Running a fine-tune model for my CNN : Value Error

Question

So I am trying to use a pre-trained model on my data set to then compare it to my own cnn model. However, I see an error as soon as I try to do model. fit so much that ((None, 4, 4, 1) vs (None,)). Where is this error coming from? Am I supposed to edit the pre-tune cnn.

The model that I am using is ResNET50 with no modification except the input layer changed to 128 and there are 2 outputs.

Any help is welcome,

CODE:

history = modelB.fit_generator(train_data,
                          validation_data = test_data, 
                          epochs=5,
                          steps_per_epoch = 1714,)

ERROR:

    ---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-89-89a7f1c1eb60> in <module>()
      2                               validation_data = test_data,
      3                               epochs=5,
----> 4                               steps_per_epoch = 1714,)

2 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py in autograph_handler(*args, **kwargs)
   1145           except Exception as e:  # pylint:disable=broad-except
   1146             if hasattr(e, "ag_error_metadata"):
-> 1147               raise e.ag_error_metadata.to_exception(e)
   1148             else:
   1149               raise

ValueError: in user code:

    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1021, in train_function  *
        return step_function(self, iterator)
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1010, in step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1000, in run_step  **
        outputs = model.train_step(data)
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 860, in train_step
        loss = self.compute_loss(x, y, y_pred, sample_weight)
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 919, in compute_loss
        y, y_pred, sample_weight, regularization_losses=self.losses)
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/compile_utils.py", line 201, in __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    File "/usr/local/lib/python3.7/dist-packages/keras/losses.py", line 141, in __call__
        losses = call_fn(y_true, y_pred)
    File "/usr/local/lib/python3.7/dist-packages/keras/losses.py", line 245, in call  **
        return ag_fn(y_true, y_pred, **self._fn_kwargs)
    File "/usr/local/lib/python3.7/dist-packages/keras/losses.py", line 1932, in binary_crossentropy
        backend.binary_crossentropy(y_true, y_pred, from_logits=from_logits),
    File "/usr/local/lib/python3.7/dist-packages/keras/backend.py", line 5247, in binary_crossentropy
        return tf.nn.sigmoid_cross_entropy_with_logits(labels=target, logits=output)

    ValueError: `logits` and `labels` must have the same shape, received ((None, 4, 4, 1) vs (None,)).

Answer 1

The Issue is with the loss function used when you compile the model.

Replace the compile with below code:

model.compile(optimizer='adam',loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), metrics=['accuracy'])

Answer 2

Use tf.keras.utils.plot_model to print out a graphic representation of the model. you have a mismatch between the number of input and output nodes.

Answer 3

Replace the loss function in compile with SparseCategoricalCrossentropy then you can rectify the error.

model.compile(optimizer='adam',loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), metrics=['accuracy'])