Implementation of pytorch semantic segmentation with figaro-1k.
- tutorial document : https://pytorchhair.gitbook.io/project/ (kor)
opencv-contrib-python 3.4.4
pytorch 0.4.1
torchvision 0.2.1
numpy 1.14.5
# specify a directory for dataset to be downloaded into, else default is ./data/
sh data/figaro.sh #<directory># sample execution
python3 main.py \
--networks mobilenet \
--dataset figaro \
--data_dir ./data/Figaro1k \
--scheduler ReduceLROnPlateau \
--batch_size 4 \
--epochs 5 \
--lr 1e-3 \
--num_workers 2 \
--optimizer adam \
--img_size 256 \
--momentum 0.5 \
--ignite True- You should add your own model script in
networksand make it avaliable inget_networkin./networks/__init__.py
with ignite
docker run davinnovation/pytorch-hairsegment:cpu python main.py
with no-ignite
docker run -p davinnovation/pytorch-hairsegment:cpu python main.py --ignite False
# sample execution
python3 evaluate.py \
--networks pspnet_resnet101 \
--ckpt_dir [path to checkpoint] \
--dataset figaro \
--data_dir ./data/Figaro1k \
--save_dir ./overlay/ \
--use_gpu True| Model | IoU | F1-score | Checkpoint |
|---|---|---|---|
| pspnet_resnet101 | 0.92 | 0.96 | link |
| pspnet_squeezenet | 0.88 | 0.91 | link |
| deeplabv3plus | 0.80 | 0.89 | - |
- Red: GT / Blue: Segmentation Map
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent