зеркало из https://github.com/microsoft/FairMOT.git
This commit is contained in:
chunyuwang
Родитель
404da00f93
Коммит
5d44d6208f
157
README.md
157
README.md
|
|
@ -1,3 +1,160 @@
|
|||
# FairMOT
|
||||
A simple baseline for one-shot multi-object tracking:
|
||||
|
||||
> [**A Simple Baseline for Multi-Object Tracking**](http://arxiv.org/abs/2004.01888),
|
||||
> Yifu Zhang, Chunyu Wang, Xinggang Wang, Wenjun Zeng, Wenyu Liu,
|
||||
> *arXiv technical report ([arXiv 2004.01888](http://arxiv.org/abs/2004.01888))*
|
||||
## Abstract
|
||||
There has been remarkable progress on object detection and re-identification in recent years which are the core components for multi-object tracking. However, little attention has been focused on accomplishing the two tasks in a single network to improve the inference speed. The initial attempts along this path ended up with degraded results mainly because the re-identification branch is not appropriately learned. In this work, we study the essential reasons behind the failure, and accordingly present a simple baseline to addresses the problems. It remarkably outperforms the state-of-the-arts on the MOT challenge datasets at 30 FPS. We hope this baseline could inspire and help evaluate new ideas in this field.
|
||||
|
||||
## Tracking performance
|
||||
### Results on MOT challenge test set
|
||||
| Dataset | MOTA | IDF1 | IDS | MT | ML | FPS |
|
||||
|--------------|-----------|--------|-------|----------|----------|--------|
|
||||
|2DMOT15 | 59.0 | 62.2 | 582 | 45.6% | 11.5% | 30.5 |
|
||||
|MOT16 | 68.7 | 70.4 | 953 | 39.5% | 19.0% | 25.9 |
|
||||
|MOT17 | 67.5 | 69.8 | 2868 | 37.7% | 20.8% | 25.9 |
|
||||
|MOT20 | 58.7 | 63.7 | 6013 | 66.3% | 8.5% | 13.2 |
|
||||
|
||||
All of the results are obtained on the [MOT challenge](https://motchallenge.net) evaluation server under the “private detector” protocol. We rank first among all the trackers on 2DMOT15, MOT17 and the recently released (2020.02.29) MOT20. Note that our IDF1 score remarkably outperforms other one-shot MOT trackers by more than **10 points**. The tracking speed of the entire system can reach up to **30 FPS**.
|
||||
|
||||
### Video demos on MOT challenge test set
|
||||
<img src="assets/MOT15.gif" width="400"/> <img src="assets/MOT16.gif" width="400"/>
|
||||
<img src="assets/MOT17.gif" width="400"/> <img src="assets/MOT20.gif" width="400"/>
|
||||
|
||||
|
||||
## Installation
|
||||
* Clone this repo, and we'll call the directory that you cloned as ${FAIRMOT_ROOT}
|
||||
* Install dependencies. We use python 3.7 and pytorch >= 1.2.0
|
||||
```
|
||||
conda create -n FairMOT
|
||||
conda activate FairMOT
|
||||
conda install pytorch==1.2.0 torchvision==0.4.0 cudatoolkit=10.0 -c pytorch
|
||||
cd ${FAIRMOT_ROOT}
|
||||
pip install -r requirements.txt
|
||||
cd src/lib/models/networks/DCNv2 sh make.sh
|
||||
```
|
||||
* We use [DCNv2](https://github.com/CharlesShang/DCNv2) in our backbone network and more details can be found in their repo.
|
||||
* In order to run the code for demos, you also need to install [ffmpeg](https://www.ffmpeg.org/).
|
||||
|
||||
## Data preparation
|
||||
|
||||
We use the same training data as [JDE](https://github.com/Zhongdao/Towards-Realtime-MOT). Please refer to their [DATA ZOO](https://github.com/Zhongdao/Towards-Realtime-MOT/blob/master/DATASET_ZOO.md) to download and prepare all the training data including Caltech Pedestrian, CityPersons, CUHK-SYSU, PRW, ETHZ, MOT17 and MOT16.
|
||||
|
||||
[2DMOT15](https://motchallenge.net/data/2D_MOT_2015/) and [MOT20](https://motchallenge.net/data/MOT20/) can be downloaded from the official webpage of MOT challenge. After downloading, you should prepare the data in the following structure:
|
||||
```
|
||||
MOT15
|
||||
|——————images
|
||||
| └——————train
|
||||
| └——————test
|
||||
└——————labels_with_ids
|
||||
└——————train(empty)
|
||||
MOT20
|
||||
|——————images
|
||||
| └——————train
|
||||
| └——————test
|
||||
└——————labels_with_ids
|
||||
└——————train(empty)
|
||||
```
|
||||
Then, you can change the seq_root and label_root in src/gen_labels_15.py and src/gen_labels_20.py and run:
|
||||
```
|
||||
cd src
|
||||
python gen_labels_15.py
|
||||
python gen_labels_20.py
|
||||
```
|
||||
to generate the labels of 2DMOT15 and MOT20. The seqinfo.ini files of 2DMOT15 can be downloaded here [[Google]](https://drive.google.com/open?id=1kJYySZy7wyETH4fKMzgJrYUrTfxKlN1w), [[Baidu],code:8o0w](https://pan.baidu.com/s/1zb5tBW7-YTzWOXpd9IzS0g).
|
||||
|
||||
## Pretrained models and baseline model
|
||||
* **Pretrained models**
|
||||
|
||||
DLA-34 COCO pretrained model: [DLA-34 official](https://drive.google.com/file/d/1pl_-ael8wERdUREEnaIfqOV_VF2bEVRT/view).
|
||||
HRNetV2 ImageNet pretrained model: [HRNetV2-W18 official](https://1drv.ms/u/s!Aus8VCZ_C_33cMkPimlmClRvmpw), [HRNetV2-W32 official](https://1drv.ms/u/s!Aus8VCZ_C_33dYBMemi9xOUFR0w).
|
||||
After downloading, you should put the pretrained models in the following structure:
|
||||
```
|
||||
${FAIRMOT_ROOT}
|
||||
└——————models
|
||||
└——————ctdet_coco_dla_2x.pth
|
||||
└——————hrnetv2_w32_imagenet_pretrained.pth
|
||||
└——————hrnetv2_w18_imagenet_pretrained.pth
|
||||
```
|
||||
* **Baseline model**
|
||||
|
||||
Our baseline FairMOT model can be downloaded here: DLA-34: [[Google]](https://drive.google.com/open?id=1udpOPum8fJdoEQm6n0jsIgMMViOMFinu) [[Baidu, code: 88yn]](https://pan.baidu.com/s/1YQGulGblw_hrfvwiO6MIvA). HRNetV2_W18: [[Google]](https://drive.google.com/open?id=1hxqE5QuzGCa6sgyBvNYhywmyohmioVAO) [[Baidu, code: 7jb1]](https://pan.baidu.com/s/1yQxXh0FuPLoFfeupHGZlCw).
|
||||
After downloading, you should put the baseline model in the following structure:
|
||||
```
|
||||
${FAIRMOT_ROOT}
|
||||
└——————models
|
||||
└——————all_dla34.pth
|
||||
└——————all_hrnet_v2_w18.pth
|
||||
└——————...
