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

aux #81

Open tomjerrygithub opened 4 years ago

tomjerrygithub commented 4 years ago

deeplabv3plus demo
Missing key(s) in state_dict: "auxlayer.block.0.weight", "auxlayer.block.1.weight", "auxlayer.block.1.bias", "auxlayer.block.1.running_mean", "auxlayer.block.1.running_var", "auxlayer.block.4.weight", "auxlayer.block.4.bias".

When i set aux =False is Ok What the aux mean?

sainatarajan commented 4 years ago

Are you trying to load a different backbone file? I got a similar error when I tried to load a different xception model file while trying to run deeplabv3plus.

tomjerrygithub commented 4 years ago

The same, i use the resnet101 now.

At 2019-10-13 01:49:11, "sainatarajan" notifications@github.com wrote:

Are you trying to load a different backbone file? I got a similar error when I tried to load a different xception model file while trying to run deeplabv3plus.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

JessonKang commented 4 years ago

deeplabv3plus demo Missing key(s) in state_dict: "auxlayer.block.0.weight", "auxlayer.block.1.weight", "auxlayer.block.1.bias", "auxlayer.block.1.running_mean", "auxlayer.block.1.running_var", "auxlayer.block.4.weight", "auxlayer.block.4.bias".

When i set aux =False is Ok What the aux mean?

Hi,Can you tell me where to set “aux = False”? thks

Tramac commented 4 years ago

deeplabv3plus demo Missing key(s) in state_dict: "auxlayer.block.0.weight", "auxlayer.block.1.weight", "auxlayer.block.1.bias", "auxlayer.block.1.running_mean", "auxlayer.block.1.running_var", "auxlayer.block.4.weight", "auxlayer.block.4.bias". When i set aux =False is Ok What the aux mean?

Hi,Can you tell me where to set “aux = False”? thks

Can be set here.

JessonKang commented 4 years ago

deeplabv3plus demo Missing key(s) in state_dict: "auxlayer.block.0.weight", "auxlayer.block.1.weight", "auxlayer.block.1.bias", "auxlayer.block.1.running_mean", "auxlayer.block.1.running_var", "auxlayer.block.4.weight", "auxlayer.block.4.bias". When i set aux =False is Ok What the aux mean?

Hi,Can you tell me where to set “aux = False”? thks

Can be set here.

Thank you very much for your reply. I checked and found it was “aux = False”, so what else could possibly lead to such a mistake?

Tramac commented 4 years ago

If you use the deeplab, maybe you can check here.

JessonKang commented 4 years ago

If you use the deeplab, maybe you can check here.

I used fcn +resnet50 train the model and called fcnv2.py when running demo.py, but I found no place to set "aux" in fcnv2.py.

Tramac commented 4 years ago

If you use the deeplab, maybe you can check here.

I used fcn +resnet50 train the model and called fcnv2.py when running demo.py, but I found no place to set "aux" in fcnv2.py.

Please check self.aux in fcnv2.py is true or false.

JessonKang commented 4 years ago

If you use the deeplab, maybe you can check here.

I used fcn +resnet50 train the model and called fcnv2.py when running demo.py, but I found no place to set "aux" in fcnv2.py.

Please check self.aux in fcnv2.py is true or false. 47/5000 I found and modified self.aux=Flase in fcnv2.py, and demo. py can run normally, thank you very very much!