,
dataset=dict(
type=dataset_type,
ann_file=data_root + 'annotations/lvis_v1_train.json',
img_prefix=data_root)),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/lvis_v1_val.json',
img_prefix=data_root),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/lvis_v1_val.json',
img_prefix=data_root))
evaluation = dict(metric=['bbox', 'segm'])
detection/configs/_base_/datasets/voc0712.py 0 → 100644
View file @ 3a6df602
# dataset settings
dataset_type = 'VOCDataset'
data_root = 'data/VOCdevkit/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(1000, 600), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1000, 600),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type='RepeatDataset',
times=3,
dataset=dict(
type=dataset_type,
ann_file=[
data_root + 'VOC2007/ImageSets/Main/trainval.txt',
data_root + 'VOC2012/ImageSets/Main/trainval.txt'
],
img_prefix=[data_root + 'VOC2007/', data_root + 'VOC2012/'],
pipeline=train_pipeline)),
val=dict(
type=dataset_type,
ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
img_prefix=data_root + 'VOC2007/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
img_prefix=data_root + 'VOC2007/',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric='mAP')
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