|
||||
```
|
||||
|
||||
## Training
|
||||
* Download the training data
|
||||
* Change the dataset root directory 'root' in src/lib/cfg/data.json and 'data_dir' in src/lib/opts.py
|
||||
* Run:
|
||||
```
|
||||
sh experiments/all_dla34.sh
|
||||
```
|
||||
|
||||
## Tracking
|
||||
* The default settings run tracking on the validation dataset from 2DMOT15. You can run:
|
||||
```
|
||||
cd src
|
||||
python track.py mot --load_model ../models/all_dla34.pth --conf_thres 0.6
|
||||
```
|
||||
to see the tracking results. You can also set save_images=True in src/track.py to save the visualization results of each frame.
|
||||
|
||||
* To get the txt results of the test set of MOT16 or MOT17, you can run:
|
||||
```
|
||||
cd src
|
||||
python track.py mot --test_mot17 True --load_model ../models/all_dla34.pth --conf_thres 0.4
|
||||
python track.py mot --test_mot16 True --load_model ../models/all_dla34.pth --conf_thres 0.4
|
||||
```
|
||||
and send the txt files to the [MOT challenge](https://motchallenge.net) evaluation server to get the results.
|
||||
|
||||
* To get the SOTA results of 2DMOT15 and MOT20, you need to finetune the baseline model on the specific dataset because our training set do not contain them. You can run:
|
||||
```
|
||||
sh experiments/ft_mot15_dla34.sh
|
||||
sh experiments/ft_mot20_dla34.sh
|
||||
```
|
||||
and then run the tracking code:
|
||||
```
|
||||
cd src
|
||||
python track.py mot --test_mot15 True --load_model your_mot15_model.pth --conf_thres 0.3
|
||||
python track.py mot --test_mot20 True --load_model your_mot20_model.pth --conf_thres 0.3
|
||||
```
|
||||
Results of the test set all need to be evaluated on the MOT challenge server. You can see the tracking results on the training set by setting --val_motxx True and run the tracking code. We set 'conf_thres' 0.4 for MOT16 and MOT17. We set 'conf_thres' 0.3 for 2DMOT15 and MOT20.
|
||||
|
||||
## Demo
|
||||
You can input a raw video and get the demo video by running src/demo.py and get the mp4 format of the demo video:
|
||||
```
|
||||
cd src
|
||||
python demo.py mot --load_model ../models/all_dla34.pth --conf_thres 0.4
|
||||
```
|
||||
You can change --input-video and --output-root to get the demos of your own videos.
|
||||
|
||||
If you have difficulty building DCNv2 and thus cannot use the DLA-34 baseline model, you can run the demo with the HRNetV2_w18 baseline model:
|
||||
```
|
||||
cd src
|
||||
python demo.py mot --load_model ../models/all_hrnet_v2_w18.pth --arch hrnet_18 --reid_dim 128 --conf_thres 0.4
|
||||
```
|
||||
--conf_thres can be set from 0.3 to 0.7 depending on your own videos.
|
||||
|
||||
## Acknowledgement
|
||||
A large part of the code is borrowed from [Zhongdao/Towards-Realtime-MOT](https://github.com/Zhongdao/Towards-Realtime-MOT) and [xingyizhou/CenterNet](https://github.com/xingyizhou/CenterNet). Thanks for their wonderful works.
|
||||
|
||||
## Citation
|
||||
|
||||
```
|
||||
@article{zhang2020simple,
|
||||
title={A Simple Baseline for Multi-Object Tracking},
|
||||
author={Zhang, Yifu and Wang, Chunyu and Wang, Xinggang and Zeng, Wenjun and Liu, Wenyu},
|
||||
journal={arXiv preprint arXiv:2004.01888},
|
||||
year={2020}
|
||||
}
|
||||
```
|
||||
|
||||
|
||||
# Contributing
|
||||
|
||||
|
|
|
|||
Двоичный файл не отображается.
|
После Ширина: | Высота: | Размер: 3.1 MiB |
Двоичный файл не отображается.
|
После Ширина: | Высота: | Размер: 5.1 MiB |
Двоичный файл не отображается.
|
После Ширина: | Высота: | Размер: 4.3 MiB |
Двоичный файл не отображается.
|
После Ширина: | Высота: | Размер: 5.5 MiB |
Двоичный файл не отображается.
|
После Ширина: | Высота: | Размер: 270 KiB |
|
|
@ -0,0 +1,3 @@
|
|||
cd src
|
||||
python train.py mot --exp_id all_dla34 --gpus 0,1 --batch_size 8 --load_model '../models/ctdet_coco_dla_2x.pth'
|
||||
cd ..
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
cd src
|
||||
python train.py mot --exp_id all_hrnet --gpus 0,1 --batch_size 8 --reid_dim 128 --arch 'hrnet_32'
|
||||
cd ..
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
cd src
|
||||
python train.py mot --exp_id all_res50 --gpus 0,1 --batch_size 8 --reid_dim 128 --arch 'resdcn_50'
|
||||
cd ..
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
cd src
|
||||
python train.py mot --exp_id ft_mot15_dla34 --gpus 0,1 --batch_size 8 --load_model '../models/all_dla34.pth' --data_cfg '../src/lib/cfg/mot15.json' --num_epochs 10 --lr 1e-5
|
||||
cd ..
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
cd src
|
||||
python train.py mot --exp_id ft_mot20_dla34 --gpus 0,1 --batch_size 8 --load_model '../models/all_dla34.pth' --data_cfg '../src/lib/cfg/mot20.json' --num_epochs 20 --lr_step '15' --K 500
|
||||
cd ..
