AI/U-2-Net
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/xuebinqin/U-2-Net synced 2025-08-14 06:35:58 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

protrait

Browse Source
This commit is contained in:
NathanUA 2020-11-21 21:12:16 -07:00
parent 99bcba1558
commit b08dc75fb0
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -28,9 +28,9 @@ __Contact__: xuebin[at]ualberta[dot]ca
git clone https://github.com/NathanUA/U-2-Net.git
```
2. Download the [**U2net_portrait.pth**](https://drive.google.com/file/d/1IG3HdpcRiDoWNookbncQjeaPN28t90yW/view?usp=sharing) model and put it into the directory: ```./saved_models/u2net_portrait/```.
2. Download the [**u2net_portrait.pth**](https://drive.google.com/file/d/1IG3HdpcRiDoWNookbncQjeaPN28t90yW/view?usp=sharing) model and put it into the directory: ```./saved_models/u2net_portrait/```.
3. Run on the testing set. Download the train and test set from [**APDrawingGAN**](https://github.com/yiranran/APDrawingGAN). These images and their ground truth are stitched side-by-side (512x1024). You need to split each of these images into two 512x512 images and put them into ```./test_data/test_portrait_images/portrait_im/``. You can also download the split testing set on [**GoogleDrive**](https://drive.google.com/file/d/1NkTsDDN8VO-JVik6VxXyV-3l2eo29KCk/view?usp=sharing). Running the inference with command ```python u2net_portrait_test.py``` will ouptut the results into ```./test_data/test_portrait_images/portrait_results```.
3. Run on the testing set. Download the train and test set from [**APDrawingGAN**](https://github.com/yiranran/APDrawingGAN). These images and their ground truth are stitched side-by-side (512x1024). You need to split each of these images into two 512x512 images and put them into ```./test_data/test_portrait_images/portrait_im/``. You can also download the split testing set on [GoogleDrive](https://drive.google.com/file/d/1NkTsDDN8VO-JVik6VxXyV-3l2eo29KCk/view?usp=sharing). Running the inference with command ```python u2net_portrait_test.py``` will ouptut the results into ```./test_data/test_portrait_images/portrait_results```.
4. Run on your own dataset. Prepare your images and put them into ```./test_data/test_portrait_images/your_portrait_im/```. Run the prediction by command ```python u2net_portrait_demo.py``` The difference of the code for runing the test set and your own dataset is that the testing set are normalized and cropped to 512x512 for including only head of human, while your own dataset may varies with different resolution and contents. To achieve stable results, we added a simple [**face detection**](https://opencv-python-tutroals.readthedocs.io/en/latest/py_tutorials/py_objdetect/py_face_detection/py_face_detection.html) step before the portrait generation in ```u2net_portrait_demo.py```. Therefore, the code will detect the biggest face from the given image and then crop, pad and resize the ROI to 512x512 for feeding to the network.