如何为解码器加载训练有素的自动编码器权重？
How to load trained autoencoder weights for decoder?
我有一个 CNN 1d 自动编码器，它有一个密集的中央层。我想训练这个自动编码器并保存它的模型。我还想保留解码器部分，目标是：将一些中心特征（独立计算）提供给训练和加载的解码器，通过解码器查看这些独立计算的特征的图像是什么。
## ENCODER
encoder_input = Input(batch_shape=(None,501,1))
x = Conv1D(256,3, activation='tanh', padding='valid')(encoder_input)
x = MaxPooling1D(2)(x)
x = Conv1D(32,3, activation='tanh', padding='valid')(x)
x = MaxPooling1D(2)(x)
_x = Flatten()(x)
encoded = Dense(32,activation = 'tanh')(_x)
## DECODER (autoencoder)
y = Conv1D(32, 3, activation='tanh', padding='valid')(x)
y = UpSampling1D(2)(y)
y = Conv1D(256, 3, activation='tanh', padding='valid')(y)
y = UpSampling1D(2)(y)
y = Flatten()(y)
y = Dense(501)(y)
decoded = Reshape((501,1))(y)
autoencoder = Model(encoder_input, decoded)
autoencoder.save('autoencoder.hdf5')
## DECODER (independent)
decoder_input = Input(batch_shape=K.int_shape(x)) # import keras.backend as K
y = Conv1D(32, 3, activation='tanh', padding='valid')(decoder_input)
y = UpSampling1D(2)(y)
y = Conv1D(256, 3, activation='tanh', padding='valid')(y)
y = UpSampling1D(2)(y)
y = Flatten()(y)
y = Dense(501)(y)
decoded = Reshape((501,1))(y)
decoder = Model(decoder_input, decoded)
decoder.save('decoder.hdf5')
编辑：
为了确保清楚，我首先需要 JOIN encoded 和第一个 y，因为 y 必须采用 encoded作为输入。完成此操作后，我需要一种方法来加载训练有素的解码器并用一些新的核心功能替换 encoded，我将用这些功能来提供我的解码器。
编辑以下答案：
我实现了建议，见下面的代码
## ENCODER
encoder_input = Input(batch_shape=(None,501,1))
x = Conv1D(256,3, activation='tanh', padding='valid')(encoder_input)
x = MaxPooling1D(2)(x)
x = Conv1D(32,3, activation='tanh', padding='valid')(x)
x = MaxPooling1D(2)(x)
_x = Flatten()(x)
encoded = Dense(32,activation = 'tanh')(_x)
## DECODER (autoencoder)
encoded = Reshape((32,1))(encoded)
y = Conv1D(32, 3, activation='tanh', padding='valid')(encoded)
y = UpSampling1D(2)(y)
y = Conv1D(256, 3, activation='tanh', padding='valid')(y)
y = UpSampling1D(2)(y)
y = Flatten()(y)
y = Dense(501)(y)
decoded = Reshape((501,1))(y)
autoencoder = Model(encoder_input, decoded)
autoencoder.compile(optimizer='adam', loss='mse')
epochs = 10
batch_size = 100
validation_split = 0.2
# train the model
history = autoencoder.fit(x = training, y = training,
epochs=epochs,
batch_size=batch_size,
validation_split=validation_split)
autoencoder.save_weights('autoencoder_weights.h5')
## DECODER (independent)
decoder_input = Input(batch_shape=K.int_shape(encoded)) # import keras.backend as K
y = Conv1D(32, 3, activation='tanh', padding='valid', name='decod_conv1d_1')(decoder_input)
y = UpSampling1D(2, name='decod_upsampling1d_1')(y)
y = Conv1D(256, 3, activation='tanh', padding='valid', name='decod_conv1d_2')(y)
y = UpSampling1D(2, name='decod_upsampling1d_2')(y)
y = Flatten(name='decod_flatten')(y)
y = Dense(501, name='decod_dense1')(y)
decoded = Reshape((501,1), name='decod_reshape')(y)
decoder = Model(decoder_input, decoded)
decoder.save_weights('decoder_weights.h5')
encoder = Model(inputs=encoder_input, outputs=encoded, name='encoder')
features = encoder.predict(training) # features
np.savetxt('features.txt', np.squeeze(features))
predictions = autoencoder.predict(training)
