可视化图形时的Tensorboard尺寸错误

如何解决可视化图形时的Tensorboard尺寸错误

我正在尝试在我的项目中使用add_graph（）函数。 我运行了这个repo (iUnet)

的修改后的代码

The iUnet model is the same like this,just for 2D

I got the code of the pytorch-docus running fine

如果您需要更多信息，请告诉我什么

Python 3.7.7， 火炬1.5.1， tensorboard 2.3.0，

y_forGraph = torch.randn(1,4,512,512)
print("this is the shape of y_forGraph",y_forGraph.shape)
writer.add_graph(iunet,y_forGraph)

感谢帮助

this is the shape of y_forGraph torch.Size([1,512])
Given groups=1,weight of size [4,3,3],expected input[1,512] to have 4 channels,but got 0 channels instead
Error occurs,No graph saved
Traceback (most recent call last):
  File "lud_train_loop_n.py",line 589,in <module>
    writer.add_graph(iunet,(y_forGraph,))
  File "/home/lud/anaconda3/envs/unet_torch_env/lib/python3.7/site-packages/torch/utils/tensorboard/writer.py",line 707,in add_graph
    self._get_file_writer().add_graph(graph(model,input_to_model,verbose))
  File "/home/lud/anaconda3/envs/unet_torch_env/lib/python3.7/site-packages/torch/utils/tensorboard/_pytorch_graph.py",line 291,in graph
    raise e
  File "/home/lud/anaconda3/envs/unet_torch_env/lib/python3.7/site-packages/torch/utils/tensorboard/_pytorch_graph.py",line 285,in graph
    trace = torch.jit.trace(model,args)
  File "/home/lud/anaconda3/envs/unet_torch_env/lib/python3.7/site-packages/torch/jit/__init__.py",line 875,in trace
    check_tolerance,_force_outplace,_module_class)
  File "/home/lud/anaconda3/envs/unet_torch_env/lib/python3.7/site-packages/torch/jit/__init__.py",line 1027,in trace_module
    module._c._create_method_from_trace(method_name,func,example_inputs,var_lookup_fn,_force_outplace)
  File "/home/lud/anaconda3/envs/unet_torch_env/lib/python3.7/site-packages/torch/nn/modules/module.py",line 548,in __call__
    result = self._slow_forward(*input,**kwargs)
  File "/home/lud/anaconda3/envs/unet_torch_env/lib/python3.7/site-packages/torch/nn/modules/module.py",line 534,in _slow_forward
    result = self.forward(*input,**kwargs)
  File "/home/lud/Dokumente/BA/UNET/iunets/networks.py",line 188,in forward
    x = self.module_L[i][j](x)
  File "/home/lud/anaconda3/envs/unet_torch_env/lib/python3.7/site-packages/torch/nn/modules/module.py",**kwargs)
  File "/home/lud/anaconda3/envs/unet_torch_env/lib/python3.7/site-packages/memcnn/models/revop.py",line 201,in forward
    *(xin + tuple([p for p in self._fn.parameters() if p.requires_grad])))
  File "/home/lud/anaconda3/envs/unet_torch_env/lib/python3.7/site-packages/memcnn/models/revop.py",line 40,in forward
    outputs = ctx.fn(*x)
  File "/home/lud/Dokumente/BA/UNET/iunets/layers.py",line 550,in forward
    y2 = x1 + self.F.forward(x2)
  File "/home/lud/Dokumente/BA/UNET/iunets/layers.py",line 637,in forward
    return self.F(x)
  File "/home/lud/anaconda3/envs/unet_torch_env/lib/python3.7/site-packages/torch/nn/modules/module.py",**kwargs)
  File "/home/lud/anaconda3/envs/unet_torch_env/lib/python3.7/site-packages/torch/nn/modules/container.py",line 100,in forward
    input = module(input)
  File "/home/lud/anaconda3/envs/unet_torch_env/lib/python3.7/site-packages/torch/nn/modules/module.py",**kwargs)
  File "/home/lud/anaconda3/envs/unet_torch_env/lib/python3.7/site-packages/torch/nn/modules/conv.py",line 353,in forward
    return self._conv_forward(input,self.weight)
  File "/home/lud/anaconda3/envs/unet_torch_env/lib/python3.7/site-packages/torch/nn/modules/conv.py",line 350,in _conv_forward
    self.padding,self.dilation,self.groups)
RuntimeError: Given groups=1,but got 0 channels instead