OMR-Research / tf-end-to-end

TensorFlow code to perform end-to-end Optical Music Recognition on monophonic scores through Convolutional Recurrent Neural Networks and CTC-based training.
MIT License
136 stars 58 forks source link

I want to know the version of TensorFlow. #10

Closed temps1101 closed 3 years ago

temps1101 commented 3 years ago

I was trying your code on google colab, but when running this code below, it returns an error: code:

python ctc_predict.py -image Data/Example/000051652-1_2_1.png -model Models/semantic_model.meta -vocabulary Data/vocabulary_semantic.txt

error:

Traceback (most recent call last):
  File "ctc_predict.py", line 13, in <module>
    tf.reset_default_graph()
AttributeError: module 'tensorflow' has no attribute 'reset_default_graph'

I think this happens because TensorFlow version of google colab is too new. I want to know the version that you used.

sorry for my terrible English, I'm not really good at itπŸ™‚

htluandc2 commented 3 years ago

You can try with Tensorflow 1.15.2 or Tensorflow 1.x. The current repository is not support with new version of Tensorflow and OpenCV.

temps1101 commented 3 years ago

thank you for the advice!πŸ™