Overfitting test of DeeplabV3+

[leogogogo]

Hi, great work! A question about overfitting test, have you tried the DeeplabV3+ model？Recently I try to do the same thing but with a picture from Cityscapes with DeeplabV3+ model, it seems like that it's hard to be overfitted compared with other models. I'm wondering whether you also have the same experience or not.

[molalasue]

Hi! I wang to aks you a question. When I tried to train on the DeeplabV3+ model, raise the followinng error: File "train.py", line 326, in trainer = Trainer(args) File "train.py", line 162, in init aux=args.aux, norm_layer=BatchNorm2d).to(self.device) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/model_zoo.py", line 122, in get_segmentation_model return modelsmodel File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/deeplabv3_plus.py", line 127, in get_deeplabv3_plus model = DeepLabV3Plus(datasets[dataset].NUM_CLASS, backbone=backbone, pretrained_base=pretrained_base, kwargs) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/deeplabv3_plus.py", line 38, in init self.pretrained = get_xception(pretrained=pretrained_base, output_stride=output_stride, kwargs) File "/home/xst/awesome-semantic-segmentation-pytorch-master/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/xst/awesome-semantic-segmentation-pytorch-master/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. Did you solve the problem? Could you please give me some advice? Thank you very much!

[Sawyer117]

@pumpkinsue Hi for me I got the training pipeline working by replacing the xception with the model here: https://github.com/jfzhang95/pytorch-deeplab-xception/blob/master/modeling/backbone/xception.py but then you need to modify the xception.py and add self.midflow in the same fashion of xception in this repo, and at last, although the training is fine, the mIOU is awfully low.

[Wongshy]

Hi! I wang to aks you a question. When I tried to train on the DeeplabV3+ model, raise the followinng error: File "train.py", line 326, in trainer = Trainer(args) File "train.py", line 162, in init aux=args.aux, norm_layer=BatchNorm2d).to(self.device) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/model_zoo.py", line 122, in get_segmentation_model return modelsmodel File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/deeplabv3_plus.py", line 127, in get_deeplabv3_plus model = DeepLabV3Plus(datasets[dataset].NUM_CLASS, backbone=backbone, pretrained_base=pretrained_base, kwargs) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/deeplabv3_plus.py", line 38, in init self.pretrained = get_xception(pretrained=pretrained_base, output_stride=output_stride, kwargs) File "/home/xst/awesome-semantic-segmentation-pytorch-master/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/xst/awesome-semantic-segmentation-pytorch-master/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. Did you solve the problem? Could you please give me some advice? Thank you very much!

Hi! I wang to aks you a question. When I tried to train on the DeeplabV3+ model, raise the followinng error: File "train.py", line 326, in trainer = Trainer(args) File "train.py", line 162, in init aux=args.aux, norm_layer=BatchNorm2d).to(self.device) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/model_zoo.py", line 122, in get_segmentation_model return modelsmodel File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/deeplabv3_plus.py", line 127, in get_deeplabv3_plus model = DeepLabV3Plus(datasets[dataset].NUM_CLASS, backbone=backbone, pretrained_base=pretrained_base, kwargs) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/deeplabv3_plus.py", line 38, in init self.pretrained = get_xception(pretrained=pretrained_base, output_stride=output_stride, kwargs) File "/home/xst/awesome-semantic-segmentation-pytorch-master/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/xst/awesome-semantic-segmentation-pytorch-master/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. Did you solve the problem? Could you please give me some advice? Thank you very much!

Have you solved your problem? I have the same one