alpr-unconstrained
alpr-unconstrained copied to clipboard
sergiomsilva
how to train OCR model?
Hi @linzhi123 , sorry but we do not plan to publish this part anytime soon.
@sergiomsilva Aren't you just using Darknet for OCR? If so, OCR can be trained separately using yolo, am i correct?
Yeah, I just want to train OCR alone. There's no training code. Yolo's training code is official, and his training code is modified. @danishansari
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 it showing good IOU(0.7) and Recall(0.96). Still working on it, haven't verified the result till now.
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 you can directly use Darknet for training and inference.
@linzhi123 please do share your experience and results(accuracy/map) after training.
I see you are interested in the training script, and I am sorry for not being able to share it with you guys at this moment because I'm really out of time. However I can give you some hints. The only modification we did in the original YOLO training algorithm was considering its data augmentation process. Basically, it reduces too much the image size, which is undesirable in this case, so we controlled it by performing small changes in the source code. We also included synthetically created data, as mentioned in the paper, but you may also achieve nice results without them.
@sergiomsilva then those modification about augmentation and controlling size reduction must be there in the darknet code in your repository?
32/5000
I want to ask how to use OCR training license plate data alone, I tried, but not so good @linzhi123
@linzhi123 hello, how do you train the ocr? And how do you prepare the dataset ?
I want to know how to train ocr too. and could we change the code for two layer plate recognition?
ok，I use tesseract4.0，and you？
could you share the details of how you used tesseract4.0? When I tried I get the error saying DPI information not present in the image.
I want to know how to train ocr too. and could we change the code for two layer plate recognition?
yes. I wish to train it for plate with 2 rows
