Jean-Paul Ainam
Jean-Paul Ainam
@chenxiangzZ Yes, the command for training PCB baseline is valid. It worked for me with the following results ```python ##### Evaluating market1501 (source) ##### Extracting features from query set ......
@kmcgill88 check PR #142
Hi, @Abdullah-Zakhoi this happens because showEnglishName has no default value, you can check this pull request where it's You can now create your own appBar instead of using the default,...
Hi @dev-fema You can check this pull request #24 that solve the above problem. You can now create your own appBar instead of using the default, you can also change...
Is t here any update for this issue? @rwieruch How did you solve it? Thanks
ImportError: torch.utils.ffi is deprecated. Please use cpp extensions instead.
Thank you. I was able to generate GradCAM for `model_base` using [https://github.com/1Konny/gradcam_plus_plus-pytorch](this link). For `model_gaze`, `register_backward_hook` doesn't fire. But `register_forward_hook` does. So, I don't have the `gradients['value']` Is there any...
Ok thank. you train three differents network, (I3D, I3D w/ gaze and I3D w/ gaze and attention). You visualize the output of `Mixed_5c` for each network.
sorry, i removed the checkpoints tjhat were previously uploaded. You can train afresh using ``` mkdir data ln -rs your_dataset_path/market1501/bounding_box_train ./market_train // Train with the all training set python main.py...