Fully trained model
gan3sh500 opened this issue · comments
Ganesh Anand commented
Can you update the model in the repo. It says the demo model is not the accurate one used to generate results in the paper.
Denis Tome' commented
Yes, this is not the model used in the paper, as well as the architecture is slightly different.
The reason is that we ported the model from a different framework (we used to use caffe).
Denis Tome' commented
Closing the issue