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
yacs
|
||||
opencv-python
|
||||
cython-bbox
|
||||
scipy
|
||||
numba
|
||||
progress
|
||||
motmetrics
|
||||
numba
|
||||
matplotlib
|
||||
lap
|
||||
openpyxl
|
||||
Pillow==6.2.2
|
||||
tensorboardX
|
||||
|
|
@ -0,0 +1,17 @@
|
|||
# ------------------------------------------------------------------------------
|
||||
# Copyright (c) Microsoft Corporation
|
||||
# Licensed under MIT License
|
||||
# ------------------------------------------------------------------------------
|
||||
|
||||
import os.path as osp
|
||||
import sys
|
||||
|
||||
def add_path(path):
|
||||
if path not in sys.path:
|
||||
sys.path.insert(0, path)
|
||||
|
||||
this_dir = osp.dirname(__file__)
|
||||
|
||||
# Add lib to PYTHONPATH
|
||||
lib_path = osp.join(this_dir, 'lib')
|
||||
add_path(lib_path)
|
||||
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
|
|
@ -0,0 +1,441 @@
|
|||
Cityscapes/images/val/frankfurt/frankfurt_000001_066574_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_067474_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_077092_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_028590_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_028335_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_050149_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_043395_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_059119_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_005543_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_010156_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_064130_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_001016_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_003025_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_071288_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_055062_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_012868_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_048196_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_044658_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_080391_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_080091_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_007365_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_013710_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_013942_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_007973_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_020693_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_016286_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_073088_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_066438_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_030067_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_067178_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_014480_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_073464_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_011810_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_005898_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_019854_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_055709_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_002512_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_007622_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_054077_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_060545_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_063045_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_032556_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_064305_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_049698_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_007857_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_012519_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_034816_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_032018_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_019969_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_025713_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_065617_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_017228_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_062016_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_009504_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_010763_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_030669_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_002646_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_001464_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_062396_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_008206_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_004327_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_075984_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_052120_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_020046_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_046504_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_078803_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_011835_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_038418_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_012699_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_031266_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_022254_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_068208_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_007285_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_039895_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_073243_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_038245_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_046779_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_025921_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_016005_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_044787_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_054415_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_033655_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_049209_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_061763_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_022797_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_028232_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_083852_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_058057_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_020287_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_012738_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_043564_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_005898_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_049770_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_065850_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_044525_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_009854_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_077434_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_062250_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_038645_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_057181_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_062509_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_020215_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_020321_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_016029_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_068063_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_017476_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_011162_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_011461_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_013240_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_079206_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_018113_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_066092_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_051807_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_058176_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_015676_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_018797_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_012870_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_064925_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_023235_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_010600_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_077233_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_067735_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_014221_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_021879_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_041664_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_003588_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_009561_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_062793_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_014565_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_083029_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_013067_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_009688_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_055387_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_023769_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_013016_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_083199_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_034047_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_049298_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_035144_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_008688_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_015328_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_024927_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_032942_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_027325_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_014741_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_009969_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_067295_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_012121_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_004859_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_015389_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_068682_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_021406_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_050686_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_000538_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_082087_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_057954_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_054219_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_003920_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_040732_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_038844_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_042733_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_037705_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_069633_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_005703_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_025512_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_002759_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_015091_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_080830_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_019607_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_009058_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_015768_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_042384_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_012009_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_068772_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_072155_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_058504_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_016273_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_060906_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_066832_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_009291_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_059642_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_064798_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_060422_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_001236_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_055172_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_005410_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_075296_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_005184_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_044413_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_002196_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_064651_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_014406_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_048355_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_051516_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_040575_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_017842_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_041074_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_057478_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_055306_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_062653_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_007407_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_048654_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_019698_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_049078_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_061682_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_055603_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_023369_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_067092_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_054884_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_058914_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_070099_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_000294_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_056580_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_032711_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_013382_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_010830_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_000576_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_020880_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_030310_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_011715_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_008200_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_052594_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_042098_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_011007_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_012038_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_001751_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_046126_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_053102_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_013496_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_046272_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_073911_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_021667_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_065160_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_059789_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_017101_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_044227_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_029600_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_008451_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_076502_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_029086_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_051737_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_031416_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_029236_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_004736_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_047178_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_010444_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_016462_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_028854_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_055538_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_021825_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000000_011074_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_071781_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_017459_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_054640_leftImg8bit.png
|
||||
Cityscapes/images/val/frankfurt/frankfurt_000001_035864_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000129_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000011_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000044_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000165_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000078_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000014_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000086_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000067_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000097_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000077_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000138_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000058_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000030_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000083_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000085_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000036_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000026_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000068_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000064_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000024_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000135_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000120_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000041_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000169_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000144_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000049_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000062_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000048_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000154_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000053_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000022_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000076_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000040_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000032_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000163_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000149_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000094_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000146_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000084_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000000_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000092_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000109_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000019_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000020_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000089_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000153_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000152_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000066_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000131_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000035_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000151_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000052_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000105_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000001_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000108_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000159_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000073_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000055_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000106_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000136_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000050_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000140_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000147_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000096_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000166_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000070_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000133_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000171_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000056_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000134_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000162_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000143_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000150_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000002_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000160_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000009_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000003_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000054_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000170_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000095_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000141_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000006_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000126_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000099_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000071_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000148_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000128_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000114_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000018_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000130_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000113_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000063_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000157_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000060_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000116_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000028_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000075_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000158_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000155_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000102_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000172_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000122_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000142_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000029_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000046_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000090_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000013_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000124_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000061_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000023_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000139_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000015_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000033_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000074_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000145_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000031_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000168_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000161_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000069_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000025_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000167_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000072_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000125_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000007_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000042_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000104_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000115_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000098_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000047_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000080_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000137_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000119_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000088_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000004_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000016_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000012_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000156_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000039_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000101_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000111_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000010_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000059_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000110_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000005_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000121_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000057_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000079_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000123_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000112_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000091_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000127_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000093_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000038_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000045_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000017_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000043_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000021_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000051_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000103_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/munster/munster_000027_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000012_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000025_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000052_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000011_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000055_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000014_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000037_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000047_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000057_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000051_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000042_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000041_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000020_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000024_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000035_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000010_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000046_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000022_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000053_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000009_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000013_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000007_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000038_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000054_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000005_000019_leftImg8bit.png
|
||||
Cityscapes/images/val/lindau/lindau_000023_000019_leftImg8bit.png
|
||||
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
|
|
@ -0,0 +1,49 @@
|
|||
# ------------------------------------------------------------------------------
|
||||
# Copyright (c) Microsoft Corporation
|
||||
# Licensed under MIT License
|
||||
# ------------------------------------------------------------------------------
|
||||
|
||||
from __future__ import absolute_import
|
||||
from __future__ import division
|
||||
from __future__ import print_function
|
||||
|
||||
import _init_paths
|
||||
|
||||
import logging
|
||||
import os
|
||||
import os.path as osp
|
||||
from opts import opts
|
||||
from tracking_utils.utils import mkdir_if_missing
|
||||
from tracking_utils.log import logger
|
||||
import datasets.dataset.jde as datasets
|
||||
from track import eval_seq
|
||||
|
||||
|
||||
logger.setLevel(logging.INFO)
|
||||
|
||||
|
||||
def demo(opt):
|
||||
result_root = opt.output_root if opt.output_root != '' else '.'
|
||||
mkdir_if_missing(result_root)
|
||||
|
||||
logger.info('Starting tracking...')
