Pravin Subramanian
Pravin Subramanian
@KrnTneja @mateuszkaleta I have commented the Sigmoid layer in the discriminator and used BCEwithLogitsLoss and the Adam optimizer with a learning rate =0.0001. But still the discriminator loss reaches zero...
@np-n > fixed by updating `config_file` to `cascade_mask_rcnn_hrnetv2p_w32_20e_v2.py`. and then upgrading the version of the model by running `!python /content/CascadeTabNet/Tools/upgrade_model_version.py /content/epoch_36.pth /content/new_epoch_36.pth`, and set `checkpoint_file` to `/content/new_epoch_36.pth`. Based on the...