torchfold
torchfold copied to clipboard
Tools for PyTorch
AttributeError: 'builtin_function_or_method' object has no attribute '_TensorBase'
if args not in self.cached_nodes[op]: RuntimeError: bool value of Tensor with more than one value is ambiguous This error appeared at every time. This time i run my code until...
I want to know how I can use it with dataparallel. What should I change in my code when I build my model on several gpus?
The current master won't work with pytorch 0.4: isinstance cannot test for TensorBase anymore and there are other issues discussed in the migration guide. I have migrated torchfold in this...
The SPINN example reads: for batch_idx, batch in enumerate(train_iter): opt.zero_grad() all_logits, all_labels = [], [] fold = torchfold.Fold(device=device) # TODO: incorrect logic here, the for loop goes through the entire...
In, ```python def _batch_args(self, arg_lists, values): ``` although, the following code reduces unnecessary chunking and cat for computations that involve sequential operations of the same kind, ```python if isinstance(arg[0], Fold.Node):...