|
||||
dataloader = datasets.LoadVideo(opt.input_video, opt.img_size)
|
||||
result_filename = os.path.join(result_root, 'results.txt')
|
||||
frame_rate = dataloader.frame_rate
|
||||
|
||||
frame_dir = None if opt.output_format == 'text' else osp.join(result_root, 'frame')
|
||||
try:
|
||||
eval_seq(opt, dataloader, 'mot', result_filename,
|
||||
save_dir=frame_dir, show_image=False, frame_rate=frame_rate)
|
||||
except Exception as e:
|
||||
logger.info(e)
|
||||
|
||||
if opt.output_format == 'video':
|
||||
output_video_path = osp.join(result_root, 'result.mp4')
|
||||
cmd_str = 'ffmpeg -f image2 -i {}/%05d.jpg -b 5000k -c:v mpeg4 {}'.format(osp.join(result_root, 'frame'), output_video_path)
|
||||
os.system(cmd_str)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
opt = opts().init()
|
||||
demo(opt)
|
||||
|
|
@ -0,0 +1,27 @@
|
|||
# ------------------------------------------------------------------------------
|
||||
# Copyright (c) Microsoft Corporation
|
||||
# Licensed under MIT License
|
||||
# ------------------------------------------------------------------------------
|
||||
|
||||
import os
|
||||
import glob
|
||||
import _init_paths
|
||||
|
||||
|
||||
def gen_caltech_path(root_path):
|
||||
label_path = 'Caltech/data/labels_with_ids'
|
||||
real_path = os.path.join(root_path, label_path)
|
||||
image_path = real_path.replace('labels_with_ids', 'images')
|
||||
images_exist = sorted(glob.glob(image_path + '/*.png'))
|
||||
with open('../src/data/caltech.all', 'w') as f:
|
||||
labels = sorted(glob.glob(real_path + '/*.txt'))
|
||||
for label in labels:
|
||||
image = label.replace('labels_with_ids', 'images').replace('.txt', '.png')
|
||||
if image in images_exist:
|
||||
print(image[22:], file=f)
|
||||
f.close()
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
root = '/data/yfzhang/MOT/JDE'
|
||||
gen_caltech_path(root)
|
||||
|
|
@ -0,0 +1,52 @@
|
|||
# ------------------------------------------------------------------------------
|
||||
# Copyright (c) Microsoft Corporation
|
||||
# Licensed under MIT License
|
||||
# ------------------------------------------------------------------------------
|
||||
|
||||
import os.path as osp
|
||||
import os
|
||||
import numpy as np
|
||||
|
||||
|
||||
def mkdirs(d):
|
||||
if not osp.exists(d):
|
||||
os.makedirs(d)
|
||||
|
||||
|
||||
seq_root = '/data/yfzhang/MOT/JDE/MOT15/images/train'
|
||||
label_root = '/data/yfzhang/MOT/JDE/MOT15/labels_with_ids/train'
|
||||
mkdirs(label_root)
|
||||
#seqs = [s for s in os.listdir(seq_root)]
|
||||
seqs = ['ADL-Rundle-6', 'ETH-Bahnhof', 'KITTI-13', 'PETS09-S2L1', 'TUD-Stadtmitte', 'ADL-Rundle-8', 'KITTI-17',
|
||||
'ETH-Pedcross2', 'ETH-Sunnyday', 'TUD-Campus', 'Venice-2']
|
||||
|
||||
tid_curr = 0
|
||||
tid_last = -1
|
||||
for seq in seqs:
|
||||
seq_info = open(osp.join(seq_root, seq, 'seqinfo.ini')).read()
|
||||
seq_width = int(seq_info[seq_info.find('imWidth=') + 8:seq_info.find('\nimHeight')])
|
||||
seq_height = int(seq_info[seq_info.find('imHeight=') + 9:seq_info.find('\nimExt')])
|
||||
|
||||
gt_txt = osp.join(seq_root, seq, 'gt', 'gt.txt')
|
||||
gt = np.loadtxt(gt_txt, dtype=np.float64, delimiter=',')
|
||||
idx = np.lexsort(gt.T[:2, :])
|
||||
gt = gt[idx, :]
|
||||
|
||||
seq_label_root = osp.join(label_root, seq, 'img1')
|
||||
mkdirs(seq_label_root)
|
||||
|
||||
for fid, tid, x, y, w, h, mark, _, _, _ in gt:
|
||||
if mark == 0:
|
||||
continue
|
||||
fid = int(fid)
|
||||
tid = int(tid)
|
||||
if not tid == tid_last:
|
||||
tid_curr += 1
|
||||
tid_last = tid
|
||||
x += w / 2
|
||||
y += h / 2
|
||||
label_fpath = osp.join(seq_label_root, '{:06d}.txt'.format(fid))
|
||||
label_str = '0 {:d} {:.6f} {:.6f} {:.6f} {:.6f}\n'.format(
|
||||
tid_curr, x / seq_width, y / seq_height, w / seq_width, h / seq_height)
|
||||
with open(label_fpath, 'a') as f:
|
||||
f.write(label_str)
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# ------------------------------------------------------------------------------
|
||||
# Copyright (c) Microsoft Corporation
|
||||
# Licensed under MIT License
|
||||
# ------------------------------------------------------------------------------
|
||||
|
||||
import os.path as osp
|
||||
import os
|
||||
import numpy as np
|
||||
|
||||
|
||||
def mkdirs(d):
|
||||
if not osp.exists(d):
|
||||
os.makedirs(d)
|
||||
|
||||
|
||||
seq_root = '/data/yfzhang/MOT/JDE/MOT20/images/train'
|
||||
label_root = '/data/yfzhang/MOT/JDE/MOT20/labels_with_ids/train'
|
||||
mkdirs(label_root)
|
||||
seqs = [s for s in os.listdir(seq_root)]
|
||||
|
||||
tid_curr = 0
|
||||
tid_last = -1
|
||||
for seq in seqs:
|
||||
seq_info = open(osp.join(seq_root, seq, 'seqinfo.ini')).read()
|
||||
seq_width = int(seq_info[seq_info.find('imWidth=') + 8:seq_info.find('\nimHeight')])
|
||||
seq_height = int(seq_info[seq_info.find('imHeight=') + 9:seq_info.find('\nimExt')])
|
||||
|
||||
gt_txt = osp.join(seq_root, seq, 'gt', 'gt.txt')
|
||||
gt = np.loadtxt(gt_txt, dtype=np.float64, delimiter=',')
|
||||
|
||||
seq_label_root = osp.join(label_root, seq, 'img1')
|
||||
mkdirs(seq_label_root)
|
||||
|
||||
for fid, tid, x, y, w, h, mark, label, _ in gt:
|
||||
if mark == 0 or not label == 1:
|
||||
continue
|
||||
fid = int(fid)
|
||||
tid = int(tid)
|
||||
if not tid == tid_last:
|
||||
tid_curr += 1
|
||||
tid_last = tid
|
||||
x += w / 2
|
||||
y += h / 2
|
||||
label_fpath = osp.join(seq_label_root, '{:06d}.txt'.format(fid))
|
||||
label_str = '0 {:d} {:.6f} {:.6f} {:.6f} {:.6f}\n'.format(
|
||||
tid_curr, x / seq_width, y / seq_height, w / seq_width, h / seq_height)
|
||||
with open(label_fpath, 'a') as f:
|
||||
f.write(label_str)
|
||||
|
|
@ -0,0 +1,220 @@
|
|||
# ------------------------------------------------------------------------------
|
||||
# Copyright (c) Microsoft Corporation
|
||||
# Licensed under MIT License
|
||||
# ------------------------------------------------------------------------------
|
||||
|
||||
from __future__ import absolute_import
|
||||
from __future__ import division
|
||||
from __future__ import print_function
|
||||
|
||||
import _init_paths
|
||||
import argparse
|
||||
import torch
|
||||
import json
|
||||
import time
|
||||
import os
|
||||
import cv2
|
||||
|
||||
from sklearn import metrics
|
||||
from scipy import interpolate
|
||||
import numpy as np
|
||||
from torchvision.transforms import transforms as T
|
||||
from models.model import create_model, load_model
|
||||
from datasets.dataset.jde import DetDataset, collate_fn
|
||||
from utils.utils import xywh2xyxy, ap_per_class, bbox_iou
|
||||
from opts import opts
|
||||
from models.decode import mot_decode
|
||||
from utils.post_process import ctdet_post_process
|
||||
|
||||
|
||||
def post_process(opt, dets, meta):
|
||||
dets = dets.detach().cpu().numpy()
|
||||
dets = dets.reshape(1, -1, dets.shape[2])
|
||||
dets = ctdet_post_process(
|
||||
dets.copy(), [meta['c']], [meta['s']],
|
||||
meta['out_height'], meta['out_width'], opt.num_classes)
|
||||
for j in range(1, opt.num_classes + 1):
|
||||
dets[0][j] = np.array(dets[0][j], dtype=np.float32).reshape(-1, 5)
|
||||
return dets[0]
|
||||
|
||||
|
||||
def merge_outputs(opt, detections):
|
||||
results = {}
|
||||
for j in range(1, opt.num_classes + 1):
|
||||
results[j] = np.concatenate(
|
||||
[detection[j] for detection in detections], axis=0).astype(np.float32)
|
||||
|
||||
scores = np.hstack(
|
||||
[results[j][:, 4] for j in range(1, opt.num_classes + 1)])
|
||||
if len(scores) > 128:
|
||||
kth = len(scores) - 128
|
||||
thresh = np.partition(scores, kth)[kth]
|
||||
for j in range(1, opt.num_classes + 1):
|
||||
keep_inds = (results[j][:, 4] >= thresh)
|
||||
results[j] = results[j][keep_inds]
|
||||
return results
|
||||
|
||||
|
||||
def test_det(
|
||||
opt,
|
||||
batch_size=12,
|
||||
img_size=(1088, 608),
|
||||
iou_thres=0.5,
|
||||
print_interval=40,
|
||||
):
|
||||
data_cfg = opt.data_cfg
|
||||
f = open(data_cfg)
|
||||
data_cfg_dict = json.load(f)
|
||||
f.close()
|
||||
nC = 1
|
||||
test_path = data_cfg_dict['test']
|
||||
dataset_root = data_cfg_dict['root']
|
||||
if opt.gpus[0] >= 0:
|
||||
opt.device = torch.device('cuda')
|
||||
else:
|
||||
opt.device = torch.device('cpu')
|
||||
print('Creating model...')
