Do you have match-table of network and backbone??

[edwardcho]

Hello Sir,

I was tested your code using my data (image resolution : 256).
But I could not train many cases.

(unfortunately, I could not train all backbone of DFANet, PSPNet, ICNet)

If you don't mind, please tell me trainable networks and matched backbone.

Thanks.

[edwardcho]

Hello Sir,

In many cases,
I got some error.

2020-04-16 02:49:10,095 Segmentron WARNING: get flops and params error: Given groups=1, weight of size 128 512 1 1, expected input[1, 2048, 1, 1] to have 512 channels, but got 2048 channels instead
2020-04-16 02:49:10,096 Segmentron INFO: Not use SyncBatchNorm!
2020-04-16 02:49:10,098 Segmentron INFO: Start training, Total Epochs: 1 = Total Iterations 367
Traceback (most recent call last):
File "tools/train.py", line 332, in
trainer.train()
File "tools/train.py", line 135, in train
outputs = self.model(images)
File "/home/itsme/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in call
result = self.forward(*input, **kwargs)
File "/data/TESTBOARD/additional_networks/segmentation/semantic_segmentation_likelyjourney_pytorch_modify/segmentron/models/bisenet.py", line 36, in forward
spatial_out = self.spatial_path(x)
File "/home/itsme/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in call
result = self.forward(*input, **kwargs)
File "/data/TESTBOARD/additional_networks/segmentation/semantic_segmentation_likelyjourney_pytorch_modify/segmentron/models/bisenet.py", line 81, in forward
x = self.conv7x7(x)
File "/home/itsme/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in call
result = self.forward(*input, **kwargs)
File "/data/TESTBOARD/additional_networks/segmentation/semantic_segmentation_likelyjourney_pytorch_modify/segmentron/modules/basic.py", line 75, in forward
x = self.bn(x)
File "/home/itsme/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 549, in call
hook_result = hook(self, input, result)
File "/home/itsme/anaconda3/lib/python3.7/site-packages/thop/vision/basic_hooks.py", line 49, in count_bn
m.total_ops += torch.DoubleTensor([int(total_ops)])
UnboundLocalError: local variable 'total_ops' referenced before assignment

I wonder what is the problems??

Thanks.