RuntimeError(2): element 0 of tensors does not require grad and does not have a grad_fn

1

Kindly assist to find out why I am still this error message: “RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn”

My section of code I am running is:

model.zero_grad()
log_probs = model(images)
loss = self.criterion(log_probs, labels)

            loss.backward()
            optimizer.step()
1 Like
2

log_probs might be detached from the computation graph. Check, if it’s .grad_fn attribute is pointing to a valid function or None (detached). In the latter case, print the .grad_fn attribute of the intermediate tensors in your model’s forward method to check which operation detaches the tensor from the computation graph. Often this is done by e.g. rewrapping a tensor via x = torch.tensor(x), using another library such as numpy, explicitly calling tensor.detach() etc.

3

Hello everyone,

I’m facing the below mentioned run-time error:

RuntimeError                              Traceback (most recent call last)
<ipython-input-98-7b6b8391c42e> in <cell line: 1>()
----> 1 trainer.fit(model, data_module)

29 frames
/usr/local/lib/python3.10/dist-packages/torch/autograd/__init__.py in backward(tensors, grad_tensors, retain_graph, create_graph, grad_variables, inputs)
    198     # some Python versions print out the first line of a multi-line function
    199     # calls in the traceback and some print out the last line
--> 200     Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
    201         tensors, grad_tensors_, retain_graph, create_graph, inputs,
    202         allow_unreachable=True, accumulate_grad=True)  # Calls into the C++ engine to run the backward pass

RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

I also have mentioned here my Collaboratory, please let me know incase you can not access the file.

Support from you will be appreciated, Thank you:)