LPRNet_Pytorch Custom Training

Custom Training

Open fadi212 opened this issue 4 years ago • 8 comments

How can we train on custom data and can we train the same model on Number Plates with multiple lines like two or three

Aug 21 '19 11:08 fadi212

if it is not chinese license plate and license plate lenth equal to 8, you should delete check(label) funtcion in LPRDataLoader.getitem;
you should modify the list of CHARS base on your license plate characters, and the filename of train/test images should be its label character;
T_length should be bigger or equal than twice max license plate lenth;
our model not support multiple lines at currenct, maybe you can merge multiple lines into one line.

Aug 21 '19 11:08 sirius-ai

2 'targets' to have scalar type Int; but got torch.cuda.FloatTensor instead (while checking arguments for ctc_loss_gpu)

Dec 26 '19 10:12 2017TJM

@2017TJM please let me know how to reproduce this issue, thanks!

Jan 09 '20 06:01 sirius-ai

Hi , im getting below error while train when i change T_length = 24, since my dataset include Indian License Plate , with single and double line license plate.

File "LPRNet_Train.py", line 94, in loss = ctc_loss(log_probs, labels, input_lengths=input_lengths, target_lengths=target_lengths) File "/home/arohi/Gunjan/Python Programming/venv/lib/python3.5/site-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(*input, **kwargs) File "/home/arohi/Gunjan/Python Programming/venv/lib/python3.5/site-packages/torch/nn/modules/loss.py", line 1295, in forward self.zero_infinity) File "/home/arohi/Gunjan/Python Programming/venv/lib/python3.5/site-packages/torch/nn/functional.py", line 1781, in ctc_loss zero_infinity) RuntimeError: Expected input_lengths to have value at most 18, but got value 24 (while checking arguments for ctc_loss_cpu)

MH02AS8015 MH02CB5249