pytorch-deep-image-matting
This repository includes the non-official pytorch implementation of deep image matting.
Performance
model | SAD | MSE | Grad | Conn | link |
---|---|---|---|---|---|
paper-stage1 | 54.6 | 0.017 | 36.7 | 55.3 | |
my-stage1 | 57.1 | 0.017 | 36.1 | 58.3 | download |
- Training batch=1, images=43100, epochs=12.
- Test maxSize=1600.
Installation
- Python 2.7.12 or 3.6.5
- Pytorch 0.4.0 or 1.0.0
- OpenCV 3.4.3
Demo
Download our model to the ./model
and run the following command. Then the predict alpha mattes will locate in the folder ./result/example/pred
.
python core/demo.py
Training
Adobe-Deep-Image-Matting-Dataset
Please concat author for available.
MSCOCO-2017-Train-Dataset
PASCAL-VOC-2012
Composite-Dataset
Run the following command and the composite training and test dataset will locate in Combined_Dataset/Training_set/comp
and Combined_Dataset/Test_set/comp
, Combined_Dataset
is the extracted folder of Adobe-Deep-Image-Matting-Dataset
python tools/composite.py
Pretrained-Model
Run the following command and the pretrained model will locate in ./model/vgg_state_dict.pth
python tools/chg_model.py
Start Training
Run the following command and start the training
bash train.sh
Test
Run the following command and start the test of Adobe-1k-Composite-Dataset
bash deploy.sh
Evaluation
Plead eval with official Matlab Code. and get the SAD, MSE, Grad Conn.
Visualization
Running model is Stage1-SAD=57.1, please click to view whole images.
Image | Trimap | Pred-Alpha | GT-Alpha |
---|---|---|---|