|
||||
model = create_model(opt.arch, opt.heads, opt.head_conv)
|
||||
model = load_model(model, opt.load_model)
|
||||
#model = torch.nn.DataParallel(model)
|
||||
model = model.to(opt.device)
|
||||
model.eval()
|
||||
|
||||
# Get dataloader
|
||||
transforms = T.Compose([T.ToTensor()])
|
||||
dataset = DetDataset(dataset_root, test_path, img_size, augment=False, transforms=transforms)
|
||||
dataloader = torch.utils.data.DataLoader(dataset, batch_size=batch_size, shuffle=False,
|
||||
num_workers=8, drop_last=False, collate_fn=collate_fn)
|
||||
mean_mAP, mean_R, mean_P, seen = 0.0, 0.0, 0.0, 0
|
||||
print('%11s' * 5 % ('Image', 'Total', 'P', 'R', 'mAP'))
|
||||
outputs, mAPs, mR, mP, TP, confidence, pred_class, target_class, jdict = \
|
||||
[], [], [], [], [], [], [], [], []
|
||||
AP_accum, AP_accum_count = np.zeros(nC), np.zeros(nC)
|
||||
for batch_i, (imgs, targets, paths, shapes, targets_len) in enumerate(dataloader):
|
||||
t = time.time()
|
||||
#seen += batch_size
|
||||
|
||||
output = model(imgs.cuda())[-1]
|
||||
origin_shape = shapes[0]
|
||||
width = origin_shape[1]
|
||||
height = origin_shape[0]
|
||||
inp_height = img_size[1]
|
||||
inp_width = img_size[0]
|
||||
c = np.array([width / 2., height / 2.], dtype=np.float32)
|
||||
s = max(float(inp_width) / float(inp_height) * height, width) * 1.0
|
||||
meta = {'c': c, 's': s,
|
||||
'out_height': inp_height // opt.down_ratio,
|
||||
'out_width': inp_width // opt.down_ratio}
|
||||
hm = output['hm'].sigmoid_()
|
||||
wh = output['wh']
|
||||
reg = output['reg'] if opt.reg_offset else None
|
||||
opt.K = 200
|
||||
detections, inds = mot_decode(hm, wh, reg=reg, cat_spec_wh=opt.cat_spec_wh, K=opt.K)
|
||||
# Compute average precision for each sample
|
||||
targets = [targets[i][:int(l)] for i, l in enumerate(targets_len)]
|
||||
for si, labels in enumerate(targets):
|
||||
seen += 1
|
||||
#path = paths[si]
|
||||
#img0 = cv2.imread(path)
|
||||
dets = detections[si]
|
||||
dets = dets.unsqueeze(0)
|
||||
dets = post_process(opt, dets, meta)
|
||||
dets = merge_outputs(opt, [dets])[1]
|
||||
|
||||
#remain_inds = dets[:, 4] > opt.det_thres
|
||||
#dets = dets[remain_inds]
|
||||
if dets is None:
|
||||
# If there are labels but no detections mark as zero AP
|
||||
if labels.size(0) != 0:
|
||||
mAPs.append(0), mR.append(0), mP.append(0)
|
||||
continue
|
||||
|
||||
# If no labels add number of detections as incorrect
|
||||
correct = []
|
||||
if labels.size(0) == 0:
|
||||
# correct.extend([0 for _ in range(len(detections))])
|
||||
mAPs.append(0), mR.append(0), mP.append(0)
|
||||
continue
|
||||
else:
|
||||
target_cls = labels[:, 0]
|
||||
|
||||
# Extract target boxes as (x1, y1, x2, y2)
|
||||
target_boxes = xywh2xyxy(labels[:, 2:6])
|
||||
target_boxes[:, 0] *= width
|
||||
target_boxes[:, 2] *= width
|
||||
target_boxes[:, 1] *= height
|
||||
target_boxes[:, 3] *= height
|
||||
|
||||
'''
|
||||
path = paths[si]
|
||||
img0 = cv2.imread(path)
|
||||
img1 = cv2.imread(path)
|
||||
for t in range(len(target_boxes)):
|
||||
x1 = target_boxes[t, 0]
|
||||
y1 = target_boxes[t, 1]
|
||||
x2 = target_boxes[t, 2]
|
||||
y2 = target_boxes[t, 3]
|
||||
cv2.rectangle(img0, (x1, y1), (x2, y2), (0, 255, 0), 4)
|
||||
cv2.imwrite('gt.jpg', img0)
|
||||
for t in range(len(dets)):
|
||||
x1 = dets[t, 0]
|
||||
y1 = dets[t, 1]
|
||||
x2 = dets[t, 2]
|
||||
y2 = dets[t, 3]
|
||||
cv2.rectangle(img1, (x1, y1), (x2, y2), (0, 255, 0), 4)
|
||||
cv2.imwrite('pred.jpg', img1)
|
||||
abc = ace
|
||||
'''
|
||||
|
||||
detected = []
|
||||
for *pred_bbox, conf in dets:
|
||||
obj_pred = 0
|
||||
pred_bbox = torch.FloatTensor(pred_bbox).view(1, -1)
|
||||
# Compute iou with target boxes
|
||||
iou = bbox_iou(pred_bbox, target_boxes, x1y1x2y2=True)[0]
|
||||
# Extract index of largest overlap
|
||||
best_i = np.argmax(iou)
|
||||
# If overlap exceeds threshold and classification is correct mark as correct
|
||||
if iou[best_i] > iou_thres and obj_pred == labels[best_i, 0] and best_i not in detected:
|
||||
correct.append(1)
|
||||
detected.append(best_i)
|
||||
else:
|
||||
correct.append(0)
|
||||
|
||||
# Compute Average Precision (AP) per class
|
||||
AP, AP_class, R, P = ap_per_class(tp=correct,
|
||||
conf=dets[:, 4],
|
||||
pred_cls=np.zeros_like(dets[:, 4]), # detections[:, 6]
|
||||
target_cls=target_cls)
|
||||
|
||||
# Accumulate AP per class
|
||||
AP_accum_count += np.bincount(AP_class, minlength=nC)
|
||||
AP_accum += np.bincount(AP_class, minlength=nC, weights=AP)
|
||||
|
||||
# Compute mean AP across all classes in this image, and append to image list
|
||||
mAPs.append(AP.mean())
|
||||
mR.append(R.mean())
|
||||
mP.append(P.mean())
|
||||
|
||||
# Means of all images
|
||||
mean_mAP = np.sum(mAPs) / (AP_accum_count + 1E-16)
|
||||
mean_R = np.sum(mR) / (AP_accum_count + 1E-16)
|
||||
mean_P = np.sum(mP) / (AP_accum_count + 1E-16)
|
||||
|
||||
if batch_i % print_interval == 0:
|
||||
# Print image mAP and running mean mAP
|
||||
print(('%11s%11s' + '%11.3g' * 4 + 's') %
|
||||
(seen, dataloader.dataset.nF, mean_P, mean_R, mean_mAP, time.time() - t))
|
||||
# Print mAP per class
|
||||
print('%11s' * 5 % ('Image', 'Total', 'P', 'R', 'mAP'))
|
||||
|
||||
print('AP: %-.4f\n\n' % (AP_accum[0] / (AP_accum_count[0] + 1E-16)))
|
||||
|
||||
# Return mAP
|
||||
return mean_mAP, mean_R, mean_P
|
||||
|
||||
if __name__ == '__main__':
|
||||
os.environ['CUDA_VISIBLE_DEVICES'] = '1'
|
||||
opt = opts().init()
|
||||
with torch.no_grad():
|
||||
