我有一个已经训练了 40 个 epoch 的模型。我为每个时期保留了检查点，并且我还使用 model.save() 保存了模型。训练代码为:

n_units = 1000
model = Sequential()
model.add(LSTM(n_units, input_shape=(None, vec_size), return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(n_units, return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(n_units))
model.add(Dropout(0.2))
model.add(Dense(vec_size, activation='linear'))
model.compile(loss='mean_squared_error', optimizer='adam')
# define the checkpoint
filepath="word2vec-{epoch:02d}-{loss:.4f}.hdf5"
checkpoint = ModelCheckpoint(filepath, monitor='loss', verbose=1, save_best_only=True, mode='min')
callbacks_list = [checkpoint]
# fit the model
model.fit(x, y, epochs=40, batch_size=50, callbacks=callbacks_list)

但是，当我加载模型并尝试再次对其进行训练时，它会重新开始，就好像它之前没有进行过训练一样。损失不是从上次训练开始的。

让我感到困惑的是，当我加载模型并重新定义模型结构并使用 load_weight 时，model.predict() 效果很好。因此，我相信模型权重已加载:

model = Sequential()
model.add(LSTM(n_units, input_shape=(None, vec_size), return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(n_units, return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(n_units))
model.add(Dropout(0.2))
model.add(Dense(vec_size, activation='linear'))
filename = "word2vec-39-0.0027.hdf5"
model.load_weights(filename)
model.compile(loss='mean_squared_error', optimizer='adam')

但是，当我继续训练时，损失与初始阶段一样高:

filepath="word2vec-{epoch:02d}-{loss:.4f}.hdf5"
checkpoint = ModelCheckpoint(filepath, monitor='loss', verbose=1, save_best_only=True, mode='min')
callbacks_list = [checkpoint]
# fit the model
model.fit(x, y, epochs=40, batch_size=50, callbacks=callbacks_list)

我搜索并找到了一些保存和加载模型的示例here和 here .但是，它们都不起作用。

更新 1

我看了this question ，试了一下，效果不错:

model.save('partly_trained.h5')
del model
load_model('partly_trained.h5')

但是当我关闭 Python 并重新打开它，然后再次运行 load_model 时，它会失败。损失与初始状态一样高。

更新 2

我试过 Yu-Yang's example code它有效。但是，当我再次使用我的代码时，它仍然失败。

这是原始训练的结果。第二个 epoch 应该从 loss = 3.1*** 开始:

13700/13846 [============================>.] - ETA: 0s - loss: 3.0519
13750/13846 [============================>.] - ETA: 0s - loss: 3.0511
13800/13846 [============================>.] - ETA: 0s - loss: 3.0512Epoch 00000: loss improved from inf to 3.05101, saving model to LPT-00-3.0510.h5

13846/13846 [==============================] - 81s - loss: 3.0510    
Epoch 2/60

   50/13846 [..............................] - ETA: 80s - loss: 3.1754
  100/13846 [..............................] - ETA: 78s - loss: 3.1174
  150/13846 [..............................] - ETA: 78s - loss: 3.0745

我关闭 Python，重新打开它，使用 model = load_model("LPT-00-3.0510.h5") 加载模型，然后使用以下命令进行训练:

filepath="LPT-{epoch:02d}-{loss:.4f}.h5"
checkpoint = ModelCheckpoint(filepath, monitor='loss', verbose=1, save_best_only=True, mode='min')
callbacks_list = [checkpoint]
# fit the model
model.fit(x, y, epochs=60, batch_size=50, callbacks=callbacks_list)

损失从4.54开始:

Epoch 1/60
   50/13846 [..............................] - ETA: 162s - loss: 4.5451
   100/13846 [..............................] - ETA: 113s - loss: 4.3835

最佳答案

由于很难弄清楚问题出在哪里，我从你的代码中创建了一个玩具示例，它似乎工作正常。

import numpy as np
from numpy.testing import assert_allclose
from keras.models import Sequential, load_model
from keras.layers import LSTM, Dropout, Dense
from keras.callbacks import ModelCheckpoint

vec_size = 100
n_units = 10

x_train = np.random.rand(500, 10, vec_size)
y_train = np.random.rand(500, vec_size)

model = Sequential()
model.add(LSTM(n_units, input_shape=(None, vec_size), return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(n_units, return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(n_units))
model.add(Dropout(0.2))
model.add(Dense(vec_size, activation='linear'))
model.compile(loss='mean_squared_error', optimizer='adam')

# define the checkpoint
filepath = "model.h5"
checkpoint = ModelCheckpoint(filepath, monitor='loss', verbose=1, save_best_only=True, mode='min')
callbacks_list = [checkpoint]

# fit the model
model.fit(x_train, y_train, epochs=5, batch_size=50, callbacks=callbacks_list)

# load the model
new_model = load_model(filepath)
assert_allclose(model.predict(x_train),
                new_model.predict(x_train),
                1e-5)

# fit the model
checkpoint = ModelCheckpoint(filepath, monitor='loss', verbose=1, save_best_only=True, mode='min')
callbacks_list = [checkpoint]
new_model.fit(x_train, y_train, epochs=5, batch_size=50, callbacks=callbacks_list)

模型加载后损失继续减少。 (重启python也没有问题)

Using TensorFlow backend.
Epoch 1/5
500/500 [==============================] - 2s - loss: 0.3216     Epoch 00000: loss improved from inf to 0.32163, saving model to model.h5
Epoch 2/5
500/500 [==============================] - 0s - loss: 0.2923     Epoch 00001: loss improved from 0.32163 to 0.29234, saving model to model.h5
Epoch 3/5
500/500 [==============================] - 0s - loss: 0.2542     Epoch 00002: loss improved from 0.29234 to 0.25415, saving model to model.h5
Epoch 4/5
500/500 [==============================] - 0s - loss: 0.2086     Epoch 00003: loss improved from 0.25415 to 0.20860, saving model to model.h5
Epoch 5/5
500/500 [==============================] - 0s - loss: 0.1725     Epoch 00004: loss improved from 0.20860 to 0.17249, saving model to model.h5

Epoch 1/5
500/500 [==============================] - 0s - loss: 0.1454     Epoch 00000: loss improved from inf to 0.14543, saving model to model.h5
Epoch 2/5
500/500 [==============================] - 0s - loss: 0.1289     Epoch 00001: loss improved from 0.14543 to 0.12892, saving model to model.h5
Epoch 3/5
500/500 [==============================] - 0s - loss: 0.1169     Epoch 00002: loss improved from 0.12892 to 0.11694, saving model to model.h5
Epoch 4/5
500/500 [==============================] - 0s - loss: 0.1097     Epoch 00003: loss improved from 0.11694 to 0.10971, saving model to model.h5
Epoch 5/5
500/500 [==============================] - 0s - loss: 0.1057     Epoch 00004: loss improved from 0.10971 to 0.10570, saving model to model.h5

顺便说一句，重新定义模型后跟 load_weight() 肯定行不通，因为 save_weight() 和 load_weight() 不保存/加载优化器。

关于python - Keras:如何保存模型并继续训练？，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/45393429/