使用不是符号张量的输入调用了层 conv2d_3 [英] Layer conv2d_3 was called with an input that isn't a symbolic tensor

问题描述

我正在为一类分类构建一个图像分类器，其中我在运行这个模型时使用了自动编码器我收到了这个错误(ValueError: Layer conv2d_3 was called with an input that is not a symbol tensor. Received类型:.完整输入:[(128, 128, 3)].层的所有输入都应该是张量.)

hi I am building a image classifier for one-class classification in which i've used autoencoder while running this model I am getting this error (ValueError: Layer conv2d_3 was called with an input that isn't a symbolic tensor. Received type: . Full input: [(128, 128, 3)]. All inputs to the layer should be tensors.)

num_of_samples = img_data.shape[0]
labels = np.ones((num_of_samples,),dtype='int64')



labels[0:376]=0 
names = ['cat']

Y = np_utils.to_categorical(labels, num_class)
input_shape=img_data[0].shape

x,y = shuffle(img_data,Y, random_state=2)

X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=2)

x = Conv2D(16, (3, 3), activation='relu', padding='same')(input_shape)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
encoded = MaxPooling2D((2, 2), padding='same')(x)

# at this point the representation is (4, 4, 8) i.e. 128-dimensional

x = Conv2D(8, (3, 3), activation='relu', padding='same')(encoded)
x = UpSampling2D((2, 2))(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
x = Conv2D(16, (3, 3), activation='relu')(x)
x = UpSampling2D((2, 2))(x)
decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)

autoencoder = Model(input_shape, decoded)
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')


autoencoder.fit(X_train, X_train,
            epochs=50,
            batch_size=32,
            shuffle=True,
            validation_data=(X_test, X_test),
            callbacks=[TensorBoard(log_dir='/tmp/autoencoder')])

推荐答案

这里:

x = Conv2D(16, (3, 3), activation='relu', padding='same')(input_shape)

形状不是张量.

这样做:

from keras.layers import *
inputTensor = Input(input_shape)
x = Conv2D(16, (3, 3), activation='relu', padding='same')(inputTensor)

---

关于自动编码器的提示

您应该将编码器和解码器作为单独的模型分开.稍后您可能只想使用其中之一.

---

Hint about autoencoders

You should separate the encoder and decoder as individual models. Later you will probably want to work with only one of them.

编码器:

inputTensor = Input(input_shape)
x = ....
encodedData = MaxPooling2D((2, 2), padding='same')(x)

encoderModel = Model(inputTensor,encodedData)

解码器:

encodedInput = Input((4,4,8))
x = ....
decodedData = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)

decoderModel = Model(encodedInput,decodedData)

自编码器:

autoencoderInput = Input(input_shape)
encoded = encoderModel(autoencoderInput)
decoded = decoderModel(encoded)

autoencoderModel = Model(autoencoderInput,decoded)

这篇关于使用不是符号张量的输入调用了层 conv2d_3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！