keras 到 tf.keras 转换：未定义密集层尺寸？
keras to tf.keras Conversion: Dense layer dimensions not defined?
所以我使用纯 keras 构建了一个卷积网络。它完全按预期编译和运行，但我需要将其转换为使用 tf.keras，以便我可以使用 tfmot。阅读文档后，我尝试转换它，结果出现以下错误：
The last dimension of the inputs to Dense should be defined. Found None.
知道我做错了什么吗？
谢谢！
原keras型号：
input_layer = keras.layers.Input(shape=(100,))
reshape_layer = keras.layers.Reshape((-1, 100, 1))(input_layer)
conv_layer_1 = keras.layers.Convolution2D(filters=30, kernel_size=(10, 1), strides=(1, 1), padding="same", activation="relu")(reshape_layer)
conv_layer_2 = keras.layers.Convolution2D(filters=30, kernel_size=(8, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_1)
conv_layer_3 = keras.layers.Convolution2D(filters=40, kernel_size=(6, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_2)
conv_layer_4 = keras.layers.Convolution2D(filters=50, kernel_size=(5, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_3)
conv_layer_5 = keras.layers.Convolution2D(filters=50, kernel_size=(5, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_4)
flatten_layer = keras.layers.Flatten()(conv_layer_5)
label_layer = keras.layers.Dense(200, activation="relu")(flatten_layer)
output_layer = keras.layers.Dense(1, activation="linear")(label_layer)
model = keras.Model(inputs=input_layer, outputs=output_layer)
已转换 tf.keras 型号：
input_layer = tf.keras.layers.InputLayer(input_shape=(100,))
reshape_layer = tf.keras.layers.Reshape((-1, 100, 1))(input_layer)
conv_layer_1 = tf.keras.layers.Convolution2D(filters=30, kernel_size=(10, 1), strides=(1, 1), padding="same", activation="relu")(reshape_layer)
conv_layer_2 = tf.keras.layers.Convolution2D(filters=30, kernel_size=(8, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_1)
conv_layer_3 = tf.keras.layers.Convolution2D(filters=40, kernel_size=(6, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_2)
conv_layer_4 = tf.keras.layers.Convolution2D(filters=50, kernel_size=(5, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_3)
conv_layer_5 = tf.keras.layers.Convolution2D(filters=50, kernel_size=(5, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_4)
flatten_layer = tf.keras.layers.Flatten()(conv_layer_5)
label_layer = tf.keras.layers.Dense(200, activation="relu")(flatten_layer)
output_layer = tf.keras.layers.Dense(1, activation="linear")(label_layer)
model = tf.keras.Model(inputs=input_layer, outputs=output_layer)
编辑 1：
我想也许我可以通过在创建后保存 keras 模型并在编译/训练之前立即将其加载为 tf.keras 模型来解决这个问题。抛出同样的错误！
您的代码几乎没有问题。修复它们，你应该可以开始了，
问题 1：使用 Input 而不是 InputLayer
标准是使用Input层而不是InputLayer（实际上内部使用InputLayer）。如果您使用 Input 层，您还需要将 input_shape 更改为 shape。
input_layer = tf.keras.layers.Input(shape=(100,))
问题 2：输出中有 2 None 个维度
当您执行以下行时，您会在输出中得到两个 None 维度。
reshape_layer = tf.keras.layers.Reshape((-1, 100, 1))(input_layer)
这就是您收到上述错误的原因。在定义 Reshape 层时，您没有定义 batch 维度，它将是 None。如果您想使用 Dense 层，那是您可以作为 None 的唯一维度。否则，Dense 层无法推断其权重的形状（这就是您得到错误的原因）。所以把它改成，
reshape_layer = tf.keras.layers.Reshape((1, 100, 1))(input_layer)
其余保持不变。
conv_layer_1 = tf.keras.layers.Convolution2D(filters=30, kernel_size=(10, 1), strides=(1, 1), padding="same", activation="relu")(reshape_layer)
conv_layer_2 = tf.keras.layers.Convolution2D(filters=30, kernel_size=(8, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_1)
conv_layer_3 = tf.keras.layers.Convolution2D(filters=40, kernel_size=(6, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_2)
conv_layer_4 = tf.keras.layers.Convolution2D(filters=50, kernel_size=(5, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_3)
conv_layer_5 = tf.keras.layers.Convolution2D(filters=50, kernel_size=(5, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_4)
flatten_layer = tf.keras.layers.Flatten()(conv_layer_5)
label_layer = tf.keras.layers.Dense(200, activation="relu")(flatten_layer)
output_layer = tf.keras.layers.Dense(1, activation="linear")(label_layer)
model = tf.keras.Model(inputs=input_layer, outputs=output_layer)
model.summary()
所以我使用纯 keras 构建了一个卷积网络。它完全按预期编译和运行，但我需要将其转换为使用 tf.keras，以便我可以使用 tfmot。阅读文档后，我尝试转换它，结果出现以下错误：
The last dimension of the inputs to Dense should be defined. Found None.
