在 Tensorflow 中——是否可以在一个层中锁定特定的卷积过滤器,或者完全删除它们?
In Tensorflow - Is it possible to lock specific convolution filters in a layer, or to remove them altogether?
在 Tensorflow 中使用迁移学习时,我知道可以锁定层以防止进一步训练,方法是:
for layer in pre_trained_model.layers:
layer.trainable = False
是否可以改为锁定图层中的特定过滤器?
如 - 如果整个图层包含 64 个过滤器,是否可以:
- 只锁定其中一些似乎包含合理过滤器和
重新训练那些没有的?
或
- 从图层中删除看起来不合理的过滤器并在没有它们的情况下重新训练?
(例如,查看重新训练的过滤器是否会发生很大变化)
一种可能的解决方案是实现自定义层,将卷积拆分为单独的 number of filters
卷积并将每个通道(这是一个具有一个输出通道的卷积)设置为 trainable
或 not trainable
.例如:
import tensorflow as tf
import numpy as np
class Conv2DExtended(tf.keras.layers.Layer):
def __init__(self, filters, kernel_size, **kwargs):
self.filters = filters
self.conv_layers = [tf.keras.layers.Conv2D(1, kernel_size, **kwargs) for _ in range(filters)]
super().__init__()
def build(self, input_shape):
_ = [l.build(input_shape) for l in self.conv_layers]
super().build(input_shape)
def set_trainable(self, channels):
"""Sets trainable channels."""
for i in channels:
self.conv_layers[i].trainable = True
def set_non_trainable(self, channels):
"""Sets not trainable channels."""
for i in channels:
self.conv_layers[i].trainable = False
def call(self, inputs):
results = [l(inputs) for l in self.conv_layers]
return tf.concat(results, -1)
以及用法示例:
inputs = tf.keras.layers.Input((28, 28, 1))
conv = Conv2DExtended(filters=4, kernel_size=(3, 3))
conv.set_non_trainable([1, 2]) # only channels 0 and 3 are trainable
res = conv(inputs)
res = tf.keras.layers.Flatten()(res)
res = tf.keras.layers.Dense(1, activation=tf.nn.sigmoid)(res)
model = tf.keras.models.Model(inputs, res)
model.compile(optimizer=tf.keras.optimizers.SGD(),
loss='binary_crossentropy',
metrics=['accuracy'])
model.fit(np.random.normal(0, 1, (10, 28, 28, 1)),
np.random.randint(0, 2, (10)),
batch_size=2,
epochs=5)
在 Tensorflow 中使用迁移学习时,我知道可以锁定层以防止进一步训练,方法是:
for layer in pre_trained_model.layers:
layer.trainable = False
是否可以改为锁定图层中的特定过滤器? 如 - 如果整个图层包含 64 个过滤器,是否可以:
- 只锁定其中一些似乎包含合理过滤器和 重新训练那些没有的?
或
- 从图层中删除看起来不合理的过滤器并在没有它们的情况下重新训练? (例如,查看重新训练的过滤器是否会发生很大变化)
一种可能的解决方案是实现自定义层,将卷积拆分为单独的 number of filters
卷积并将每个通道(这是一个具有一个输出通道的卷积)设置为 trainable
或 not trainable
.例如:
import tensorflow as tf
import numpy as np
class Conv2DExtended(tf.keras.layers.Layer):
def __init__(self, filters, kernel_size, **kwargs):
self.filters = filters
self.conv_layers = [tf.keras.layers.Conv2D(1, kernel_size, **kwargs) for _ in range(filters)]
super().__init__()
def build(self, input_shape):
_ = [l.build(input_shape) for l in self.conv_layers]
super().build(input_shape)
def set_trainable(self, channels):
"""Sets trainable channels."""
for i in channels:
self.conv_layers[i].trainable = True
def set_non_trainable(self, channels):
"""Sets not trainable channels."""
for i in channels:
self.conv_layers[i].trainable = False
def call(self, inputs):
results = [l(inputs) for l in self.conv_layers]
return tf.concat(results, -1)
以及用法示例:
inputs = tf.keras.layers.Input((28, 28, 1))
conv = Conv2DExtended(filters=4, kernel_size=(3, 3))
conv.set_non_trainable([1, 2]) # only channels 0 and 3 are trainable
res = conv(inputs)
res = tf.keras.layers.Flatten()(res)
res = tf.keras.layers.Dense(1, activation=tf.nn.sigmoid)(res)
model = tf.keras.models.Model(inputs, res)
model.compile(optimizer=tf.keras.optimizers.SGD(),
loss='binary_crossentropy',
metrics=['accuracy'])
model.fit(np.random.normal(0, 1, (10, 28, 28, 1)),
np.random.randint(0, 2, (10)),
batch_size=2,
epochs=5)