我使用以下相当简单的代码来预测可能有3个类别的输出变量：
n_factors = 20
np.random.seed = 42
def embedding_input(name, n_in, n_out, reg):
inp = Input(shape=(1,), dtype='int64', name=name)
return inp, Embedding(n_in, n_out, input_length=1, W_regularizer=l2(reg))(inp)
user_in, u = embedding_input('user_in', n_users, n_factors, 1e-4)
artifact_in, a = embedding_input('artifact_in', n_artifacts, n_factors, 1e-4)
mt = Input(shape=(31,))
mr = Input(shape=(1,))
sub = Input(shape=(24,))
def onehot(featurename):
onehot_encoder = OneHotEncoder(sparse=False)
onehot_encoded = onehot_encoder.fit_transform(Modality_Durations[featurename].reshape(-1, 1))
trn_onehot_encoded = onehot_encoded[msk]
val_onehot_encoded = onehot_encoded[~msk]
return trn_onehot_encoded, val_onehot_encoded
trn_onehot_encoded_mt, val_onehot_encoded_mt = onehot('modality_type')
trn_onehot_encoded_mr, val_onehot_encoded_mr = onehot('roleid')
trn_onehot_encoded_sub, val_onehot_encoded_sub = onehot('subject')
trn_onehot_encoded_quartile, val_onehot_encoded_quartile = onehot('quartile')
# Model
x = merge([u, a], mode='concat')
x = Flatten()(x)
x = merge([x, mt], mode='concat')
x = merge([x, mr], mode='concat')
x = merge([x, sub], mode='concat')
x = Dense(10, activation='relu')(x)
BatchNormalization()
x = Dense(3, activation='softmax')(x)
nn = Model([user_in, artifact_in, mt, mr, sub], x)
nn.compile(loss='sparse_categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
nn.optimizer.lr = 0.001
nn.fit([trn.member_id, trn.artifact_id, trn_onehot_encoded_mt, trn_onehot_encoded_mr, trn_onehot_encoded_sub], trn_onehot_encoded_quartile,
batch_size=256,
epochs=2,
validation_data=([val.member_id, val.artifact_id, val_onehot_encoded_mt, val_onehot_encoded_mr, val_onehot_encoded_sub], val_onehot_encoded_quartile)
)
以下是该模型的摘要：
____________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
====================================================================================================
user_in (InputLayer) (None, 1) 0
____________________________________________________________________________________________________
artifact_in (InputLayer) (None, 1) 0
____________________________________________________________________________________________________
embedding_9 (Embedding) (None, 1, 20) 5902380 user_in[0][0]
____________________________________________________________________________________________________
embedding_10 (Embedding) (None, 1, 20) 594200 artifact_in[0][0]
____________________________________________________________________________________________________
merge_25 (Merge) (None, 1, 40) 0 embedding_9[0][0]
embedding_10[0][0]
____________________________________________________________________________________________________
flatten_7 (Flatten) (None, 40) 0 merge_25[0][0]
____________________________________________________________________________________________________
input_13 (InputLayer) (None, 31) 0
____________________________________________________________________________________________________
merge_26 (Merge) (None, 71) 0 flatten_7[0][0]
input_13[0][0]
____________________________________________________________________________________________________
input_14 (InputLayer) (None, 1) 0
____________________________________________________________________________________________________
merge_27 (Merge) (None, 72) 0 merge_26[0][0]
input_14[0][0]
____________________________________________________________________________________________________
input_15 (InputLayer) (None, 24) 0
____________________________________________________________________________________________________
merge_28 (Merge) (None, 96) 0 merge_27[0][0]
input_15[0][0]
____________________________________________________________________________________________________
dense_13 (Dense) (None, 10) 970 merge_28[0][0]
____________________________________________________________________________________________________
dense_14 (Dense) (None, 3) 33 dense_13[0][0]
====================================================================================================
Total params: 6,497,583
Trainable params: 6,497,583
Non-trainable params: 0
_____________________________
但是在fit语句中，我收到以下错误：
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-71-7de0782d7d5d> in <module>()
5 batch_size=256,
6 epochs=2,
----> 7 validation_data=([val.member_id, val.artifact_id, val_onehot_encoded_mt, val_onehot_encoded_mr, val_onehot_encoded_sub], val_onehot_encoded_quartile)
8 )
9 # nn.fit([trn.member_id, trn.artifact_id, trn_onehot_encoded_mt, trn_onehot_encoded_mr, trn_onehot_encoded_sub], trn.duration_new,
/home/prateek_dl/anaconda3/lib/python3.5/site-packages/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, **kwargs)
1520 class_weight=class_weight,
1521 check_batch_axis=False,
-> 1522 batch_size=batch_size)
1523 # Prepare validation data.
1524 do_validation = False
/home/prateek_dl/anaconda3/lib/python3.5/site-packages/keras/engine/training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, check_batch_axis, batch_size)
1380 output_shapes,
1381 check_batch_axis=False,
-> 1382 exception_prefix='target')
1383 sample_weights = _standardize_sample_weights(sample_weight,
1384 self._feed_output_names)
/home/prateek_dl/anaconda3/lib/python3.5/site-packages/keras/engine/training.py in _standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
142 ' to have shape ' + str(shapes[i]) +
143 ' but got array with shape ' +
--> 144 str(array.shape))
145 return arrays
146
ValueError: Error when checking target: expected dense_14 to have shape (None, 1) but got array with shape (1956554, 3)
如何解决此错误？为什么最终图层在根据(None,1)输出summary()时需要(None,3)？
非常感谢任何帮助。
答案 0 :(得分：0)
我使用categorical_entropy而不是sparse_categorical_entropy修正了错误。