Image-Caption-Generator

Image-Caption-Generator copied to clipboard

i'm using a google colab. when i start !python train_val.py

Traceback (most recent call last): File "train_val.py", line 86, in verbose=1) File "/usr/local/lib/python3.6/dist-packages/keras/legacy/interfaces.py", line 91, in wrapper return func(*args, **kwargs) File "/usr/local/lib/python3.6/dist-packages/keras/engine/training.py", line 1658, in fit_generator initial_epoch=initial_epoch) File "/usr/local/lib/python3.6/dist-packages/keras/engine/training_generator.py", line 103, in fit_generator callbacks._call_begin_hook('train') File "/usr/local/lib/python3.6/dist-packages/keras/callbacks.py", line 103, in _call_begin_hook self.on_train_begin() File "/usr/local/lib/python3.6/dist-packages/keras/callbacks.py", line 219, in on_train_begin callback.on_train_begin(logs) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/callbacks.py", line 905, in on_train_begin if self.model._in_multi_worker_mode(): AttributeError: 'Model' object has no attribute '_in_multi_worker_mode'

Please make sure that you're using the right version of libraries as mentioned in the requirements section in Readme.md I think this error is due to version mismatch as Keras & Tensorflow API is constantly changing and my code was tested on Tensorflow - 1.13.1 & Keras - 2.2.4. P.S. I also used Google Colab for the project so there shouldn't be an issue provided that you have the right version of libraries.

This error arises due to the mixed usage of Keras API and tensorflow.keras API. I was able to resolve the error by changing from tensorflow.keras.callbacks import ModelCheckpoint to from keras.callbacks import ModelCheckpoint in the train_val.py file.

This error arises due to the mixed usage of Keras API and tensorflow.keras API. I was able to resolve the error by changing from tensorflow.keras.callbacks import ModelCheckpoint to from keras.callbacks import ModelCheckpoint in the train_val.py file.

In my code I used only keras. rather than tensorflow.keras. then also I am getting error:

tensorflow.python.framework.errors_impl.invalidargumenterror graph execution error

what should I do please tell me