Kongsea
Kongsea
Besides, I have changed the learning rate to 1e-5 or even small, but it still didn't work.
Thank you. Now it works well.
It raised this error again even after I set the LR to 0.00005. Please help to check the reason. Thank you.
Besides, during training, the fast_rcnn_loc_loss is a constant: 0.0 @yangxue0827
I changed ANCHOR_SCALES from [1.] to [2**-2, 2**-1, 1.], now it works. However, the fast_rcnn_loc_loss is still always be 0.0 after 10k iterations of training. Does it make sense?
I have finally trained the model successfully. The losses of the model are finally reduced to a normal level and the detection results using the final model are also good....
Thank you for your rapid answer.
As I mentioned above, I have changed ANCHOR_SCALES. You can have a try. Besides, you should carefully check your data. Maybe the error was caused by your data. For example,...
If the images are not square, can CycleGAN process it? How to modify the code? Thank you.