Keras密集层形状错误 [英] Keras Dense layer shape error
问题描述
我正在使用keras创建LSTM模型.训练时,我遇到了这个错误.
I am using keras to create a LSTM model. While training, I am getting this error.
ValueError: Error when checking target: expected dense_4 to have shape (1,) but got array with shape (34,)
这是我的模特
model = Sequential()
model.add(Embedding(max_words, embedding_dim, input_length=maxlen))
model.add(LSTM(128, activation='relu'))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(units = 34 ,activation='softmax'))
model.layers[0].set_weights([embedding_matrix])
model.layers[0].trainable = False
model.compile(optimizer='rmsprop',loss='sparse_categorical_crossentropy',metrics=['acc'])
模型摘要:
Layer (type) Output Shape Param #
=================================================================
embedding_2 (Embedding) (None, 15, 50) 500000
_________________________________________________________________
lstm_2 (LSTM) (None, 128) 91648
_________________________________________________________________
dense_3 (Dense) (None, 64) 8256
_________________________________________________________________
dropout_2 (Dropout) (None, 64) 0
_________________________________________________________________
dense_4 (Dense) (None, 34) 2210
=================================================================
Total params: 602,114
Trainable params: 102,114
Non-trainable params: 500,000
_________________________________________________________________
我打电话给
history = model.fit(X_train, y_train,epochs=100,batch_size=128)
y_train
是形状为(299, 34)
的单次热编码标签.
X_train
的形状为(299, 15)
.
y_train
is a one-hot-encoded label with shape (299, 34)
.
X_train
is of shape (299, 15)
.
我不确定为什么模型正在寻找shape(1,),因为我可以看到dense_4 (Dense)
的输出形状为((None,34).
I am not sure why model is looking for shape(1,) as I can see that dense_4 (Dense)
has an output shape of `(None, 34).
推荐答案
好,我发现了问题.我将其发布为答案,以便它可以帮助面临同样问题的其他人.
Ok, I found the issue. I am posting this as answer so that it can help others also who is facing the same issue.
这不是层配置,而是错误的丢失功能.
It was not the layer configuration but the wrong loss function.
我使用sparse_categorical_crossentropy
作为损失,其中标签必须具有形状[batch_size]
且dtype为int32或int64.我已经更改为categorical_crossentropy
,它期望标签为[batch_size,num_classes].
I was using sparse_categorical_crossentropy
as loss where labels must have the shape [batch_size]
and the dtype int32 or int64. I have changed is to categorical_crossentropy
which expect label of [batch_size, num_classes].
keras抛出的错误消息具有误导性.
Error message thrown by keras was misleading.
这篇关于Keras密集层形状错误的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!