map = test_det(opt, batch_size=4)
|
||||
|
|
@ -0,0 +1,117 @@
|
|||
# ------------------------------------------------------------------------------
|
||||
# Copyright (c) Microsoft Corporation
|
||||
# Licensed under MIT License
|
||||
# ------------------------------------------------------------------------------
|
||||
|
||||
|
||||
from __future__ import absolute_import
|
||||
from __future__ import division
|
||||
from __future__ import print_function
|
||||
|
||||
import _init_paths
|
||||
import argparse
|
||||
import torch
|
||||
import json
|
||||
import time
|
||||
import os
|
||||
import cv2
|
||||
import math
|
||||
|
||||
from sklearn import metrics
|
||||
from scipy import interpolate
|
||||
import numpy as np
|
||||
from torchvision.transforms import transforms as T
|
||||
import torch.nn.functional as F
|
||||
from models.model import create_model, load_model
|
||||
from datasets.dataset.jde import JointDataset, collate_fn
|
||||
from models.utils import _tranpose_and_gather_feat
|
||||
from utils.utils import xywh2xyxy, ap_per_class, bbox_iou
|
||||
from opts import opts
|
||||
from models.decode import mot_decode
|
||||
from utils.post_process import ctdet_post_process
|
||||
|
||||
|
||||
def test_emb(
|
||||
opt,
|
||||
batch_size=16,
|
||||
img_size=(1088, 608),
|
||||
print_interval=40,
|
||||
):
|
||||
data_cfg = opt.data_cfg
|
||||
f = open(data_cfg)
|
||||
data_cfg_dict = json.load(f)
|
||||
f.close()
|
||||
nC = 1
|
||||
test_paths = data_cfg_dict['test_emb']
|
||||
dataset_root = data_cfg_dict['root']
|
||||
if opt.gpus[0] >= 0:
|
||||
opt.device = torch.device('cuda')
|
||||
else:
|
||||
opt.device = torch.device('cpu')
|
||||
print('Creating model...')
|
||||
model = create_model(opt.arch, opt.heads, opt.head_conv)
|
||||
model = load_model(model, opt.load_model)
|
||||
# model = torch.nn.DataParallel(model)
|
||||
model = model.to(opt.device)
|
||||
model.eval()
|
||||
|
||||
# Get dataloader
|
||||
transforms = T.Compose([T.ToTensor()])
|
||||
dataset = JointDataset(opt, dataset_root, test_paths, img_size, augment=False, transforms=transforms)
|
||||
dataloader = torch.utils.data.DataLoader(dataset, batch_size=batch_size, shuffle=False,
|
||||
num_workers=8, drop_last=False)
|
||||
embedding, id_labels = [], []
|
||||
print('Extracting pedestrain features...')
|
||||
for batch_i, batch in enumerate(dataloader):
|
||||
t = time.time()
|
||||
output = model(batch['input'].cuda())[-1]
|
||||
id_head = _tranpose_and_gather_feat(output['id'], batch['ind'].cuda())
|
||||
id_head = id_head[batch['reg_mask'].cuda() > 0].contiguous()
|
||||
emb_scale = math.sqrt(2) * math.log(opt.nID - 1)
|
||||
id_head = emb_scale * F.normalize(id_head)
|
||||
id_target = batch['ids'].cuda()[batch['reg_mask'].cuda() > 0]
|
||||
|
||||
for i in range(0, id_head.shape[0]):
|
||||
if len(id_head.shape) == 0:
|
||||
continue
|
||||
else:
|
||||
feat, label = id_head[i], id_target[i].long()
|
||||
if label != -1:
|
||||
embedding.append(feat)
|
||||
id_labels.append(label)
|
||||
|
||||
if batch_i % print_interval == 0:
|
||||
print(
|
||||
'Extracting {}/{}, # of instances {}, time {:.2f} sec.'.format(batch_i, len(dataloader), len(id_labels),
|
||||
time.time() - t))
|
||||
|
||||
print('Computing pairwise similairity...')
|
||||
if len(embedding) < 1:
|
||||
return None
|
||||
embedding = torch.stack(embedding, dim=0).cuda()
|
||||
id_labels = torch.LongTensor(id_labels)
|
||||
n = len(id_labels)
|
||||
print(n, len(embedding))
|
||||
assert len(embedding) == n
|
||||
|
||||
embedding = F.normalize(embedding, dim=1)
|
||||
pdist = torch.mm(embedding, embedding.t()).cpu().numpy()
|
||||
gt = id_labels.expand(n, n).eq(id_labels.expand(n, n).t()).numpy()
|
||||
|
||||
up_triangle = np.where(np.triu(pdist) - np.eye(n) * pdist != 0)
|
||||
pdist = pdist[up_triangle]
|
||||
gt = gt[up_triangle]
|
||||
|
||||
far_levels = [1e-6, 1e-5, 1e-4, 1e-3, 1e-2, 1e-1]
|
||||
far, tar, threshold = metrics.roc_curve(gt, pdist)
|
||||
interp = interpolate.interp1d(far, tar)
|
||||
tar_at_far = [interp(x) for x in far_levels]
|
||||
for f, fa in enumerate(far_levels):
|
||||
print('TPR@FAR={:.7f}: {:.4f}'.format(fa, tar_at_far[f]))
|
||||
return tar_at_far
|
||||
|
||||
if __name__ == '__main__':
|
||||
os.environ['CUDA_VISIBLE_DEVICES'] = '1'
|
||||
opt = opts().init()
|
||||
with torch.no_grad():
|
||||
map = test_emb(opt, batch_size=4)
|
||||
|
|
@ -0,0 +1,240 @@
|
|||
# ------------------------------------------------------------------------------
|
||||
# Copyright (c) Microsoft Corporation
|
||||
# Licensed under MIT License
|
||||
# ------------------------------------------------------------------------------
|
||||
|
||||
from __future__ import absolute_import
|
||||
from __future__ import division
|
||||
from __future__ import print_function
|
||||
|
||||
import _init_paths
|
||||
import os
|
||||
import os.path as osp
|
||||
import cv2
|
||||
import logging
|
||||
import argparse
|
||||
import motmetrics as mm
|
||||
import numpy as np
|
||||
import torch
|
||||
|
||||
from tracker.multitracker import JDETracker
|
||||
from tracking_utils import visualization as vis
|
||||
from tracking_utils.log import logger
|
||||
from tracking_utils.timer import Timer
|
||||
from tracking_utils.evaluation import Evaluator
|
||||
import datasets.dataset.jde as datasets
|
||||
|
||||
from tracking_utils.utils import mkdir_if_missing
|
||||
from opts import opts
|
||||
|
||||
|
||||
def write_results(filename, results, data_type):
