Keras.predict giving different results depending on how used

[TMosh]

For the community:
See also this reply in a related thread:

Does training = true in the resnet blocks break the code?

I compared the summary of the ResNet50 model that we created and the pretrained model and don’t see any difference in the number of trainable parameters. But then I took a look at the resnet50 function and noticed that it does not pass the training parameter to any of the instances of the identity block or conv block. But the definitions of those functions set training = True. So what I then did was change the definitions of those functions to set the default value of training to False. When I d…