keras - 检查带有嵌入层的目标时出错

Question

I'm trying to run keras model as follows:

model = Sequential()
model.add(Dense(10, activation='relu',input_shape=(286,)))
model.add(Dense(1, activation='softmax',input_shape=(324827, 286)))

This code works, but if I'm trying to add an embedding layer:

model = Sequential()
model.add(Embedding(286,64, input_shape=(286,)))
model.add(Dense(10, activation='relu',input_shape=(286,)))
model.add(Dense(1, activation='softmax',input_shape=(324827, 286)))

I'm getting the following error :

ValueError: Error when checking target: expected dense_2 to have 3 dimensions, but got array with shape (324827, 1)

My data have 286 features and 324827 rows. I'm probably doing something wrong with the shape definitions, can you tell me what it is ? Thanks

Answer 1

You don't need to provide the input_shape in the second Dense layer, and neither the first one, only on the first layer, the following layers shape will be coomputed :

from tensorflow.keras.layers import Embedding, Dense
from tensorflow.keras.models import Sequential

# 286 features and 324827 rows (324827, 286)

model = Sequential()
model.add(Embedding(286,64, input_shape=(286,)))
model.add(Dense(10, activation='relu'))
model.add(Dense(1, activation='softmax'))
model.compile(loss='mse', optimizer='adam')
model.summary()

returns :

Model: "sequential_2"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
embedding_2 (Embedding)      (None, 286, 64)           18304     
_________________________________________________________________
dense_2 (Dense)              (None, 286, 10)           650       
_________________________________________________________________
dense_3 (Dense)              (None, 286, 1)            11        
=================================================================
Total params: 18,965
Trainable params: 18,965
Non-trainable params: 0
_________________________________________________________________

I hope it's what you're looking for