Belval / CRNN

A TensorFlow implementation of https://github.com/bgshih/crnn
MIT License
297 stars 101 forks source link

Why the output is the same when using the pretrained model for prediction? #69

Open Timthony opened 4 years ago

Timthony commented 4 years ago

Output: Use standard file APIs to check for files with this prefix. Loading data Testing beignet iiiii apocynaceous iiiii arshine iiiii

Why is the output always "iiiiii"? I have confirmed that the inputs are different. Preliminary judgment is a problem with tensorflow environment or api, but no solution is found?