File name of training images about crnn-pytorch

[Holmeyoung]

Hi, it doesn’t matter.

1. You really need more data, maybe 100000 sample for 1000 classes.

2. But even 100 samples should print loss either. Change the batchSize in params.py to 1 and see what will happen. If there is still nothing printed, it’s not the sample problem.

[Holmeyoung]

Hi, check the file size of your lmdb file. I guess you didn’t access the image successfully. The txt file should looks like

absolute/path/to/your/image/1.jpg
المفضل

If there are still problems, you can tell me.

[niddal-imam]

I checked the lmdv files and they are 100 KB and 9 KB for training and 70 KB and 8 KB for val. They are small because I am using small data (100 sample). My txt files look like your example.

/Volumes/EXTERNAL/Models/crnn_pytorch-master/to_lmdb/val_images/img_almofdalh_11.jpg
المفضل

[Holmeyoung]

Hi, check the following params in params.py

# training process
displayInterval = 100 # interval to be print the train loss
valInterval = 1000 # interval to val the model loss and accuray
saveInterval = 1000 # interval to save model
n_test_disp = 10 # number of samples to display when val the model

Look at the comment and you will know the reason is that your training sample amount didn’t reach the displayInterval valInterval...so change them smaller, for example 100%64=1 is ok for you(64 is the batch size)

[niddal-imam]

Thank you for your reply, and sorry for asking so many question. I made the changes that you suggest, but still does not print the loss. It just run for 15 - 20 mins and stop. I may need more data, right?

[niddal-imam]

I changed the batchSize, and it start printing.

Thanks