|
||||
if data_type == 'mot':
|
||||
save_format = '{frame},{id},{x1},{y1},{w},{h},1,-1,-1,-1\n'
|
||||
elif data_type == 'kitti':
|
||||
save_format = '{frame} {id} pedestrian 0 0 -10 {x1} {y1} {x2} {y2} -10 -10 -10 -1000 -1000 -1000 -10\n'
|
||||
else:
|
||||
raise ValueError(data_type)
|
||||
|
||||
with open(filename, 'w') as f:
|
||||
for frame_id, tlwhs, track_ids in results:
|
||||
if data_type == 'kitti':
|
||||
frame_id -= 1
|
||||
for tlwh, track_id in zip(tlwhs, track_ids):
|
||||
if track_id < 0:
|
||||
continue
|
||||
x1, y1, w, h = tlwh
|
||||
x2, y2 = x1 + w, y1 + h
|
||||
line = save_format.format(frame=frame_id, id=track_id, x1=x1, y1=y1, x2=x2, y2=y2, w=w, h=h)
|
||||
f.write(line)
|
||||
logger.info('save results to {}'.format(filename))
|
||||
|
||||
|
||||
def eval_seq(opt, dataloader, data_type, result_filename, save_dir=None, show_image=True, frame_rate=30):
|
||||
if save_dir:
|
||||
mkdir_if_missing(save_dir)
|
||||
tracker = JDETracker(opt, frame_rate=frame_rate)
|
||||
timer = Timer()
|
||||
results = []
|
||||
frame_id = 0
|
||||
for path, img, img0 in dataloader:
|
||||
if frame_id % 20 == 0:
|
||||
logger.info('Processing frame {} ({:.2f} fps)'.format(frame_id, 1. / max(1e-5, timer.average_time)))
|
||||
|
||||
# run tracking
|
||||
timer.tic()
|
||||
blob = torch.from_numpy(img).cuda().unsqueeze(0)
|
||||
online_targets = tracker.update(blob, img0)
|
||||
online_tlwhs = []
|
||||
online_ids = []
|
||||
for t in online_targets:
|
||||
tlwh = t.tlwh
|
||||
tid = t.track_id
|
||||
vertical = tlwh[2] / tlwh[3] > 1.6
|
||||
if tlwh[2] * tlwh[3] > opt.min_box_area and not vertical:
|
||||
online_tlwhs.append(tlwh)
|
||||
online_ids.append(tid)
|
||||
timer.toc()
|
||||
# save results
|
||||
results.append((frame_id + 1, online_tlwhs, online_ids))
|
||||
if show_image or save_dir is not None:
|
||||
online_im = vis.plot_tracking(img0, online_tlwhs, online_ids, frame_id=frame_id,
|
||||
fps=1. / timer.average_time)
|
||||
if show_image:
|
||||
cv2.imshow('online_im', online_im)
|
||||
if save_dir is not None:
|
||||
cv2.imwrite(os.path.join(save_dir, '{:05d}.jpg'.format(frame_id)), online_im)
|
||||
frame_id += 1
|
||||
# save results
|
||||
write_results(result_filename, results, data_type)
|
||||
return frame_id, timer.average_time, timer.calls
|
||||
|
||||
|
||||
def main(opt, data_root='/data/MOT16/train', det_root=None, seqs=('MOT16-05',), exp_name='demo',
|
||||
save_images=False, save_videos=False, show_image=True):
|
||||
logger.setLevel(logging.INFO)
|
||||
result_root = os.path.join(data_root, '..', 'results', exp_name)
|
||||
mkdir_if_missing(result_root)
|
||||
data_type = 'mot'
|
||||
|
||||
# run tracking
|
||||
accs = []
|
||||
n_frame = 0
|
||||
timer_avgs, timer_calls = [], []
|
||||
for seq in seqs:
|
||||
output_dir = os.path.join(data_root, '..', 'outputs', exp_name, seq) if save_images or save_videos else None
|
||||
logger.info('start seq: {}'.format(seq))
|
||||
dataloader = datasets.LoadImages(osp.join(data_root, seq, 'img1'), opt.img_size)
|
||||
result_filename = os.path.join(result_root, '{}.txt'.format(seq))
|
||||
meta_info = open(os.path.join(data_root, seq, 'seqinfo.ini')).read()
|
||||
frame_rate = int(meta_info[meta_info.find('frameRate') + 10:meta_info.find('\nseqLength')])
|
||||
nf, ta, tc = eval_seq(opt, dataloader, data_type, result_filename,
|
||||
save_dir=output_dir, show_image=show_image, frame_rate=frame_rate)
|
||||
n_frame += nf
|
||||
timer_avgs.append(ta)
|
||||
timer_calls.append(tc)
|
||||
|
||||
# eval
|
||||
logger.info('Evaluate seq: {}'.format(seq))
|
||||
evaluator = Evaluator(data_root, seq, data_type)
|
||||
accs.append(evaluator.eval_file(result_filename))
|
||||
if save_videos:
|
||||
output_video_path = osp.join(output_dir, '{}.mp4'.format(seq))
|
||||
cmd_str = 'ffmpeg -f image2 -i {}/%05d.jpg -c:v copy {}'.format(output_dir, output_video_path)
|
||||
os.system(cmd_str)
|
||||
timer_avgs = np.asarray(timer_avgs)
|
||||
timer_calls = np.asarray(timer_calls)
|
||||
all_time = np.dot(timer_avgs, timer_calls)
|
||||
avg_time = all_time / np.sum(timer_calls)
|
||||
logger.info('Time elapsed: {:.2f} seconds, FPS: {:.2f}'.format(all_time, 1.0 / avg_time))
|
||||
|
||||
# get summary
|
||||
metrics = mm.metrics.motchallenge_metrics
|
||||
mh = mm.metrics.create()
|
||||
summary = Evaluator.get_summary(accs, seqs, metrics)
|
||||
strsummary = mm.io.render_summary(
|
||||
summary,
|
||||
formatters=mh.formatters,
|
||||
namemap=mm.io.motchallenge_metric_names
|
||||
)
|
||||
print(strsummary)
|
||||
Evaluator.save_summary(summary, os.path.join(result_root, 'summary_{}.xlsx'.format(exp_name)))
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
|
||||
opt = opts().init()
|
||||
|
||||
if not opt.val_mot16:
|
||||
seqs_str = '''KITTI-13
|
||||
KITTI-17
|
||||
ADL-Rundle-6
|
||||
PETS09-S2L1
|
||||
TUD-Campus
|
||||
TUD-Stadtmitte'''
|
||||
data_root = os.path.join(opt.data_dir, 'MOT15/images/train')
|
||||
else:
|
||||
seqs_str = '''MOT16-02
|
||||
MOT16-04
|
||||
MOT16-05
|
||||
MOT16-09
|
||||
MOT16-10
|
||||
MOT16-11
|
||||
MOT16-13'''
|
||||
data_root = os.path.join(opt.data_dir, 'MOT16/train')
|
||||
if opt.test_mot16:
|
||||
seqs_str = '''MOT16-01
|
||||
MOT16-03
|
||||
MOT16-06
|
||||
MOT16-07
|
||||
MOT16-08
|
||||
MOT16-12
|
||||
MOT16-14'''
|
||||
data_root = os.path.join(opt.data_dir, 'MOT16/test')
|
||||
if opt.test_mot15:
|
||||
seqs_str = '''ADL-Rundle-1
|
||||
ADL-Rundle-3
|
||||
AVG-TownCentre
|
||||
ETH-Crossing
|
||||
