CODEWITHSUNDEEP
python-3.xtensorflowmachine-learningkerasdeep-learning
ah bon
ah bon

Reputation: 10011

ValueError: Shapes (32, 5, 5) and (32, 2) are incompatible

I have the following data:

   overall   reviewTime reviewerID  \
0        4  08 24, 2010  u04428712   
1        5  10 31, 2009  u06946603   
2        4  10 13, 2015  u92735614   
3        5  06 28, 2017  u35112935   
4        4  10 12, 2015  u07141505   

                                          reviewText  \
0  So is Katy Perry's new album "Teenage Dream" c...   
1  I got this CD almost 10 years ago, and given t...   
2  I REALLY enjoy this pairing of Anderson and Po...   
3  Finally got it . It was everything thought it ...   
4  Look at all star cast.  Outstanding record, pl...   

                                             summary  unixReviewTime  \
0  Amazing that I Actually Bought This...More Ama...      1282608000   
1                                    Excellent album      1256947200   
2                Love the Music, Hate the Light Show      1444694400   
3                                              Great      1498608000   
4                                   Love these guys.      1444608000   

           category   price     itemID  reviewHash image  
0               Pop  $35.93  p70761125    85559980   NaN  
1  Alternative Rock  $11.28  p85427891    41699565   NaN  
2               Pop  $89.86  p82172532    24751194   NaN  
3               Pop  $11.89  p15255251    22820631   NaN  
4              Jazz  $15.24  p82618188    53377470   NaN  
Index(['overall', 'reviewTime', 'reviewerID', 'reviewText', 'summary',
       'unixReviewTime', 'category', 'price', 'itemID', 'reviewHash', 'image'],
      dtype='object')
(200000, 11)

and shape of data:

X train shape  (160000, 100)
X test shape  (40000, 100)
y train shape  (160000, 5)
y test shape  (40000, 5)

Code for modelling:

# Add sequential model
model = Sequential()
# Add embedding layer 
# No of output dimenstions is 100 as we embedded with Glove 100d
Embed_Layer = Embedding(vocab_size, 100, weights=[embedding_matrix], input_length=(MAX_SEQUENCE_LENGTH,), trainable=True)
#define Inputs
review_input = Input(shape=(MAX_SEQUENCE_LENGTH,), dtype= 'int32', name = 'review_input')
review_embedding = Embed_Layer(review_input)
Flatten_Layer = Flatten()
review_flatten = Flatten_Layer(review_embedding)
output_size = 2

dense1 = Dense(100,activation='relu')(review_flatten)
dense2 = Dense(32,activation='relu')(dense1)
predict = Dense(2,activation='softmax')(dense2)

model = Model(inputs=[review_input],outputs=[predict])
model.compile(optimizer='adam',loss='categorical_crossentropy',metrics=['acc'])
print(model.summary())

Out:

Model: "functional_33"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
review_input (InputLayer)    [(None, 100)]             0         
_________________________________________________________________
embedding_17 (Embedding)     (None, 100, 100)          22228800  
_________________________________________________________________
flatten_17 (Flatten)         (None, 10000)             0         
_________________________________________________________________
dense_48 (Dense)             (None, 100)               1000100   
_________________________________________________________________
dense_49 (Dense)             (None, 32)                3232      
_________________________________________________________________
dense_50 (Dense)             (None, 2)                 66        
=================================================================
Total params: 23,232,198
Trainable params: 23,232,198
Non-trainable params: 0
_________________________________________________________________
None

After y_train = tf.one_hot(y_train, 5), then during the fitting of the model using model.fit(X_train, y_train, epochs= 5, batch_size=32, verbose=True, validation_data=(X_test, y_test)), the following error occurs:

ValueError: in user code:

    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:806 train_function  *
        return step_function(self, iterator)
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:796 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:1211 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:2585 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:2945 _call_for_each_replica
        return fn(*args, **kwargs)
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:789 run_step  **
        outputs = model.train_step(data)
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:748 train_step
        loss = self.compiled_loss(
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/compile_utils.py:204 __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/keras/losses.py:149 __call__
        losses = ag_call(y_true, y_pred)
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/keras/losses.py:253 call  **
        return ag_fn(y_true, y_pred, **self._fn_kwargs)
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/util/dispatch.py:201 wrapper
        return target(*args, **kwargs)
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/keras/losses.py:1535 categorical_crossentropy
        return K.categorical_crossentropy(y_true, y_pred, from_logits=from_logits)
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/util/dispatch.py:201 wrapper
        return target(*args, **kwargs)
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/keras/backend.py:4687 categorical_crossentropy
        target.shape.assert_is_compatible_with(output.shape)
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/framework/tensor_shape.py:1134 assert_is_compatible_with
        raise ValueError("Shapes %s and %s are incompatible" % (self, other))

    ValueError: Shapes (32, 5, 5) and (32, 2) are incompatible

Can someone assists with an idea of how to solve that?

Upvotes: 0

Views: 707

Answers (2)

Sunny
Sunny

Reputation: 302

If you are trying to classify between 5 classes you shoud use 5 nodes in the last dense layer:

predict = Dense(5,activation='softmax')(dense2)

Upvotes: 1

Andrey
Andrey

Reputation: 6367

The model output shape is (None, 2). Try:

y_train = tf.one_hot(y_train, 2)

Upvotes: 1

Related Questions