试图在预测测试图像时获得每一层的输出，但是得到一个错误输入张量到一个函数必须来自`tf.keras.Input`答案

【问题标题】：Trying to get output of each layer while predicting test image, however getting an error Input tensors to a Functional must come from `tf.keras.Input`试图在预测测试图像时获得每一层的输出，但是得到一个错误输入张量到一个函数必须来自`tf.keras.Input`
【发布时间】：2022-04-19 13:31:55
【问题描述】：

我正在尝试使用 TensorFlow 和 Keras 在 Python 中进行图像识别。请查看下面我提供的链接中的代码，因为我遇到了相同代码的另一个问题，现在已修复。

getting error while predicting a test image - cannot reshape array of size

我按照Keras, How to get the output of each layer? 的帖子获取每一层的输出并使用下面的代码

from keras import backend as K 
inp = model.input                                           # input placeholder
outputs = [layer.output for layer in model.layers[:12]]        # all layer outputs except first (input) layer
functor = K.function([inp, K.learning_phase()], outputs )   # evaluation function

# Testing
test = numpy.random.random(input_shape)[np.newaxis,...]
layer_outs = functor([test, 1.])
print (layer_outs)

但是，我收到以下错误：

ValueError: Input tensors to a Functional must come from `tf.keras.Input`. Received: 0 (missing previous layer metadata).

有人可以帮助获取我正在预测的图像的每一层的输出，该图像是新图像，而不是网络训练过的图像的一部分吗？

【问题讨论】：

标签： python tensorflow image-processing keras deep-learning

【解决方案1】：

如果您可以将模型定义如下，那么您将不会收到上述特定错误：

model = Sequential([
                    tf.keras.Input(shape=(X_train.shape[1:])),
                    Conv2D(32, (3, 3), padding='same', activation='relu'),
                    Conv2D(32, (3, 3),  activation='relu', padding='same'),
                    Dropout(0.2),
                    BatchNormalization(),
                    Conv2D(64, (3, 3), padding='same', name='test1', activation='relu'),
                    MaxPooling2D(pool_size=(2, 2)),
                    Dropout(0.2),
                    BatchNormalization(),
                    Conv2D(64, (3, 3), padding='same', name='test2', activation='relu'),
                    MaxPooling2D(pool_size=(2, 2)),
                    Dropout(0.2),
                    BatchNormalization(),
                    Conv2D(128, (3, 3), padding='same', name='test3',activation='relu'),
                    Dropout(0.2),
                    BatchNormalization(),
                    Flatten(),
                    Dropout(0.2),
                    Dense(256, kernel_constraint=maxnorm(3),activation='relu'),
                    Dropout(0.2),
                    BatchNormalization(),
                    Dense(128, kernel_constraint=maxnorm(3),activation='relu'),
                    Dropout(0.2),
                    BatchNormalization(),
                    Dense(class_num,activation='softmax')
])

现在，要从模型中获取每个定义层的输出值，请检查：

from tensorflow.keras import backend as K

for index, layer in enumerate(model.layers):
    func = K.function([model.get_layer(index=0).input], layer.output)
    layerOutput = func([X_test]) 
    print(layerOutput.shape) # to check each layer output, remove .shape

输出：

(10000, 28, 28, 32)
(10000, 28, 28, 32)
(10000, 28, 28, 32)
(10000, 28, 28, 32)
(10000, 28, 28, 64)
(10000, 14, 14, 64)
(10000, 14, 14, 64)
(10000, 14, 14, 64)
(10000, 14, 14, 64)
(10000, 7, 7, 64)
(10000, 7, 7, 64)
(10000, 7, 7, 64)
(10000, 7, 7, 128)
(10000, 7, 7, 128)
(10000, 7, 7, 128)
(10000, 6272)
(10000, 6272)
(10000, 256)
(10000, 256)
(10000, 256)
(10000, 128)
(10000, 128)
(10000, 128)
(10000, 10)

要提取特定层的输出值，您可以使用以下代码：

feature_extractor = keras.Model(
    inputs=model.inputs,
    outputs=model.get_layer(name="test1").output)

features = feature_extractor(X_test)
features.shape
features

输出：

TensorShape([10000, 28, 28, 64])

<tf.Tensor: shape=(10000, 28, 28, 64), dtype=float32, numpy=
array([[[[0.00000000e+00, 0.00000000e+00, 0.00000000e+00, ...,
          0.00000000e+00, 0.00000000e+00, 0.00000000e+00],
         [0.00000000e+00, 0.00000000e+00, 0.00000000e+00, ..
.
.
.

【讨论】：