Danish Ansari

@sergiomsilva Aren't you just using Darknet for OCR? If so, OCR can be trained separately using yolo, am i correct?

Yes i am training it using YOLO-v2 with the same network and weights that is there in this repository. I am not able to get the loss reduced much, otherwise...

I used YOLO-v2 itself, did not modified any of the code. I am just training for 36 classes instead of 35. So only config file has to be modified. So...

@linzhi123 please do share your experience and results(accuracy/map) after training.

@sergiomsilva then those modification about augmentation and controlling size reduction must be there in the darknet code in your repository?

@linzhi123 are you using actual images or synthetically generated? I started training it on synthetic data, the accuracy on val and test data is about 99% but on real data...

I think all should be labeled correctly, and it should work fine.

@qjadud1994 How would you recommend fine-tuning, should we use differential learning rates, i.e. lower lr for CNN and higher for RNN? Or a global lower learning rate like 1e-3 or...