Keras Debugging, forward pass

kjewqr123 · January 27, 2023, 2:52am

How do I set a break point in the keras model?

I am talking about this one. Can I set a break point on the forward pass of the model. If yes, where?

keras-team/keras-applications/blob/master/keras_applications/efficientnet.py#L407

      
        
                        file_hash = WEIGHTS_HASHES[model_name[-2:]][1]
                    file_name = model_name + file_suff
                    weights_path = keras_utils.get_file(file_name,
                                                        BASE_WEIGHTS_PATH + file_name,
                                                        cache_subdir='models',
                                                        file_hash=file_hash)
                    model.load_weights(weights_path)
                elif weights is not None:
                    model.load_weights(weights)
            
            
    return model
            
            

            
def EfficientNetB0(include_top=True,
                               weights='imagenet',
                               input_tensor=None,
                               input_shape=None,
                               pooling=None,
                               classes=1000,
                               **kwargs):
                return EfficientNet(1.0, 1.0, 224, 0.2,

Renu_Patel · September 8, 2023, 6:47pm

Hi @kjewqr123

Welcome to the TensorFlow Forum!

You can try using Tensorflow Callbacks for the same task. There are multiple default callbacks available to use as per your requirements. You can also customize the callbacks with its available methods eg. on_batch_begin(), on_epoch_begin() with some conditions to perform accordingly.

Please refer to the mentioned links for more details.