predictions = np.squeeze(predictions)
np.savetxt('predictions.txt', predictions)
然后我打开另一个文件
import h5py
import keras.backend as K
def load_weights(model, filepath):
with h5py.File(filepath, mode='r') as f:
file_layer_names = [n.decode('utf8') for n in f.attrs['layer_names']]
model_layer_names = [layer.name for layer in model.layers]
weight_values_to_load = []
for name in file_layer_names:
if name not in model_layer_names:
print(name, "is ignored; skipping")
continue
g = f[name]
weight_names = [n.decode('utf8') for n in g.attrs['weight_names']]
weight_values = []
if len(weight_names) != 0:
weight_values = [g[weight_name] for weight_name in weight_names]
try:
layer = model.get_layer(name=name)
except:
layer = None
if layer is not None:
symbolic_weights = (layer.trainable_weights +
layer.non_trainable_weights)
if len(symbolic_weights) != len(weight_values):
print('Model & file weights shapes mismatch')
else:
weight_values_to_load += zip(symbolic_weights, weight_values)
K.batch_set_value(weight_values_to_load)
## DECODER (independent)
decoder_input = Input(batch_shape=(None,32,1))
y = Conv1D(32, 3, activation='tanh',padding='valid',name='decod_conv1d_1')(decoder_input)
y = UpSampling1D(2, name='decod_upsampling1d_1')(y)
y = Conv1D(256, 3, activation='tanh', padding='valid', name='decod_conv1d_2')(y)
y = UpSampling1D(2, name='decod_upsampling1d_2')(y)
y = Flatten(name='decod_flatten')(y)
y = Dense(501, name='decod_dense1')(y)
decoded = Reshape((501,1), name='decod_reshape')(y)
decoder = Model(decoder_input, decoded)
#decoder.save_weights('decoder_weights.h5')
load_weights(decoder, 'autoencoder_weights.h5')
# Read autoencoder
decoder.summary()
# read encoded features
features = np.loadtxt('features.txt'.format(batch_size, epochs))
features = np.reshape(features, [1500,32,1])
# evaluate loaded model on features
prediction = decoder.predict(features)
autoencoderpredictions = np.loadtxt('predictions.txt'.format(batch_size, epochs))
fig, ax = plt.subplots(5, figsize=(10,20))
for i in range(5):
ax[i].plot(prediction[100*i], color='blue', label='Decoder')
ax[i].plot(autoencoderpredictions[100*i], color='red', label='AE')
ax[i].set_xlabel('Time components', fontsize='x-large')
ax[i].set_ylabel('Amplitude', fontsize='x-large')
ax[i].set_title('Seismogram n. {:}'.format(1500+100*i+1), fontsize='x-large')
ax[i].legend(fontsize='x-large')
plt.subplots_adjust(hspace=1)
plt.close()
prediction和autoencoderpredictions不同意。似乎 prediction 只是小噪音，而 autoencoder predictions 具有合理的值。
您需要：(1) 保存 AE（自动编码器）的权重； (2)加载权重文件； (3) 反序列化文件，只分配那些与新模型（解码器）兼容的权重。
- (1)：
.save 确实包含权重，但是使用 .save_weights 可以省去额外的反序列化步骤。此外，.save 保存优化器状态和模型架构，后者与您的新解码器无关
- (2)：
load_weights 默认尝试分配 所有 保存的权重，这不会起作用
下面的代码完成 (3)（和补救措施 (2)）如下：
- 加载所有权重
- 检索加载的权重名称并将它们存储在
file_layer_names（列表）
- 检索当前模型权重名称并将它们存储在
model_layer_names（列表） 中
- 迭代
file_layer_names 为 name；如果 name 在 model_layer_names 中，将具有该名称的加载重量附加到 weight_values_to_load
- 将
weight_values_to_load 中的权重分配给使用 K.batch_set_value 的模型
请注意，这需要您命名 AE 和解码器模型中的每一层并使它们匹配。可以重写此代码以在 try-except 循环中按顺序强制分配，但这既低效又容易出错。
用法:
## omitted; use code as in question but name all ## DECODER layers as below
autoencoder.save_weights('autoencoder_weights.h5')
