mg2033 / mobilenet-v2 Goto Github PK

I try the code and get the runtime error down,any idea?

Training...
Epoch-0-: 0%| | 0/391 [00:00<?, ?it/s]Traceback (most recent call last):
File "main.py", line 46, in
main()
File "main.py", line 34, in main
trainer.train()
File "/home/qiaokang/MobileNet-V2-master/train.py", line 63, in train
cur_loss.backward()
File "/usr/local/lib/python3.5/dist-packages/torch/tensor.py", line 93, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "/usr/local/lib/python3.5/dist-packages/torch/autograd/init.py", line 89, in backward
allow_unreachable=True) # allow_unreachable flag
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation

Hello and thanks for the contribution.
Would it be possible to have the decoder part for semantic segmentation purposes?

After fixing the 'inplace' operation issue, code got stuck at curloss.backward() by giving the mentioned error:
"'float' object has no attribute 'backward'".
Please help me correctly executing the code.

This is quite bad code style, you need to provide more information.
e.g. it will catch errors if the config file doesn't exist or if the config file can't be processed.

I wonder if you provide with pretrained weight on ImageNet?Just give me a link wound bee better.And more,it's the first time I see that weight is saved by rar,it;s some difficult for me to use it,could you write more about how to test a classcification by an image?

Thanks for this implementation.
When I execute this on my PC I find the error as [RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation], which initiates from util file >>cur_loss.backward() from line 65.
Please look into it and help me out.