tensorflow_CTC_example icon indicating copy to clipboard operation
tensorflow_CTC_example copied to clipboard

Published 20 hours ago • verified publisher icon jonrein

Training images

Open joyJZhang opened this issue 8 years ago • 2 comments

hello,i used your model to train myself captcha images,but the loss is always 14,and don't convergence。Can you show me your training images?or tell me how to see them .I want to know whether my pictures are too complicated。Thanks.

joyJZhang avatar Nov 18 '16 09:11 joyJZhang

The inputs in the example code are processed features from speech waveforms, not images. If you're trying to use this type of model structure with image data, you'll likely need a few more layers, with possibly a mix of convolution and LSTM layers.

jonrein avatar Nov 18 '16 15:11 jonrein

Hello, can you specify how to prepair input and output for OCR like tasks?

Related: https://github.com/igormq/ctc_tensorflow_example/issues/20

mrgloom avatar Sep 01 '17 13:09 mrgloom