使用Tensorflow 2.0模型子类访问层的输入/输出

在一个大学练习中，我使用了TF2.0的模型子类化API。这是我的代码(它是Alexnet架构，如果你想知道……):

class MyModel(Model):
    def __init__(self):
        super(MyModel, self).__init__()
        # OPS
        self.relu = Activation('relu', name='ReLU')
        self.maxpool = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), padding='valid', name='MaxPool')
        self.softmax = Activation('softmax', name='Softmax')

        # Conv layers
        self.conv1 = Conv2D(filters=96, input_shape=(224, 224, 3), kernel_size=(11, 11), strides=(4, 4), padding='same',
                            name='conv1')
        self.conv2a = Conv2D(filters=128, kernel_size=(5, 5), strides=(1, 1), padding='same', name='conv2a')
        self.conv2b = Conv2D(filters=128, kernel_size=(5, 5), strides=(1, 1), padding='same', name='conv2b')
        self.conv3 = Conv2D(filters=384, kernel_size=(3, 3), strides=(1, 1), padding='same', name='conv3')
        self.conv4a = Conv2D(filters=192, kernel_size=(3, 3), strides=(1, 1), padding='same', name='conv4a')
        self.conv4b = Conv2D(filters=192, kernel_size=(3, 3), strides=(1, 1), padding='same', name='conv4b')
        self.conv5a = Conv2D(filters=128, kernel_size=(3, 3), strides=(1, 1), padding='same', name='conv5a')
        self.conv5b = Conv2D(filters=128, kernel_size=(3, 3), strides=(1, 1), padding='same', name='conv5b')

        # Fully-connected layers

        self.flatten = Flatten()

        self.dense1 = Dense(4096, input_shape=(100,), name='FC_4096_1')
        self.dense2 = Dense(4096, name='FC_4096_2')
        self.dense3 = Dense(1000, name='FC_1000')

        # Network definition

    def call(self, x, **kwargs):
        x = self.conv1(x)
        x = self.relu(x)
        x = tf.nn.local_response_normalization(x, depth_radius=2, alpha=2e-05, beta=0.75, bias=1.0)
        x = self.maxpool(x)

        x = tf.concat((self.conv2a(x[:, :, :, :48]), self.conv2b(x[:, :, :, 48:])), 3)
        x = self.relu(x)
        x = tf.nn.local_response_normalization(x, depth_radius=2, alpha=2e-05, beta=0.75, bias=1.0)
        x = self.maxpool(x)

        x = self.conv3(x)
        x = self.relu(x)
        x = tf.concat((self.conv4a(x[:, :, :, :192]), self.conv4b(x[:, :, :, 192:])), 3)
        x = self.relu(x)
        x = tf.concat((self.conv5a(x[:, :, :, :192]), self.conv5b(x[:, :, :, 192:])), 3)
        x = self.relu(x)
        x = self.maxpool(x)

        x = self.flatten(x)

        x = self.dense1(x)
        x = self.relu(x)
        x = self.dense2(x)
        x = self.relu(x)
        x = self.dense3(x)
        return self.softmax(x)

我的目标是访问一个任意层的输出(为了最大化一个特定神经元的激活，如果你必须确切地知道:))。问题是，试图访问任何层的输出，我得到一个属性错误。例如:

model = MyModel()
print(model.get_layer('conv1').output)
# => AttributeError: Layer conv1 has no inbound nodes.

我在SO中发现了一些关于这个错误的问题，他们都声称我必须在第一层定义输入形状，但是正如你所看到的，它已经完成了(参见self的定义)。conv1在_init__功能)! 我发现如果我定义一个keras。layers。输入对象，我确实设法获得了conv1的输出，但试图访问更深层次的失败，例如:

model = MyModel()
I = tf.keras.Input(shape=(224, 224, 3))
model(I)
print(model.get_layer('conv1').output)
# prints Tensor("my_model/conv1/Identity:0", shape=(None, 56, 56, 96), dtype=float32)
print(model.get_layer('FC_1000').output)
# => AttributeError: Layer FC_1000 has no inbound nodes.

我在谷歌上搜索了我遇到的每一个例外，但是没有找到答案。在这种情况下，我如何访问任何层的输入/输出(或者输入/输出_shape属性)? 问题来源StackOverflow 地址：/questions/59383356/accessing-layers-input-output-using-tensorflow-2-0-model-sub-classing