Tramac / awesome-semantic-segmentation-pytorch

Semantic Segmentation on PyTorch (include FCN, PSPNet, Deeplabv3, Deeplabv3+, DANet, DenseASPP, BiSeNet, EncNet, DUNet, ICNet, ENet, OCNet, CCNet, PSANet, CGNet, ESPNet, LEDNet, DFANet)
Apache License 2.0
2.82k stars 581 forks source link

How to get the xception base model file ? #82

Open tomjerrygithub opened 4 years ago

tomjerrygithub commented 4 years ago

deeplabv3+ without xception base file , very slow can you share the base model file ? or how to get it? thx

sainatarajan commented 4 years ago

I have tried 2-3 different xception.pth files available all over the internet and it always throws some dictionary error. This is obvious since the model was built by different people and hence not compatible with the model built by this repo owner.

pyradd commented 4 years ago

I am facing the same issue. @Tramac Please provide us with the specific xception base model. Or else runnug deeplabv3_plus is not convenient. Thanks :)

lr1234567 commented 4 years ago

你好,我也遇到了这个问题,请问您是怎么解决的?下面是报错日志 Traceback (most recent call last): File "train.py", line 340, in trainer = Trainer(args) File "train.py", line 167, in init aux=args.aux, norm_layer=BatchNorm2d).to(self.device) File "/home/lr/桌面/awesome-semantic-segmentation-pytorch-master.2/core/models/model_zoo.py", line 137, in get_segmentation_model return modelsmodel File "/home/lr/桌面/awesome-semantic-segmentation-pytorch-master.2/core/models/deeplabv3_plus.py", line 131, in get_deeplabv3_plus model = DeepLabV3Plus(datasets[dataset].NUM_CLASS, backbone=backbone, pretrained_base=pretrained_base, kwargs) File "/home/lr/桌面/awesome-semantic-segmentation-pytorch-master.2/core/models/deeplabv3_plus.py", line 39, in init self.pretrained = get_xception(pretrained=pretrained_base, output_stride=output_stride, kwargs) File "/home/lr/桌面/awesome-semantic-segmentation-pytorch-master.2/core/models/base_models/xception.py", line 390, in get_xception model.load_state_dict(torch.load(get_model_file('xception', root=root))) File "/home/lr/桌面/awesome-semantic-segmentation-pytorch-master.2/core/models/model_store.py", line 68, in get_model_file raise ValueError('Model file is not found. Downloading or trainning.') ValueError: Model file is not found. Downloading or trainning.

sainatarajan commented 4 years ago

@lr1234567 xception backbone is not available. So try a different model such as PSPNet.

lr1234567 commented 4 years ago

@lr1234567 xception backbone is not available. So try a different model such as PSPNet. 好的 感谢告知

bbbts commented 1 month ago

I have tried 2-3 different xception.pth files available all over the internet and it always throws some dictionary error. This is obvious since the model was built by different people and hence not compatible with the model built by this repo owner.

@tomjerrygithub @sainatarajan @pyradd I am having the same issue training on deeplabv3_plus with xception. Were you able to solve it? Were you able to find the base xception backbone? Kindly help