search

Holmeyoung / crnn-pytorch

Pytorch implementation of CRNN (CNN + RNN + CTCLoss) for all language OCR.
MIT License
378 stars 105 forks source link

The loss was very low at the beginning #44

Open lim-0 opened 4 years ago

lim-0 commented 4 years ago

firstly,thank you for your code. I have 20000 images for training and 2000 for testing(all generate by code) when i started training the loss was always very small(e.g 0.09),can you tell me how can I deal with it.

ghost commented 4 years ago

how is the performance on the testing data? maybe training data size is too small, so that it is very easy for the network to fit?

lim-0 commented 4 years ago

how is the performance on the testing data? maybe training data size is too small, so that it is very easy for the network to fit?

thank you for your answer.The test result is good,as you say ,may be the data I generated is too esay to fit.