GOTURN-Tensorflow-master
所属分类:视频捕捉采集剪辑
开发工具:Python
文件大小:5110KB
下载次数:3
上传日期:2020-08-04 11:20:36
上 传 者:
卡瓦一
说明: 2016cvpr目标跟踪代码,GOTURN实现
(2016CVPR target tracking code)
文件列表:
LICENCE (1066, 2018-02-12)
__init__.py (0, 2018-02-12)
checkpoints (0, 2018-02-12)
checkpoints\checkpoint (91, 2018-02-12)
checkpoints\checkpoint.ckpt-1.index (1859, 2018-02-12)
goturn_net.py (17682, 2018-02-12)
imgs (0, 2018-02-12)
imgs\pull7f-web_e2.png (241255, 2018-02-12)
load_and_test.py (4264, 2018-02-12)
test_example (0, 2018-02-12)
test_example\searching (0, 2018-02-12)
test_example\searching\000000.jpg (7212, 2018-02-12)
test_example\searching\000001.jpg (8330, 2018-02-12)
test_example\searching\000002.jpg (7140, 2018-02-12)
test_example\searching\000003.jpg (4731, 2018-02-12)
test_example\searching\000004.jpg (12038, 2018-02-12)
test_example\searching\000005.jpg (8271, 2018-02-12)
test_example\searching\000006.jpg (6191, 2018-02-12)
test_example\searching\000007.jpg (7890, 2018-02-12)
test_example\searching\000008.jpg (10321, 2018-02-12)
test_example\searching\000009.jpg (5103, 2018-02-12)
test_example\searching\000010.jpg (11351, 2018-02-12)
test_example\searching\000011.jpg (14907, 2018-02-12)
test_example\searching\000012.jpg (14151, 2018-02-12)
test_example\searching\000013.jpg (15299, 2018-02-12)
test_example\searching\000014.jpg (10730, 2018-02-12)
test_example\searching\000015.jpg (17003, 2018-02-12)
test_example\searching\000016.jpg (11778, 2018-02-12)
test_example\searching\000017.jpg (22019, 2018-02-12)
test_example\searching\000018.jpg (28655, 2018-02-12)
test_example\searching\000019.jpg (26210, 2018-02-12)
test_example\searching\000020.jpg (17213, 2018-02-12)
test_example\searching\000021.jpg (32913, 2018-02-12)
test_example\searching\000022.jpg (26019, 2018-02-12)
test_example\searching\000023.jpg (28530, 2018-02-12)
test_example\searching\000024.jpg (28740, 2018-02-12)
test_example\searching\000025.jpg (37046, 2018-02-12)
... ...
# GOTURN-Tensorflow
This is a tensorflow implementation of GOTURN.
Thanks to author **David Held** for his help of this implementation.
The original paper is:
**[Learning to Track at 100 FPS with Deep Regression Networks](http://davheld.github.io/GOTURN/GOTURN.html)**,
[David Held](http://davheld.github.io/),
[Sebastian Thrun](http://robots.stanford.edu/),
[Silvio Savarese](http://cvgl.stanford.edu/silvio/),
The github repo for caffe implementation is given by the authors:
**[davheld/GOTURN](https://github.com/davheld/GOTURN)**
Brief illustration of how this network works:
You can refer to the paper or github repo above for more details.
## Environment
- python3
- tensorflow 1.0+, both cpu and gpu work fine
## How to use it
### Finetune for your own dataset
1. Create a folder, fill in all training images
2. Create a
.txt file
- It should contains target image, searching image and ground-truth bounding box
- Bounding box is in the form of ``, usually from 0 to 1, but exceeding this range is also fine.
- Example of one line:
`train/target/000024.jpg,train/searching/000024.jpg,0.292692307692307***,0.22233115468409587,0.7991794871794871,0.7608061002178***9`
3. Change related places in `train.py`
4. Train it and wait!
```python
python train.py
```
5. The log file is `train.log` by default
### Test
1. Download pretrained model from: [GOTURN_MODEL](https://drive.google.com/open?id=0BwToyaMzz69QZ3Zlc0h4NzhBNDg)
2. Uncompress the `checkpoints` folder, and put it in the root directory of this repo
3. Test on examples just by running `load_and_test.py`
```python
python load_and_test.py
```
4. The log file is `test.log` by default
### TIPS
Be careful, the output of this network actually always from 0 to 10 thus I multiplied the ground-truth bounding boxes( always ranging from 0 to 1) by 10.
近期下载者:
相关文件:
收藏者: