donnyyou / torchcv
- среда, 16 октября 2019 г. в 00:28:34
Shell
A PyTorch-Based Framework for Deep Learning in Computer Vision
@misc{you2019torchcv,
author = {Ansheng You and Xiangtai Li and Zhen Zhu and Yunhai Tong},
title = {TorchCV: A PyTorch-Based Framework for Deep Learning in Computer Vision},
howpublished = {\url{https://github.com/donnyyou/torchcv}},
year = {2019}
}
This repository provides source code for most deep learning based cv problems. We'll do our best to keep this repository up-to-date. If you do find a problem about this repository, please raise an issue or submit a pull request.
Generative Adversarial Networks
Now only support Python3.x, pytorch 1.0.
pip3 install -r requirements.txt
cd extensions
sh make.sh
All the performances showed below fully reimplemented the papers' results.
Model | Train | Test | Top-1 | Top-5 | BS | Iters | Scripts |
---|---|---|---|---|---|---|---|
ResNet50 | train | val | 77.54 | 93.59 | 512 | 30W | ResNet50 |
ResNet101 | train | val | 78.94 | 94.56 | 512 | 30W | ResNet101 |
ShuffleNetV2x0.5 | train | val | 60.90 | 82.54 | 1024 | 40W | ShuffleNetV2x0.5 |
ShuffleNetV2x1.0 | train | val | 69.71 | 88.91 | 1024 | 40W | ShuffleNetV2x1.0 |
DFNetV1 | train | val | 70.99 | 89.68 | 1024 | 40W | DFNetV1 |
DFNetV2 | train | val | 74.22 | 91.61 | 1024 | 40W | DFNetV2 |
Model | Backbone | Train | Test | mIOU | BS | Iters | Scripts |
---|---|---|---|---|---|---|---|
PSPNet | 3x3-Res101 | train | val | 78.20 | 8 | 4W | PSPNet |
DeepLabV3 | 3x3-Res101 | train | val | 79.13 | 8 | 4W | DeepLabV3 |
Model | Backbone | Train | Test | mIOU | PixelACC | BS | Iters | Scripts |
---|---|---|---|---|---|---|---|---|
PSPNet | 3x3-Res50 | train | val | 41.52 | 80.09 | 16 | 15W | PSPNet |
DeepLabv3 | 3x3-Res50 | train | val | 42.16 | 80.36 | 16 | 15W | DeepLabV3 |
PSPNet | 3x3-Res101 | train | val | 43.60 | 81.30 | 16 | 15W | PSPNet |
DeepLabv3 | 3x3-Res101 | train | val | 44.13 | 81.42 | 16 | 15W | DeepLabV3 |
Model | Backbone | Train | Test | mAP | BS | Epochs | Scripts |
---|---|---|---|---|---|---|---|
SSD300 | VGG16 | 07+12_trainval | 07_test | 0.786 | 32 | 235 | SSD300 |
SSD512 | VGG16 | 07+12_trainval | 07_test | 0.808 | 32 | 235 | SSD512 |
Faster R-CNN | VGG16 | 07_trainval | 07_test | 0.706 | 1 | 15 | Faster R-CNN |
TorchCV has defined the dataset format of all the tasks which you could check in the subdirs of datasets. Following is an example dataset directory trees for training semantic segmentation. You could preprocess the open datasets with the scripts in folder datasets/seg/preprocess
DataSet
train
image
00001.jpg/png
00002.jpg/png
...
label
00001.png
00002.png
...
val
image
00001.jpg/png
00002.jpg/png
...
label
00001.png
00002.png
...
Take PSPNet as an example. ("tag" could be any string, include an empty one.)
cd scripts/seg/cityscapes/
bash run_fs_pspnet_cityscapes_seg.sh train tag
cd scripts/seg/cityscapes/
bash run_fs_pspnet_cityscapes_seg.sh train tag
cd scripts/seg/cityscapes/
bash run_fs_pspnet_cityscapes_seg.sh val tag
cd scripts/seg/cityscapes/
bash run_fs_pspnet_cityscapes_seg.sh test tag