Maocheng Hu 46b2185aee second commit пре 3 година
..
model 46b2185aee second commit пре 3 година
README.md 46b2185aee second commit пре 3 година
basic_ops.py 46b2185aee second commit пре 3 година
benchmark.py 46b2185aee second commit пре 3 година
config.yml 46b2185aee second commit пре 3 година
dataloader.py 46b2185aee second commit пре 3 година
forward.py 46b2185aee second commit пре 3 година
logger.py 46b2185aee second commit пре 3 година
utils.py 46b2185aee second commit пре 3 година

README.md

Deep Hough Transform for Semantic Line Detection

High speed performance Jittor implementation Code accompanying the paper "Deep Hough Transform for Semantic Line Detection" (ECCV 2020, PAMI 2021). arXiv2003.04676 | Online Demo | Project page | New dataset | Line Annotator

  • Jittor inference code is open available now.
  • Training code will come soon.

High speed of Jittor framework

Network inference FPS and speedup ratio (without post processing):

  <td rowspan="2"></td>
  <td colspan="3">TITAN XP</td>
  <td colspan="3">Tesla P100</td>
  <td colspan="3">RTX 2080Ti</td>

  <td>bs=1</td>
  <td>bs=4</td>
  <td>bs=8</td>
 <td>bs=1</td>
  <td>bs=4</td>
  <td>bs=8</td>
 <td>bs=1</td>
  <td>bs=4</td>
  <td>bs=8</td>

  <td>Jittor</td>
  <td>44</td>
  <td>54</td>
 <td>56</td>
 <td>42</td>
  <td>49</td>
 <td>52</td>
 <td>82</td>
  <td>98</td>
 <td>100</td>

  <td>Pytorch</td>
  <td>39</td>
  <td>48</td>
 <td>49</td>
 <td>35</td>
  <td>44</td>
 <td>44</td>
 <td>64</td>
  <td>71</td>
 <td>71</td>

  <td>Speedup</td>
  <td>1.13</td>
  <td>1.13</td>
 <td>1.14</td>
 <td>1.20</td>
  <td>1.11</td>
 <td>1.18</td>
 <td>1.28</td>
  <td>1.38</td>
 <td>1.41</td>

Tesla V100 (16G PCI-E) Tesla V100 RTX TITAN
bs=1 bs=4 bs=8 bs=1 bs=4 bs=8 bs=1 bs=4 bs=8
Jittor 89 115 120 88 108 113 27 74 106
Pytorch 38 75 82 10 34 53 9 15 34
Speedup 2.34 1.53 1.46 8.80 3.18 2.13 3.00 4.93 3.12

Requirements

jittor
numpy
scipy
opencv-python
scikit-image
pytorch 1.0<=1.3
tqdm
yml

Pretrain model (based on ResNet50-FPN): http://data.kaizhao.net/projects/deep-hough-transform/dht_r50_fpn_sel-c9a29d40.pth (SEL dataset) and http://data.kaizhao.net/projects/deep-hough-transform/dht_r50_nkl_d97b97138.pth (NKL dataset / used in online demo)

Prepare training data

Download original SEL dataset from here and extract to data/ directory. After that, the directory structure should be like:

data
├── ICCV2017_JTLEE_gtlines_all
├── ICCV2017_JTLEE_gt_pri_lines_for_test
├── ICCV2017_JTLEE_images
├── prepare_data_JTLEE.py
├── Readme.txt
├── test_idx_1716.txt
└── train_idx_1716.txt

Then run python script to generate parametric space label.

cd deep-hough-transfrom
python data/prepare_data_JTLEE.py --root './data/ICCV2017_JTLEE_images/' --label './data/ICCV2017_JTLEE_gtlines_all' --save-dir './data/training/JTLEE_resize_100_100/' --list './data/training/JTLEE.lst' --prefix 'JTLEE_resize_100_100' --fixsize 400 --numangle 100 --numrho 100

For NKL dataset, you can download the dataset and put it to data dir. Then run python script to generate parametric space label.

cd deep-hough-transform
python data/prepare_data_NKL.py --root './data/NKL' --label './data/NKL' --save-dir './data/training/NKL_resize_100_100' --fixsize 400

Forward

Generate visualization results and save coordinates to _.npy file.

CUDA_VISIBLE_DEVICES=0 python forward.py --model (your_best_model.pth) --tmp (your_result_save_dir)

Citation

If our method/dataset are useful to your research, please consider to cite us:

@article{hu2020jittor,
  title={Jittor: a novel deep learning framework with meta-operators and unified graph execution},
  author={Hu, Shi-Min and Liang, Dun and Yang, Guo-Ye and Yang, Guo-Wei and Zhou, Wen-Yang},
  journal={Information Sciences},
  volume={63},
  number={222103},
  pages={1--21},
  year={2020}
}
@article{zhao2021deep,
  author    = {Kai Zhao and Qi Han and Chang-bin Zhang and Jun Xu and Ming-ming Cheng},
  title     = {Deep Hough Transform for Semantic Line Detection},
  journal   = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
  year      = {2021},
  doi       = {10.1109/TPAMI.2021.3077129}
}
@inproceedings{eccv2020line,
  title={Deep Hough Transform for Semantic Line Detection},
  author={Qi Han and Kai Zhao and Jun Xu and Ming-Ming Cheng},
  booktitle={ECCV},
  pages={750--766},
  year={2020}
}

License

This project is licensed under the Creative Commons NonCommercial (CC BY-NC 3.0) license where only non-commercial usage is allowed. For commercial usage, please contact us.