I couldn't run the code due to version compatibility issues. After some trial and error, I found out that tensorflow and dm-sonnet should be version 1. I added the requirements.txt file so that others don't have to go through that trial and error.
There was still some issues regarding Protobuf version but they go away when the code is run using a flag: PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python python i3d_tf_to_pt.py --rgb --flow
I added these two issues in the README.
I also changed .cuda() with .to(device), so that the code can be run using CPU as well.
This is my first pull request, I hope I didn't mess it up :)
I couldn't run the code due to version compatibility issues. After some trial and error, I found out that tensorflow and dm-sonnet should be version 1. I added the requirements.txt file so that others don't have to go through that trial and error.
There was still some issues regarding Protobuf version but they go away when the code is run using a flag:
PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python python i3d_tf_to_pt.py --rgb --flow
I added these two issues in the README.
I also changed
.cuda()
with.to(device)
, so that the code can be run using CPU as well.This is my first pull request, I hope I didn't mess it up :)