0

我在 Keras 有一个模型如下：

data = Input(shape=input_shape)

# 512 x 640 x 3
pad1 = TimeDistributed(ZeroPadding2D(padding=(100, 100)))(data)

# 712 x 840 x 3
conv1_1 = TimeDistributed(Conv2D(8, (3,3), padding="valid", activation="relu", name="block1_conv1", data_format="channels_last"))(pad1)
conv1_2 = TimeDistributed(Conv2D(8, (3,3), padding="same", activation="relu", name="block1_conv2", data_format="channels_last"))(conv1_1)
pool1   = TimeDistributed(MaxPooling2D((2,2), strides=(2,2), padding="same", name="block1_pool", data_format="channels_last"))(conv1_2)

我希望能够将 conv1_1 和 conv1_2 的可训练权重参数设置为每个时间步的预训练值。我可以这样做吗？Keras 似乎将这些层视为具有自己可训练参数的实体，而不是具有相同共享可训练权重的 Conv2D 函数的集合。有没有办法改变这个？如何访问单个时间片的可训练权重并将其分配给所有时间片？

4

1 回答 1

1

你可以这样做：

data = Input(shape=input_shape)

# 512 x 640 x 3
pad1 = TimeDistributed(ZeroPadding2D(padding=(100, 100)))(data)

# 712 x 840 x 3
nd_conv1_1 = Conv2D(8, (3,3), padding="valid", activation="relu", name="block1_conv1", data_format="channels_last")
nd_conv1_2 = Conv2D(8, (3,3), padding="same", activation="relu", name="block1_conv2", data_format="channels_last")
conv1_1 = TimeDistributed(nd_conv1_1)(pad1)
conv1_2 = TimeDistributed(nd_conv1_2)(conv1_1)
pool1   = TimeDistributed(MaxPooling2D((2,2), strides=(2,2), padding="same", name="block1_pool", data_format="channels_last"))(conv1_2)

nd_conv1_1.trainable = True/False
nd_conv1_2.trainable = True/False
于 2018-10-10T13:30:41.090 回答