## DECODER (independent)
decoder_input = Input(batch_shape=K.int_shape(x))
y = Conv1D(32, 3, activation='tanh',padding='valid',name='decod_conv1d_1')(decoder_input)
y = UpSampling1D(2, name='decod_upsampling1d_1')(y)
y = Conv1D(256, 3, activation='tanh', padding='valid', name='decod_conv1d_2')(y)
y = UpSampling1D(2, name='decod_upsampling1d_2')(y)
y = Flatten(name='decod_flatten')(y)
y = Dense(501, name='decod_dense1')(y)
decoded = Reshape((501,1), name='decod_reshape')(y)
decoder = Model(decoder_input, decoded)
decoder.save_weights('decoder_weights.h5')
load_weights(decoder, 'autoencoder_weights.h5')
函数：
import h5py
import keras.backend as K
def load_weights(model, filepath):
with h5py.File(filepath, mode='r') as f:
file_layer_names = [n.decode('utf8') for n in f.attrs['layer_names']]
model_layer_names = [layer.name for layer in model.layers]
weight_values_to_load = []
for name in file_layer_names:
if name not in model_layer_names:
print(name, "is ignored; skipping")
continue
g = f[name]
weight_names = [n.decode('utf8') for n in g.attrs['weight_names']]
weight_values = []
if len(weight_names) != 0:
weight_values = [g[weight_name] for weight_name in weight_names]
try:
layer = model.get_layer(name=name)
except:
layer = None
if layer is not None:
symbolic_weights = (layer.trainable_weights +
layer.non_trainable_weights)
if len(symbolic_weights) != len(weight_values):
print('Model & file weights shapes mismatch')
else:
weight_values_to_load += zip(symbolic_weights, weight_values)
K.batch_set_value(weight_values_to_load)
我有一个 CNN 1d 自动编码器，它有一个密集的中央层。我想训练这个自动编码器并保存它的模型。我还想保留解码器部分，目标是：将一些中心特征（独立计算）提供给训练和加载的解码器，通过解码器查看这些独立计算的特征的图像是什么。
## ENCODER
encoder_input = Input(batch_shape=(None,501,1))
x = Conv1D(256,3, activation='tanh', padding='valid')(encoder_input)
x = MaxPooling1D(2)(x)
x = Conv1D(32,3, activation='tanh', padding='valid')(x)
x = MaxPooling1D(2)(x)
_x = Flatten()(x)
encoded = Dense(32,activation = 'tanh')(_x)
## DECODER (autoencoder)
y = Conv1D(32, 3, activation='tanh', padding='valid')(x)
y = UpSampling1D(2)(y)
y = Conv1D(256, 3, activation='tanh', padding='valid')(y)
y = UpSampling1D(2)(y)
y = Flatten()(y)
y = Dense(501)(y)
decoded = Reshape((501,1))(y)
autoencoder = Model(encoder_input, decoded)
autoencoder.save('autoencoder.hdf5')
## DECODER (independent)
decoder_input = Input(batch_shape=K.int_shape(x)) # import keras.backend as K
y = Conv1D(32, 3, activation='tanh', padding='valid')(decoder_input)
y = UpSampling1D(2)(y)
y = Conv1D(256, 3, activation='tanh', padding='valid')(y)
y = UpSampling1D(2)(y)
y = Flatten()(y)
y = Dense(501)(y)
decoded = Reshape((501,1))(y)
decoder = Model(decoder_input, decoded)
decoder.save('decoder.hdf5')
编辑：
为了确保清楚，我首先需要 JOIN encoded 和第一个 y，因为 y 必须采用 encoded作为输入。完成此操作后，我需要一种方法来加载训练有素的解码器并用一些新的核心功能替换 encoded，我将用这些功能来提供我的解码器。
编辑以下答案：
我实现了建议，见下面的代码
## ENCODER
encoder_input = Input(batch_shape=(None,501,1))
x = Conv1D(256,3, activation='tanh', padding='valid')(encoder_input)
x = MaxPooling1D(2)(x)
x = Conv1D(32,3, activation='tanh', padding='valid')(x)
x = MaxPooling1D(2)(x)
