Created by: phonism

here is my code

dropout_layer = paddle.networks.dropout_layer(input=concat_layer, dropout_rate=0.5)
# fc and output layer
output = paddle.layer.fc(input=dropout_layer, size=class_dim, act=paddle.activation.Sigmoid())

dropout_layer work for cpu, but gpu not. it will get the follow error.

Traceback (most recent call last):
  File "model.py", line 188, in <module>
    train_cnn_model(num_pass=num_pass)
  File "model.py", line 108, in train_cnn_model
    [cost, output, label] = convolution_net(dict_dim, class_dim=class_dim)
  File "model.py", line 42, in convolution_net
    dropout_layer = paddle.networks.dropout_layer(input=concat_layer, dropout_rate=0.5)
AttributeError: 'module' object has no attribute 'dropout_layer'