ETH-Jelmoli
|
||||
ETH-Linthescher
|
||||
KITTI-16
|
||||
KITTI-19
|
||||
PETS09-S2L2
|
||||
TUD-Crossing
|
||||
Venice-1'''
|
||||
data_root = os.path.join(opt.data_dir, 'MOT15/images/test')
|
||||
if opt.test_mot17:
|
||||
seqs_str = '''MOT17-01-SDP
|
||||
MOT17-03-SDP
|
||||
MOT17-06-SDP
|
||||
MOT17-07-SDP
|
||||
MOT17-08-SDP
|
||||
MOT17-12-SDP
|
||||
MOT17-14-SDP'''
|
||||
data_root = os.path.join(opt.data_dir, 'MOT17/images/test')
|
||||
if opt.val_mot17:
|
||||
seqs_str = '''MOT17-02-SDP
|
||||
MOT17-04-SDP
|
||||
MOT17-05-SDP
|
||||
MOT17-09-SDP
|
||||
MOT17-10-SDP
|
||||
MOT17-11-SDP
|
||||
MOT17-13-SDP'''
|
||||
data_root = os.path.join(opt.data_dir, 'MOT17/images/train')
|
||||
if opt.val_mot15:
|
||||
seqs_str = '''KITTI-13
|
||||
KITTI-17
|
||||
ETH-Bahnhof
|
||||
ETH-Sunnyday
|
||||
PETS09-S2L1
|
||||
TUD-Campus
|
||||
TUD-Stadtmitte
|
||||
ADL-Rundle-6
|
||||
ADL-Rundle-8
|
||||
ETH-Pedcross2
|
||||
TUD-Stadtmitte'''
|
||||
data_root = os.path.join(opt.data_dir, 'MOT15/images/train')
|
||||
if opt.val_mot20:
|
||||
seqs_str = '''MOT20-01
|
||||
MOT20-02
|
||||
MOT20-03
|
||||
MOT20-05
|
||||
'''
|
||||
data_root = os.path.join(opt.data_dir, 'MOT20/images/train')
|
||||
if opt.test_mot20:
|
||||
seqs_str = '''MOT20-04
|
||||
MOT20-06
|
||||
MOT20-07
|
||||
MOT20-08
|
||||
'''
|
||||
data_root = os.path.join(opt.data_dir, 'MOT20/images/test')
|
||||
seqs = [seq.strip() for seq in seqs_str.split()]
|
||||
|
||||
main(opt,
|
||||
data_root=data_root,
|
||||
seqs=seqs,
|
||||
exp_name='MOT15_val_all_dla34',
|
||||
show_image=False,
|
||||
save_images=False,
|
||||
save_videos=False)
|
||||
|
|
@ -0,0 +1,101 @@
|
|||
# ------------------------------------------------------------------------------
|
||||
# Copyright (c) Microsoft Corporation
|
||||
# Licensed under MIT License
|
||||
# ------------------------------------------------------------------------------
|
||||
from __future__ import absolute_import
|
||||
from __future__ import division
|
||||
from __future__ import print_function
|
||||
|
||||
import _init_paths
|
||||
|
||||
import os
|
||||
|
||||
import json
|
||||
import torch
|
||||
import torch.utils.data
|
||||
from torchvision.transforms import transforms as T
|
||||
from opts import opts
|
||||
from models.model import create_model, load_model, save_model
|
||||
from models.data_parallel import DataParallel
|
||||
from logger import Logger
|
||||
from datasets.dataset_factory import get_dataset
|
||||
from trains.train_factory import train_factory
|
||||
|
||||
|
||||
def main(opt):
|
||||
torch.manual_seed(opt.seed)
|
||||
torch.backends.cudnn.benchmark = not opt.not_cuda_benchmark and not opt.test
|
||||
|
||||
print('Setting up data...')
|
||||
Dataset = get_dataset(opt.dataset, opt.task)
|
||||
f = open(opt.data_cfg)
|
||||
data_config = json.load(f)
|
||||
trainset_paths = data_config['train']
|
||||
dataset_root = data_config['root']
|
||||
f.close()
|
||||
transforms = T.Compose([T.ToTensor()])
|
||||
dataset = Dataset(opt, dataset_root, trainset_paths, (1088, 608), augment=True, transforms=transforms)
|
||||
opt = opts().update_dataset_info_and_set_heads(opt, dataset)
|
||||
print(opt)
|
||||
|
||||
logger = Logger(opt)
|
||||
|
||||
os.environ['CUDA_VISIBLE_DEVICES'] = opt.gpus_str
|
||||
opt.device = torch.device('cuda' if opt.gpus[0] >= 0 else 'cpu')
|
||||
|
||||
print('Creating model...')
|
||||
model = create_model(opt.arch, opt.heads, opt.head_conv)
|
||||
optimizer = torch.optim.Adam(model.parameters(), opt.lr)
|
||||
start_epoch = 0
|
||||
if opt.load_model != '':
|
||||
model, optimizer, start_epoch = load_model(
|
||||
model, opt.load_model, optimizer, opt.resume, opt.lr, opt.lr_step)
|
||||
|
||||
# Get dataloader
|
||||
|
||||
train_loader = torch.utils.data.DataLoader(
|
||||
dataset,
|
||||
batch_size=opt.batch_size,
|
||||
shuffle=True,
|
||||
num_workers=opt.num_workers,
|
||||
pin_memory=True,
|
||||
drop_last=True
|
||||
)
|
||||
|
||||
print('Starting training...')
|
||||
Trainer = train_factory[opt.task]
|
||||
trainer = Trainer(opt, model, optimizer)
|
||||
trainer.set_device(opt.gpus, opt.chunk_sizes, opt.device)
|
||||
best = 1e10
|
||||
for epoch in range(start_epoch + 1, opt.num_epochs + 1):
|
||||
mark = epoch if opt.save_all else 'last'
|
||||
log_dict_train, _ = trainer.train(epoch, train_loader)
|
||||
logger.write('epoch: {} |'.format(epoch))
|
||||
for k, v in log_dict_train.items():
|
||||
logger.scalar_summary('train_{}'.format(k), v, epoch)
|
||||
logger.write('{} {:8f} | '.format(k, v))
|
||||
|
||||
if opt.val_intervals > 0 and epoch % opt.val_intervals == 0:
|
||||
save_model(os.path.join(opt.save_dir, 'model_{}.pth'.format(mark)),
|
||||
epoch, model, optimizer)
|
||||
else:
|
||||
save_model(os.path.join(opt.save_dir, 'model_last.pth'),
|
||||
epoch, model, optimizer)
|
||||
logger.write('\n')
|
||||
if epoch in opt.lr_step:
|
||||
save_model(os.path.join(opt.save_dir, 'model_{}.pth'.format(epoch)),
|
||||
epoch, model, optimizer)
|
||||
lr = opt.lr * (0.1 ** (opt.lr_step.index(epoch) + 1))
|
||||
print('Drop LR to', lr)
|
||||
for param_group in optimizer.param_groups:
|
||||
param_group['lr'] = lr
|
||||
if epoch % 5 == 0:
|
||||
save_model(os.path.join(opt.save_dir, 'model_{}.pth'.format(epoch)),
|
||||
epoch, model, optimizer)
|
||||
logger.close()
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
os.environ['CUDA_VISIBLE_DEVICES'] = '0, 1'
|
||||
opt = opts().parse()
|
||||
main(opt)
|
||||
Загрузка…
Ссылка в новой задаче