ouyang11111

Results 10 issues of ouyang11111

@stonessss yes, i write test code. 1. copy and overwrite. https://github.com/jaemin93/pytorch-deeplab-xception/blob/master/test.py https://github.com/jaemin93/pytorch-deeplab-xception/blob/master/dataloaders/__init__.py 2. add test.txt(you want to test img id) in VOC path /ImageSets/Segmentation test.txt is like val, train.txt 3....

我用PascalVOC训练的权重 失败了 boxes = outputs[:,0:4]

please open the pretrained model dowload link

# install wsl cd projects/WSL pip install git+https://github.com/lucasb-eyer/pydensecrf.git pip install opencv-python sklearn shapely pip install git+https://github.com/cocodataset/panopticapi.git git submodule update --init --recursive python3 -m pip install -v -e . ## 运行到这一步会产生巨量bug,导致编译失败,

Download VGG Backbone from [here](https://1drv.ms/f/s!Am1oWgo9554dgRQ8RE1SRGvK7HW2) following [UWSOD repo](https://github.com/shenyunhang/UWSOD/tree/UWSOD/projects/WSL).

Hello, I want to use your model to batch convert real images into different styles, but the intermediate files generated by your model take up too much space. Is there...

how to set batch size and optimizer