_x = Flatten()(x)
encoded = Dense(32,activation = 'tanh')(_x)
## DECODER (autoencoder)
encoded = Reshape((32,1))(encoded)
y = Conv1D(32, 3, activation='tanh', padding='valid')(encoded)
y = UpSampling1D(2)(y)
y = Conv1D(256, 3, activation='tanh', padding='valid')(y)
y = UpSampling1D(2)(y)
y = Flatten()(y)
y = Dense(501)(y)
decoded = Reshape((501,1))(y)
autoencoder = Model(encoder_input, decoded)
autoencoder.compile(optimizer='adam', loss='mse')
epochs = 10
batch_size = 100
validation_split = 0.2
# train the model
history = autoencoder.fit(x = training, y = training,
epochs=epochs,
batch_size=batch_size,
validation_split=validation_split)
autoencoder.save_weights('autoencoder_weights.h5')
## DECODER (independent)
decoder_input = Input(batch_shape=K.int_shape(encoded)) # import keras.backend as K
y = Conv1D(32, 3, activation='tanh', padding='valid', name='decod_conv1d_1')(decoder_input)
y = UpSampling1D(2, name='decod_upsampling1d_1')(y)
y = Conv1D(256, 3, activation='tanh', padding='valid', name='decod_conv1d_2')(y)
y = UpSampling1D(2, name='decod_upsampling1d_2')(y)
y = Flatten(name='decod_flatten')(y)
y = Dense(501, name='decod_dense1')(y)
decoded = Reshape((501,1), name='decod_reshape')(y)
decoder = Model(decoder_input, decoded)
decoder.save_weights('decoder_weights.h5')
encoder = Model(inputs=encoder_input, outputs=encoded, name='encoder')
features = encoder.predict(training) # features
np.savetxt('features.txt', np.squeeze(features))
predictions = autoencoder.predict(training)
predictions = np.squeeze(predictions)
np.savetxt('predictions.txt', predictions)
然后我打开另一个文件
import h5py
import keras.backend as K
def load_weights(model, filepath):
with h5py.File(filepath, mode='r') as f:
file_layer_names = [n.decode('utf8') for n in f.attrs['layer_names']]
model_layer_names = [layer.name for layer in model.layers]
weight_values_to_load = []
for name in file_layer_names:
if name not in model_layer_names:
print(name, "is ignored; skipping")
continue
g = f[name]
weight_names = [n.decode('utf8') for n in g.attrs['weight_names']]
weight_values = []
if len(weight_names) != 0:
weight_values = [g[weight_name] for weight_name in weight_names]
try:
layer = model.get_layer(name=name)
except:
layer = None
if layer is not None:
symbolic_weights = (layer.trainable_weights +
layer.non_trainable_weights)
if len(symbolic_weights) != len(weight_values):
print('Model & file weights shapes mismatch')
else:
weight_values_to_load += zip(symbolic_weights, weight_values)
K.batch_set_value(weight_values_to_load)
## DECODER (independent)
decoder_input = Input(batch_shape=(None,32,1))
y = Conv1D(32, 3, activation='tanh',padding='valid',name='decod_conv1d_1')(decoder_input)
y = UpSampling1D(2, name='decod_upsampling1d_1')(y)
y = Conv1D(256, 3, activation='tanh', padding='valid', name='decod_conv1d_2')(y)
y = UpSampling1D(2, name='decod_upsampling1d_2')(y)
y = Flatten(name='decod_flatten')(y)
y = Dense(501, name='decod_dense1')(y)
decoded = Reshape((501,1), name='decod_reshape')(y)
decoder = Model(decoder_input, decoded)
#decoder.save_weights('decoder_weights.h5')
