CODEWITHSUNDEEP
pythontensorflowmachine-learningkerasdeep-learning
Brian Sukhnandan
Brian Sukhnandan

Reputation: 33

Tensorflow throwing ValueError() after making it to first epoch

I'm experiencing a "ValueError: Shapes (None, None) and (None, 8, 8, 7) are incompatible" anytime I am training my model in Tensorflow. So far:

history = model.fit(train_batches,
                    steps_per_epoch=train_steps,
                    class_weight=class_weights,
                    validation_data=validation_batches,
                    validation_steps=val_steps,
                    epochs=30,
                    verbose=1,
                    callbacks=callbacks_list
                    )

gives this stacktrace:

Traceback (most recent call last):
  File "/home/brian/Desktop/381-deep-learning/main.py", line 410, in <module>
    epochs=30
  File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 324, in new_func
    return func(*args, **kwargs)
  File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 1479, in fit_generator
    initial_epoch=initial_epoch)
  File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 66, in _method_wrapper
    return method(self, *args, **kwargs)
  File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 848, in fit
    tmp_logs = train_function(iterator)
  File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py", line 580, in __call__
    result = self._call(*args, **kwds)
  File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py", line 627, in _call
    self._initialize(args, kwds, add_initializers_to=initializers)
  File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py", line 506, in _initialize
    *args, **kwds))
  File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 2446, in _get_concrete_function_internal_garbage_collected
    graph_function, _, _ = self._maybe_define_function(args, kwargs)
  File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 2777, in _maybe_define_function
    graph_function = self._create_graph_function(args, kwargs)
  File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 2667, in _create_graph_function
    capture_by_value=self._capture_by_value),
  File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/framework/func_graph.py", line 981, in func_graph_from_py_func
    func_outputs = python_func(*func_args, **func_kwargs)
  File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py", line 441, in wrapped_fn
    return weak_wrapped_fn().__wrapped__(*args, **kwds)
  File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/framework/func_graph.py", line 968, in wrapper
    raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:

    /home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py:571 train_function  *
        outputs = self.distribute_strategy.run(
    /home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/distribute/distribute_lib.py:951 run  **
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/distribute/distribute_lib.py:2290 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/distribute/distribute_lib.py:2649 _call_for_each_replica
        return fn(*args, **kwargs)
    /home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py:533 train_step  **
        y, y_pred, sample_weight, regularization_losses=self.losses)
    /home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/compile_utils.py:205 __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    /home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/keras/losses.py:143 __call__
        losses = self.call(y_true, y_pred)
    /home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/keras/losses.py:246 call
        return self.fn(y_true, y_pred, **self._fn_kwargs)
    /home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/keras/losses.py:1527 categorical_crossentropy
        return K.categorical_crossentropy(y_true, y_pred, from_logits=from_logits)
    /home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/keras/backend.py:4561 categorical_crossentropy
        target.shape.assert_is_compatible_with(output.shape)
    /home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/framework/tensor_shape.py:1117 assert_is_compatible_with
        raise ValueError("Shapes %s and %s are incompatible" % (self, other))

    ValueError: Shapes (None, None) and (None, 8, 8, 7) are incompatible


Process finished with exit code 1

after making it to Epoch 1/30.

Here is my model definition in case anyone in wondering:

# Create Inception Res Net model as used in paper
resnet = tf.keras.applications.inception_resnet_v2.InceptionResNetV2()

print("Layers of ResNet: "+str(len(resnet.layers))) //782 layers

x = resnet.layers[-28].output

x = tf.keras.layers.Dropout(0.25)(x)

# Make a prediction layer with 7 nodes for the 7 dir in our train_dir.
predictions_layer = tf.keras.layers.Dense(7, activation='softmax')(x)

# print(resnet.input)

# inputs=resnet.input selects the input layer, outputs=predictions refers to the
# dense layer we created above.

model = tf.keras.Model(inputs=resnet.input, outputs=predictions_layer)

What I believe may be the cause of my issue is my model declaration because when I observe my model.summary() what I see is this (with all in between layers excluded of course):

Output of model.summary()

input_1 (InputLayer)            [(None, 299, 299, 3) 0       
__________________________________________________________________________________________________
dropout (Dropout)               (None, 8, 8, 192)    0           batch_normalization_195[0][0]    
__________________________________________________________________________________________________               
dense (Dense)                   (None, 8, 8, 7)      1351        dropout[0][0]                    
==================================================================================================
Total params: 47,465,959
Trainable params: 47,411,559
Non-trainable params: 54,400

I included a pastebin of my entire file in case I missed anything: https://pastebin.com/raw/E0VQ83JQ

I understand that it is expecting type (None, None) and my output layer is sent to a Dense Layer of shape (None, 8, 8, 7), but how would I do the reshaping?

Any help is appreciated, including documentation which you'd think I'd find useful on the subject.

Upvotes: 2

Views: 440

Answers (2)

Saugat Pudasaini
Saugat Pudasaini

Reputation: 21

First Convert X and Y into numpy array then convert x_train,y_train into the 'Standardscale' which coverts large values in small values

X=X.values
y=y.values

from sklearn.preprocessing import StandardScaler
scaler=StandardScaler()
X_train=scaler.fit_transform(X_train)
X_test=scaler.fit_transform(X_test)

Now apply model.fit

Upvotes: 0

sreagm
sreagm

Reputation: 378

There should be a flatten layer between output from ResNet and the Dense layer. 

# Create Inception Res Net model as used in paper

resnet = tf.keras.applications.inception_resnet_v2.InceptionResNetV2()

print("Layers of ResNet: "+str(len(resnet.layers))) //782 layers

x = resnet.layers[-28].output

x = tf.keras.layers.Dropout(0.25)(x)

### Edit here.
x = tf.keras.layers.Flatten()(x)
# Make a prediction layer with 7 nodes for the 7 dir in our train_dir.
predictions_layer = tf.keras.layers.Dense(7, activation='softmax')(x)

# print(resnet.input)

# inputs=resnet.input selects the input layer, outputs=predictions refers to the
# dense layer we created above.

model = tf.keras.Model(inputs=resnet.input, outputs=predictions_layer)

Also, make sure that train_batches is valid.

Upvotes: 2

Related Questions