Question

我似乎对更新的keras版本有问题。这种神经网络结构导致了这个错误：

  print "Data-train-in: " + str(data_train_input[0].shape)
        print "Data-train-out: " + str(data_train_output[0].shape)
        print "Data-test-in: " + str(data_test_input[0].shape)
        #sys.exit()

        model.add(Conv2D(filters = 32, kernel_size = (3,3) , padding = "same" , activation = "LeakyRelu" , input_shape = (3,6,3)))
        model.add(Conv2D(filters = 64, kernel_size = (3,3) , padding = "same" , activation = "LeakyRelu", ))
        model.add(Conv2D(filters = 64, kernel_size = (3,3) , padding = "same" , activation = "LeakyRelu", ))
        model.add(Conv2D(filters = 32, kernel_size = (1,1) , padding = "same" , activation = "LeakyRelu", ))
        print model.output_shape
#        model.add(MaxPooling2D(pool_size=(3,1)))
        print model.output_shape
        model.add(Flatten())
        print model.output_shape
#        model.add(Dense(output_dim=300, input_dim=200, init="normal",activation='tanh'))
#        model.add(Dense(output_dim=32, input_dim=200, init="normal",activation='relu'))
#        model.add(Dense(output_dim=1, input_dim=32, init="normal",activation='tanh'))
        model.add(Dense(output_dim=13, input_dim=32, init="normal",activation='LeakyReLU'))
        model.add(Dense(output_dim=1,  init="normal", activation='linear'))
        print model.summary()
        model.compile(loss='mean_squared_error', optimizer="adam")

给出这个输出：

Data-train-in: (3, 6, 3)
Data-train-out: (1,)
Data-test-in: (3, 6, 3)
Traceback (most recent call last):
  File "keras_convolutional_feature_extraction.py", line 602, in <module>
    model(i,train_input_data_interweawed_normalized,output_data_train,test_input_data_interweawed_normalized,output_data_test)
  File "keras_convolutional_feature_extraction.py", line 535, in model
    model.add(Conv2D(filters = 32, kernel_size = (3,3) , padding = "same" , activation = "LeakyRelu" , input_shape = (3,6,3)))
  File "/usr/local/lib/python2.7/dist-packages/keras/legacy/interfaces.py", line 87, in wrapper
    return func(*args, **kwargs)
  File "/usr/local/lib/python2.7/dist-packages/keras/layers/convolutional.py", line 455, in __init__
    **kwargs)
  File "/usr/local/lib/python2.7/dist-packages/keras/layers/convolutional.py", line 108, in __init__
    self.activation = activations.get(activation)
  File "/usr/local/lib/python2.7/dist-packages/keras/activations.py", line 69, in get
    return deserialize(identifier)
  File "/usr/local/lib/python2.7/dist-packages/keras/activations.py", line 61, in deserialize
    printable_module_name='activation function')
  File "/usr/local/lib/python2.7/dist-packages/keras/utils/generic_utils.py", line 157, in deserialize_keras_object
    ':' + class_name)
UnboundLocalError: local variable 'class_name' referenced before assignment

我读了一些关于这个问题的其他帖子，但这似乎与其他帖子类似。

Answer 1

必须以可分离的方式添加高级图层，而不是在定义卷积图层的同一行中。

带有keras 2.0的UnboundLocalError

1 个答案: