ValueError：数据基数与 tf.keras 不明确

Question

I have a dataframe with two columns; the first includes a sentence and the second is a target label (9 in total - sentence can be classified to more than one label).

I have used word2vec to vectorise the text and thats resulted in an array with length 64.

The initial problem I had

Tensorflow - ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type float)

To overcome this I have converted the np.array to

train_inputs = tf.convert_to_tensor([df_train_title_train])

But now I am getting a new problem - see below.

I have been researching stackflow and other sources for days and am struggling to get my simple neural network to work.

print(train_inputs.shape)
print(train_targets.shape)
print(validation_inputs.shape)
print(validation_targets.shape)
print(train_inputs[0].shape)
print(train_targets[0].shape)

(1, 63586, 64)
(63586, 9)
(1, 7066, 64)
(7066, 9)
(63586, 64)
(9,)



# Set the input and output sizes
input_size = 64
output_size = 9
# Use same hidden layer size for both hidden layers. Not a necessity.
hidden_layer_size = 64

# define how the model will look like
model = tf.keras.Sequential([
    tf.keras.layers.Dense(hidden_layer_size, activation='relu'), # 1st hidden layer
    tf.keras.layers.Dense(hidden_layer_size, activation='relu'), # 2nd hidden layer
    tf.keras.layers.Dense(hidden_layer_size, activation='relu'), # 2nd hidden layer
    tf.keras.layers.Dense(output_size, activation='softmax') # output layer
])


# model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])


### Training
# That's where we train the model we have built.

# set the batch size
batch_size = 10

# set a maximum number of training epochs
max_epochs = 10


# fit the model
# note that this time the train, validation and test data are not iterable
model.fit(train_inputs, # train inputs
          train_targets, # train targets
          batch_size=batch_size, # batch size
          epochs=max_epochs, # epochs that we will train for (assuming early stopping doesn't kick in)
          validation_data=(validation_inputs, validation_targets), # validation data
          verbose = 2 # making sure we get enough information about the training process
          )  

Error Message

/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/data_adapter.py in _check_data_cardinality(data)
   1527           label, ", ".join(str(i.shape[0]) for i in nest.flatten(single_data)))
   1528     msg += "Make sure all arrays contain the same number of samples."
-> 1529     raise ValueError(msg)
   1530 
   1531 

ValueError: Data cardinality is ambiguous:
  x sizes: 1
  y sizes: 63586
Make sure all arrays contain the same number of samples.

Answer 1

You do not set the shape of your input anywhere; you should do this either with an explicit Input layer in the beginning of your model (see the example in the docs ):

# before the first Dense layer:
tf.keras.Input(shape=(64,))

or by including an input_shape argument in your first layer:

tf.keras.layers.Dense(hidden_layer_size, activation='relu', input_shape=(64,)), # 1st hidden layer

Most probably, you will not even need convert_to_tensor (not quite sure though).

Also, irrelevant to your issue, but since you are in a multi-class setting, you should use loss='categorical_crossentropy' , and not binary_crossentropy ; see Why binary_crossentropy and categorical_crossentropy give different performances for the same problem?