问题描述
我正在建立这个模型:
inputs = model.inputs[:2]
layer_output = model.get_layer('Encoder-12-FeedForward-Norm').output
input_layer= keras.layers.Input(shape=(SEQ_LEN,768))(layer_output)
conv_layer= keras.layers.Conv1D(100, kernel_size=3, activation='relu', data_format='channels_first')(input_layer)
maxpool_layer = keras.layers.MaxPooling1D(pool_size=4)(conv_layer)
flat_layer= keras.layers.Flatten()(maxpool_layer)
outputs = keras.layers.Dense(units=3, activation='softmax')(flat_layer)
model = keras.models.Model(inputs, outputs)
model.compile(RAdam(learning_rate =LR),loss='sparse_categorical_crossentropy',metrics=['sparse_categorical_accuracy'])
，并且我一直收到此错误TypeError: 'Tensor' object is not callable，我知道layer_output是张量而不是层，Keras可以处理层.但是我发现很难找出正确的方法.我以前用相似的输入构建了一个biLSTM模型，并且工作正常.有人可以向我指出一些可以帮助我更好地理解该问题的东西吗?我尝试将input_layer传递给conv_layer，但出现此错误TypeError: Layer conv1d_1 does not support masking, but was passed an input_mask: Tensor("Encoder-12-FeedForward-Add/All:0", shape=(?, 35), dtype=bool)
and I keep getting this error TypeError: 'Tensor' object is not callable I know layer_output is a tensor and not a layer and Keras works with layers. But I'm finding it difficult to figure out the right thing to do. I have previously build a biLSTM model with similar inputs and it works fine. Can someone point me to something that will help me understand the issue better? I have tried passing the input_layer to the conv_layer but I get this error TypeError: Layer conv1d_1 does not support masking, but was passed an input_mask: Tensor("Encoder-12-FeedForward-Add/All:0", shape=(?, 35), dtype=bool)
推荐答案
input_layer= keras.layers.Input(shape=(SEQ_LEN,768))(layer_output)
您正在尝试将输入传递给输入张量???
You're trying to pass an input to an input tensor???
要么有张量:layer_output;或者您有一个输入张量:Input(shape...).试图将两者混合在一起是没有意义的.
Either you have a tensor: layer_output; or you have an input tensor: Input(shape...). There is no point in trying to mix both things.
在您的代码中，左侧的所有内容均为Tensor，这是正确的！
中间的所有内容均为Layer，所有层的右侧均称为Tensor.
In your code, everything on the left side are Tensor, and that's correct!
Everything in the middle are Layer, and all layers are called with the right side, which are Tensor.
tensor_instance = Layer(...)(tensor_instance)
但是Input不是层，Input是张量.您不能Input(...)(tensor_instance)，因为Input不是图层.
But Input is not a layer, Input is a tensor. You cannot Input(...)(tensor_instance) because Input is not a layer.
不需要使用layer_output(张量)做任何事情.您已经拥有了，所以继续:
There is no need to do anything with layer_output (tensor). You already have it, so just go ahead:
conv_layer_output_tensor = Conv1D(...)(layer_output)
建议:
Suggestion:
inputs = model.inputs[:2] #what is this model??
layer_output = model.get_layer('Encoder-12-FeedForward-Norm').output
#this may not work
#unless this output can be fully gotten with the two inputs you selected
#(and there is a chance that Keras code is not prepared for this)
conv_output = keras.layers.Conv1D(100, kernel_size=3, activation='relu',
data_format='channels_first')(layer_output)
maxpool_output = keras.layers.MaxPooling1D(pool_size=4)(conv_output)
flat_output= keras.layers.Flatten()(maxpool_output)
outputs = keras.layers.Dense(units=3, activation='softmax')(flat_output)
another_model = keras.models.Model(inputs, outputs)
another_model.compile(RAdam(learning_rate = LR),
loss='sparse_categorical_crossentropy',
metrics=['sparse_categorical_accuracy'])
这篇关于TypeError:'Tensor'对象不可调用凯拉斯·伯特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！