知道我做错了什么吗？
谢谢！
原keras型号：
input_layer = keras.layers.Input(shape=(100,))
reshape_layer = keras.layers.Reshape((-1, 100, 1))(input_layer)
conv_layer_1 = keras.layers.Convolution2D(filters=30, kernel_size=(10, 1), strides=(1, 1), padding="same", activation="relu")(reshape_layer)
conv_layer_2 = keras.layers.Convolution2D(filters=30, kernel_size=(8, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_1)
conv_layer_3 = keras.layers.Convolution2D(filters=40, kernel_size=(6, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_2)
conv_layer_4 = keras.layers.Convolution2D(filters=50, kernel_size=(5, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_3)
conv_layer_5 = keras.layers.Convolution2D(filters=50, kernel_size=(5, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_4)
flatten_layer = keras.layers.Flatten()(conv_layer_5)
label_layer = keras.layers.Dense(200, activation="relu")(flatten_layer)
output_layer = keras.layers.Dense(1, activation="linear")(label_layer)
model = keras.Model(inputs=input_layer, outputs=output_layer)
已转换 tf.keras 型号：
input_layer = tf.keras.layers.InputLayer(input_shape=(100,))
reshape_layer = tf.keras.layers.Reshape((-1, 100, 1))(input_layer)
conv_layer_1 = tf.keras.layers.Convolution2D(filters=30, kernel_size=(10, 1), strides=(1, 1), padding="same", activation="relu")(reshape_layer)
conv_layer_2 = tf.keras.layers.Convolution2D(filters=30, kernel_size=(8, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_1)
conv_layer_3 = tf.keras.layers.Convolution2D(filters=40, kernel_size=(6, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_2)
conv_layer_4 = tf.keras.layers.Convolution2D(filters=50, kernel_size=(5, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_3)
conv_layer_5 = tf.keras.layers.Convolution2D(filters=50, kernel_size=(5, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_4)
flatten_layer = tf.keras.layers.Flatten()(conv_layer_5)
label_layer = tf.keras.layers.Dense(200, activation="relu")(flatten_layer)
output_layer = tf.keras.layers.Dense(1, activation="linear")(label_layer)
model = tf.keras.Model(inputs=input_layer, outputs=output_layer)
编辑 1：
我想也许我可以通过在创建后保存 keras 模型并在编译/训练之前立即将其加载为 tf.keras 模型来解决这个问题。抛出同样的错误！
您的代码几乎没有问题。修复它们，你应该可以开始了，
问题 1：使用 Input 而不是 InputLayer
标准是使用Input层而不是InputLayer（实际上内部使用InputLayer）。如果您使用 Input 层，您还需要将 input_shape 更改为 shape。
input_layer = tf.keras.layers.Input(shape=(100,))
问题 2：输出中有 2 None 个维度
当您执行以下行时，您会在输出中得到两个 None 维度。
reshape_layer = tf.keras.layers.Reshape((-1, 100, 1))(input_layer)
这就是您收到上述错误的原因。在定义 Reshape 层时，您没有定义 batch 维度，它将是 None。如果您想使用 Dense 层，那是您可以作为 None 的唯一维度。否则，Dense 层无法推断其权重的形状（这就是您得到错误的原因）。所以把它改成，
reshape_layer = tf.keras.layers.Reshape((1, 100, 1))(input_layer)
其余保持不变。
conv_layer_1 = tf.keras.layers.Convolution2D(filters=30, kernel_size=(10, 1), strides=(1, 1), padding="same", activation="relu")(reshape_layer)
conv_layer_2 = tf.keras.layers.Convolution2D(filters=30, kernel_size=(8, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_1)
conv_layer_3 = tf.keras.layers.Convolution2D(filters=40, kernel_size=(6, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_2)
conv_layer_4 = tf.keras.layers.Convolution2D(filters=50, kernel_size=(5, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_3)
conv_layer_5 = tf.keras.layers.Convolution2D(filters=50, kernel_size=(5, 1), strides=(1, 1), padding="same", activation="relu")(conv_layer_4)
flatten_layer = tf.keras.layers.Flatten()(conv_layer_5)
label_layer = tf.keras.layers.Dense(200, activation="relu")(flatten_layer)
output_layer = tf.keras.layers.Dense(1, activation="linear")(label_layer)
model = tf.keras.Model(inputs=input_layer, outputs=output_layer)
model.summary()