Hello author, when I run train.py, it appears
File "LipReadingGUI-master/Training/lipnet/callbacks.py", line 86, in on_epoch_end
"{0:.5f}".format(stats['bleu'][0]), "{0:.5f}".format(stats['bleu'][1])])
TypeError: a bytes-like object is required, not 'str'
I am using python 3.6, how to solve this situation?

There are a lot of errors and issues while installing all the dependencies as many of them are outdated

So can you please provide requirements.txt for this project?

And if you have a container image of this project can you please share it on dockerhub

Thank you

Hello. I get this error while running the GUI.py. Kindly let me know how to solve this. Thankyou

Exception in Tkinter callback
Traceback (most recent call last):
File "C:\Users\pedne\anaconda3\lib\tkinter_init_.py", line 1883, in call
return self.func(*args)
File "C:\Users\pedne\Desktop\onkar\Upwork\LipReadingGUI-master\PredictGUI\GUI.py", line 50, in caption
video, result = predict(WEIGHTS_PATH, VIDEO_PATH)
File "C:\Users\pedne\Desktop\onkar\Upwork\LipReadingGUI-master\PredictGUI\predict.py", line 59, in predict
y_pred = lipnet.predict(X_data)
File "C:\Users\pedne\Desktop\onkar\Upwork\LipReadingGUI-master\PredictGUI..\Training\lipnet\model.py", line 74, in predict
return self.test_function([input_batch])[0] # the first 0 indicates test
File "C:\Users\pedne\Desktop\onkar\Upwork\LipReadingGUI-master\PredictGUI..\Training\lipnet\model.py", line 79, in test_function
return K.function([self.input_data, K.learning_phase()], [self.y_pred, K.learning_phase()])
File "C:\Users\pedne\anaconda3\lib\site-packages\keras\backend.py", line 4062, in function
model = models.Model(inputs=inputs, outputs=outputs)
File "C:\Users\pedne\anaconda3\lib\site-packages\tensorflow\python\training\tracking\base.py", line 522, in _method_wrapper
result = method(self, *args, **kwargs)
File "C:\Users\pedne\anaconda3\lib\site-packages\keras\engine\functional.py", line 110, in init
self._init_graph_network(inputs, outputs)
File "C:\Users\pedne\anaconda3\lib\site-packages\tensorflow\python\training\tracking\base.py", line 522, in _method_wrapper
result = method(self, *args, **kwargs)
File "C:\Users\pedne\anaconda3\lib\site-packages\keras\engine\functional.py", line 147, in _init_graph_network
self._validate_graph_inputs_and_outputs()
File "C:\Users\pedne\anaconda3\lib\site-packages\keras\engine\functional.py", line 683, in _validate_graph_inputs_and_outputs
raise ValueError('Input tensors to a ' + cls_name + ' ' +
ValueError: Input tensors to a Functional must come from tf.keras.Input. Received: 0 (missing previous layer metadata).