Error when checking input: expected dense_1_input to have 2 dimensions, but got array with shape (25000, 700, 50)

Question

trainData.shape = (25000, 700, 50) , Shape as follows:

[[[ 0.7095   0.863    0.712   ...  0.02715 -1.305    0.5195 ]
  [-0.66     1.715   -1.934   ...  0.5684   0.754    0.2593 ]
  [-0.3533   2.256   -1.292   ... -0.2708   0.6714  -1.128  ]
  ...
  [ 0.       0.       0.      ...  0.       0.       0.     ]
  [ 0.       0.       0.      ...  0.       0.       0.     ]
  [ 0.       0.       0.      ...  0.       0.       0.     ]]
  ...

trainLabel.shape = (25000,) , , Shape as follows:

[1. 1. 1. ... 0. 0. 0.]

Using them to train MLP models, How should I reshape trainData and trainLabel ? The detailed code is as follows:

def MySimpleMLP(feature=700, vec_size=50):
    auc_roc = LSTM.as_keras_metric(tf.compat.v1.metrics.auc)

    model = Sequential()

    model.add(Dense(32, activation='relu', input_shape=(feature * vec_size,)))
    model.add(Dropout(0.2))
    model.add(Dense(32, activation='relu'))
    model.add(Dropout(0.2))
    model.add(Dense(1, activation='softmax'))

    model.compile(loss="binary_crossentropy", optimizer="adam", metrics=[auc_roc])
    return model

 ......       

 model.fit(trainData, trainLabel, validation_split=0.2, epochs=10, batch_size=64, verbose=2)

help,please.

asymmetryFan · Answer 1 · 2020-12-25T22:11:27.420

Try adding a Flatten layer like so:

def MySimpleMLP(feature=700, vec_size=50):
    auc_roc = LSTM.as_keras_metric(tf.compat.v1.metrics.auc)

    model = Sequential()

    model.add(Dense(32, activation='relu', input_shape=(feature * vec_size,)))
    model.add(Dropout(0.2))
    model.add(Dense(32, activation='relu'))
    model.add(Flatten())
    model.add(Dropout(0.2))
    model.add(Dense(1, activation='softmax'))

    model.compile(loss="binary_crossentropy", optimizer="adam", metrics=[auc_roc])
    return model

 ......       

 model.fit(trainData, trainLabel, validation_split=0.2, epochs=10, batch_size=64, verbose=2)

Flatten turns a (num_of_samples, 64, 32, 32) array into a (num_of_samples, 643232) array, i.e. it makes the array 2D, which is exactly what you need.

thanks for your answer . I put it on the first layer and it works.But its val_auc is always equal to 0.5. — user9903583, Dec 24 '19 at 12:28

Error when checking input: expected dense_1_input to have 2 dimensions, but got array with shape (25000, 700, 50)

1 Answers1