load_weights(decoder, 'autoencoder_weights.h5')
# Read autoencoder
decoder.summary()
# read encoded features
features = np.loadtxt('features.txt'.format(batch_size, epochs))
features = np.reshape(features, [1500,32,1])
# evaluate loaded model on features
prediction = decoder.predict(features)
autoencoderpredictions = np.loadtxt('predictions.txt'.format(batch_size, epochs))
fig, ax = plt.subplots(5, figsize=(10,20))
for i in range(5):
ax[i].plot(prediction[100*i], color='blue', label='Decoder')
ax[i].plot(autoencoderpredictions[100*i], color='red', label='AE')
ax[i].set_xlabel('Time components', fontsize='x-large')
ax[i].set_ylabel('Amplitude', fontsize='x-large')
ax[i].set_title('Seismogram n. {:}'.format(1500+100*i+1), fontsize='x-large')
ax[i].legend(fontsize='x-large')
plt.subplots_adjust(hspace=1)
plt.close()
prediction和autoencoderpredictions不同意。似乎 prediction 只是小噪音，而 autoencoder predictions 具有合理的值。
您需要：(1) 保存 AE（自动编码器）的权重； (2)加载权重文件； (3) 反序列化文件，只分配那些与新模型（解码器）兼容的权重。
- (1)：
.save确实包含权重，但是使用.save_weights可以省去额外的反序列化步骤。此外，.save保存优化器状态和模型架构，后者与您的新解码器无关 - (2)：
load_weights默认尝试分配 所有 保存的权重，这不会起作用
下面的代码完成 (3)（和补救措施 (2)）如下：
- 加载所有权重
- 检索加载的权重名称并将它们存储在
file_layer_names（列表） - 检索当前模型权重名称并将它们存储在
model_layer_names（列表） 中
- 迭代
file_layer_names为name；如果name在model_layer_names中，将具有该名称的加载重量附加到weight_values_to_load - 将
weight_values_to_load中的权重分配给使用K.batch_set_value 的模型
请注意，这需要您命名 AE 和解码器模型中的每一层并使它们匹配。可以重写此代码以在 try-except 循环中按顺序强制分配，但这既低效又容易出错。
用法:
## omitted; use code as in question but name all ## DECODER layers as below
autoencoder.save_weights('autoencoder_weights.h5')
## DECODER (independent)
decoder_input = Input(batch_shape=K.int_shape(x))
y = Conv1D(32, 3, activation='tanh',padding='valid',name='decod_conv1d_1')(decoder_input)
y = UpSampling1D(2, name='decod_upsampling1d_1')(y)
y = Conv1D(256, 3, activation='tanh', padding='valid', name='decod_conv1d_2')(y)
y = UpSampling1D(2, name='decod_upsampling1d_2')(y)
y = Flatten(name='decod_flatten')(y)
y = Dense(501, name='decod_dense1')(y)
decoded = Reshape((501,1), name='decod_reshape')(y)
decoder = Model(decoder_input, decoded)
decoder.save_weights('decoder_weights.h5')
load_weights(decoder, 'autoencoder_weights.h5')
函数：
import h5py
import keras.backend as K
def load_weights(model, filepath):
with h5py.File(filepath, mode='r') as f:
file_layer_names = [n.decode('utf8') for n in f.attrs['layer_names']]
model_layer_names = [layer.name for layer in model.layers]
weight_values_to_load = []
for name in file_layer_names:
if name not in model_layer_names:
print(name, "is ignored; skipping")
continue
g = f[name]
weight_names = [n.decode('utf8') for n in g.attrs['weight_names']]
weight_values = []
if len(weight_names) != 0:
weight_values = [g[weight_name] for weight_name in weight_names]
try:
layer = model.get_layer(name=name)
except:
layer = None
if layer is not None:
symbolic_weights = (layer.trainable_weights +
layer.non_trainable_weights)
if len(symbolic_weights) != len(weight_values):
print('Model & file weights shapes mismatch')
else:
weight_values_to_load += zip(symbolic_weights, weight_values)
K.batch_set_value(weight_values_to_load)