One-Shot-Object-Detection
One-Shot-Object-Detection copied to clipboard
Fix bug: RuntimeError: set_sizes_contiguous is not allowed on Tensor …
When i tried your source with newer version of pytorch (1.4) the following error happened.
Traceback (most recent call last):
File "test_net.py", line 276, in <module>
im_data.data.resize_(data[0].size()).copy_(data[0])
RuntimeError: set_sizes_contiguous is not allowed on a Tensor created from .data or .detach().
If your intent is to change the metadata of a Tensor (such as sizes / strides / storage / storage_offset)
without autograd tracking the change, remove the .data / .detach() call and wrap the change in a `with torch.no_grad():` block.
For example, change:
x.data.set_(y)
to:
with torch.no_grad():
x.set_(y)
So i add a pr to fix it.