ValueError: Error when checking target: expected dense_13 to have shape (None, 6) but got array with shape (6, 1)

Question

I am training a classification network with training data which has X.shape = (1119, 7) and Y.shape = (1119, 6). Below is my simple Keras network with and output dim of 6 (size of labels). The error which is returned is below the code

hidden_size = 128
model = Sequential()
model.add(Embedding(7, hidden_size))
#model.add(LSTM(128, input_shape=(1,7)))
model.add(LSTM(hidden_size, return_sequences=True))
model.add(LSTM(hidden_size, return_sequences=True))
model.add(Dense(output_dim=6, activation='softmax'))
# Compile model
model.compile(loss='categorical_crossentropy', 
              optimizer='adam', 
              metrics=["categorical_accuracy"])

ValueError: Error when checking target: expected dense_13 to have shape (None, 6) but got array with shape (6, 1)

I would perfer not to do this in tensorflow because I am just prototyping yet it is my first run at Keras and am confused about why it cannot take this data. I attempted to reshape the data in a number of ways in which nothing worked. Any advice as to why this isn't work would be greatly appreciated.

I think Dense(output_dim=6, activation='softmax')) must be changed to Dense( 6 , activation='softmax')) — Shubham Panchal
– Shubham Panchal, Commented Mar 13, 2019 at 1:17
There's no problem with your model. You should give data processing and training code. — giser_yugang
– giser_yugang, Commented Mar 13, 2019 at 2:04

Anna Krogager · Accepted Answer · 2019-03-13 07:45:10Z

1

You should probably remove the parameter return_sequences=True from your last LSTM layer. When using return_sequences=True, the output of the LSTM layer has shape (seq_len, hidden_size). Passing this on to a Dense layer gives you an output shape of (seq_len, 6), which is incompatible with your labels. If you instead omit return_sequences=True, then your LSTM layer returns shape (hidden_size,) (it only returns the last element of the sequence) and subsequently your final Dense layer will have output shape (6,) like your labels.

answered Mar 13, 2019 at 7:45

Anna Krogager

3,59819 silver badges24 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

The_Watcher Over a year ago

ValueError: Input 0 is incompatible with layer lstm_17: expected ndim=3, found ndim=2 is the error I receive if I attempt this.

Anna Krogager Over a year ago

Is lstm_17 the first or second LSTM layer? The first LSTM needs return_sequences=True, the second one doesn't. Also, your input X_train should have shape (batch_size, seq_length).

Collectives™ on Stack Overflow

ValueError: Error when checking target: expected dense_13 to have shape (None, 6) but got array with shape (6, 1)

1 Answer 1

2 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

2 Comments

Your Answer

Sign up or log in

Post as a guest

Related