Tramac
Tramac
`pascal_voc.py` is ok.
Hi, please change this [line](https://github.com/Tramac/awesome-semantic-segmentation-pytorch/blob/7fbe397a9add570fe1ebee8654898f2b3ba1942f/core/models/pspnet.py#L104) to your model path.
The `vgg16-397923af.pth` is the pretrained model and the `fcn32s_vgg16_pascal_voc.pth` is your trained model.
Thank you! Please feel free to contact me on WeChat or Zhihu if you don't mind.
Sorry, there is no trained model. [This](https://github.com/Tramac/Lightweight-Segmentation) project with trained model maybe helpful.
Please try `.../datasets/voc/VOCdevkit` -> `../datasets/voc/VOCdevkit`.
You need to change the first convolutional layer.
It looks like the `python` is missing.
Please print `python train.py --help`
Sorry, I did not keep the trained model.