110

如何在 Keras 中从 HDF5 文件加载模型？

我尝试了什么：

model = Sequential()

model.add(Dense(64, input_dim=14, init='uniform'))
model.add(LeakyReLU(alpha=0.3))
model.add(BatchNormalization(epsilon=1e-06, mode=0, momentum=0.9, weights=None))
model.add(Dropout(0.5))

model.add(Dense(64, init='uniform'))
model.add(LeakyReLU(alpha=0.3))
model.add(BatchNormalization(epsilon=1e-06, mode=0, momentum=0.9, weights=None))
model.add(Dropout(0.5))

model.add(Dense(2, init='uniform'))
model.add(Activation('softmax'))


sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='binary_crossentropy', optimizer=sgd)

checkpointer = ModelCheckpoint(filepath="/weights.hdf5", verbose=1, save_best_only=True)
model.fit(X_train, y_train, nb_epoch=20, batch_size=16, show_accuracy=True, validation_split=0.2, verbose = 2, callbacks=[checkpointer])

上述代码成功地将最佳模型保存到名为 weights.hdf5 的文件中。然后我想做的是加载该模型。下面的代码显示了我是如何尝试这样做的：

model2 = Sequential()
model2.load_weights("/Users/Desktop/SquareSpace/weights.hdf5")

这是我得到的错误：

IndexError                                Traceback (most recent call last)
<ipython-input-101-ec968f9e95c5> in <module>()
      1 model2 = Sequential()
----> 2 model2.load_weights("/Users/Desktop/SquareSpace/weights.hdf5")

/Applications/anaconda/lib/python2.7/site-packages/keras/models.pyc in load_weights(self, filepath)
    582             g = f['layer_{}'.format(k)]
    583             weights = [g['param_{}'.format(p)] for p in range(g.attrs['nb_params'])]
--> 584             self.layers[k].set_weights(weights)
    585         f.close()
    586 

IndexError: list index out of range
4

5 回答 5

232

如果您将完整的模型（不仅是权重）存储在 HDF5 文件中，那么它就像

from keras.models import load_model
model = load_model('model.h5')
于 2017-04-06T19:17:07.037 回答
91

load_weights仅设置网络的权重。您仍然需要在调用之前定义其架构load_weights：

def create_model():
   model = Sequential()
   model.add(Dense(64, input_dim=14, init='uniform'))
   model.add(LeakyReLU(alpha=0.3))
   model.add(BatchNormalization(epsilon=1e-06, mode=0, momentum=0.9, weights=None))
   model.add(Dropout(0.5)) 
   model.add(Dense(64, init='uniform'))
   model.add(LeakyReLU(alpha=0.3))
   model.add(BatchNormalization(epsilon=1e-06, mode=0, momentum=0.9, weights=None))
   model.add(Dropout(0.5))
   model.add(Dense(2, init='uniform'))
   model.add(Activation('softmax'))
   return model

def train():
   model = create_model()
   sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
   model.compile(loss='binary_crossentropy', optimizer=sgd)

   checkpointer = ModelCheckpoint(filepath="/tmp/weights.hdf5", verbose=1, save_best_only=True)
   model.fit(X_train, y_train, nb_epoch=20, batch_size=16, show_accuracy=True, validation_split=0.2, verbose=2, callbacks=[checkpointer])

def load_trained_model(weights_path):
   model = create_model()
   model.load_weights(weights_path)
于 2016-02-04T09:13:21.403 回答
29

请参阅以下示例代码，了解如何构建基本的 Keras 神经网络模型、保存模型 (JSON) 和权重 (HDF5) 并加载它们：

# create model
model = Sequential()
model.add(Dense(X.shape[1], input_dim=X.shape[1], activation='relu')) #Input Layer
model.add(Dense(X.shape[1], activation='relu')) #Hidden Layer
model.add(Dense(output_dim, activation='softmax')) #Output Layer

# Compile & Fit model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(X,Y,nb_epoch=5,batch_size=100,verbose=1)    

# serialize model to JSON
model_json = model.to_json()
with open("Data/model.json", "w") as json_file:
    json_file.write(simplejson.dumps(simplejson.loads(model_json), indent=4))

# serialize weights to HDF5
model.save_weights("Data/model.h5")
print("Saved model to disk")

# load json and create model
json_file = open('Data/model.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
loaded_model = model_from_json(loaded_model_json)

# load weights into new model
loaded_model.load_weights("Data/model.h5")
print("Loaded model from disk")

# evaluate loaded model on test data 
# Define X_test & Y_test data first
loaded_model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
score = loaded_model.evaluate(X_test, Y_test, verbose=0)
print ("%s: %.2f%%" % (loaded_model.metrics_names[1], score[1]*100))
于 2017-01-15T10:23:14.463 回答
8

根据官方文档 https://keras.io/getting-started/faq/#how-can-i-install-hdf5-or-h5py-to-save-my-models-in-keras

你可以做 ：

首先通过运行测试你是否安装了 h5py

import h5py

如果您在导入 h5py 时没有错误，您可以保存：

from keras.models import load_model

model.save('my_model.h5')  # creates a HDF5 file 'my_model.h5'
del model  # deletes the existing model

# returns a compiled model
# identical to the previous one
model = load_model('my_model.h5')

如果需要安装 h5py http://docs.h5py.org/en/latest/build.html

于 2018-12-16T00:23:13.280 回答
0

我是这样做的

from keras.models import Sequential
from keras_contrib.losses import import crf_loss
from keras_contrib.metrics import crf_viterbi_accuracy

# To save model
model.save('my_model_01.hdf5')

# To load the model
custom_objects={'CRF': CRF,'crf_loss': crf_loss,'crf_viterbi_accuracy':crf_viterbi_accuracy}

# To load a persisted model that uses the CRF layer 
model1 = load_model("/home/abc/my_model_01.hdf5", custom_objects = custom_objects)
于 2019-03-04T07:09:34.483 回答