在Tensorflow中训练一个模型后:
如何拯救训练过的模型? 您以后如何恢复这个保存的模型?
在Tensorflow中训练一个模型后:
如何拯救训练过的模型? 您以后如何恢复这个保存的模型?
当前回答
特遣部队。keras模型保存TF2.0
我看到了使用TF1.x保存模型的很好的答案。我想提供更多关于保存张量流的提示。Keras模型有点复杂,因为有很多方法来保存一个模型。
这里我提供了一个保存张量流的例子。Keras模型到当前目录下的model_path文件夹。这可以很好地与最新的tensorflow (TF2.0)一起工作。如果在不久的将来有任何变化,我会更新这个描述。
保存和加载整个模型
import tensorflow as tf
from tensorflow import keras
mnist = tf.keras.datasets.mnist
#import data
(x_train, y_train),(x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
# create a model
def create_model():
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(input_shape=(28, 28)),
tf.keras.layers.Dense(512, activation=tf.nn.relu),
tf.keras.layers.Dropout(0.2),
tf.keras.layers.Dense(10, activation=tf.nn.softmax)
])
# compile the model
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
return model
# Create a basic model instance
model=create_model()
model.fit(x_train, y_train, epochs=1)
loss, acc = model.evaluate(x_test, y_test,verbose=1)
print("Original model, accuracy: {:5.2f}%".format(100*acc))
# Save entire model to a HDF5 file
model.save('./model_path/my_model.h5')
# Recreate the exact same model, including weights and optimizer.
new_model = keras.models.load_model('./model_path/my_model.h5')
loss, acc = new_model.evaluate(x_test, y_test)
print("Restored model, accuracy: {:5.2f}%".format(100*acc))
仅保存和加载模型重量
如果您只对保存模型权重感兴趣,然后加载权重以恢复模型,那么
model.fit(x_train, y_train, epochs=5)
loss, acc = model.evaluate(x_test, y_test,verbose=1)
print("Original model, accuracy: {:5.2f}%".format(100*acc))
# Save the weights
model.save_weights('./checkpoints/my_checkpoint')
# Restore the weights
model = create_model()
model.load_weights('./checkpoints/my_checkpoint')
loss,acc = model.evaluate(x_test, y_test)
print("Restored model, accuracy: {:5.2f}%".format(100*acc))
使用keras检查点回调保存和恢复
# include the epoch in the file name. (uses `str.format`)
checkpoint_path = "training_2/cp-{epoch:04d}.ckpt"
checkpoint_dir = os.path.dirname(checkpoint_path)
cp_callback = tf.keras.callbacks.ModelCheckpoint(
checkpoint_path, verbose=1, save_weights_only=True,
# Save weights, every 5-epochs.
period=5)
model = create_model()
model.save_weights(checkpoint_path.format(epoch=0))
model.fit(train_images, train_labels,
epochs = 50, callbacks = [cp_callback],
validation_data = (test_images,test_labels),
verbose=0)
latest = tf.train.latest_checkpoint(checkpoint_dir)
new_model = create_model()
new_model.load_weights(latest)
loss, acc = new_model.evaluate(test_images, test_labels)
print("Restored model, accuracy: {:5.2f}%".format(100*acc))
保存自定义度量的模型
import tensorflow as tf
from tensorflow import keras
mnist = tf.keras.datasets.mnist
(x_train, y_train),(x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
# Custom Loss1 (for example)
@tf.function()
def customLoss1(yTrue,yPred):
return tf.reduce_mean(yTrue-yPred)
# Custom Loss2 (for example)
@tf.function()
def customLoss2(yTrue, yPred):
return tf.reduce_mean(tf.square(tf.subtract(yTrue,yPred)))
def create_model():
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(input_shape=(28, 28)),
tf.keras.layers.Dense(512, activation=tf.nn.relu),
tf.keras.layers.Dropout(0.2),
tf.keras.layers.Dense(10, activation=tf.nn.softmax)
])
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy', customLoss1, customLoss2])
return model
# Create a basic model instance
model=create_model()
# Fit and evaluate model
model.fit(x_train, y_train, epochs=1)
loss, acc,loss1, loss2 = model.evaluate(x_test, y_test,verbose=1)
print("Original model, accuracy: {:5.2f}%".format(100*acc))
model.save("./model.h5")
new_model=tf.keras.models.load_model("./model.h5",custom_objects={'customLoss1':customLoss1,'customLoss2':customLoss2})
使用自定义操作保存keras模型
当我们像下面的例子(tf.tile)一样进行自定义操作时,我们需要创建一个函数并使用Lambda层进行包装。否则,无法保存模型。
import numpy as np
import tensorflow as tf
from tensorflow.keras.layers import Input, Lambda
from tensorflow.keras import Model
def my_fun(a):
out = tf.tile(a, (1, tf.shape(a)[0]))
return out
a = Input(shape=(10,))
#out = tf.tile(a, (1, tf.shape(a)[0]))
out = Lambda(lambda x : my_fun(x))(a)
model = Model(a, out)
x = np.zeros((50,10), dtype=np.float32)
print(model(x).numpy())
model.save('my_model.h5')
#load the model
new_model=tf.keras.models.load_model("my_model.h5")
我想我已经介绍了许多保存tf的方法中的一些。keras模型。然而,还有许多其他的方法。如果你发现你的用例没有在上面提到,请在下面评论。谢谢!
其他回答
你可以使用Tensorflow中的saver对象来保存你训练过的模型。该对象提供保存和恢复模型的方法。
在TensorFlow中保存一个训练好的模型:
tf.train.Saver.save(sess, save_path, global_step=None, latest_filename=None,
meta_graph_suffix='meta', write_meta_graph=True,
write_state=True, strip_default_attrs=False,
save_debug_info=False)
在TensorFlow中恢复已保存的模型:
tf.train.Saver.restore(sess, save_path, latest_filename=None,
meta_graph_suffix='meta', clear_devices=False,
import_scope=None)
tensorflow - 2.0
这很简单。
import tensorflow as tf
SAVE
model.save("model_name")
恢复
model = tf.keras.models.load_model('model_name')
我在版本:
tensorflow (1.13.1)
tensorflow-gpu (1.13.1)
简单的方法是
拯救策略:
model.save("model.h5")
恢复:
model = tf.keras.models.load_model("model.h5")
你也可以用更简单的方法。
步骤1:初始化所有变量
W1 = tf.Variable(tf.truncated_normal([6, 6, 1, K], stddev=0.1), name="W1")
B1 = tf.Variable(tf.constant(0.1, tf.float32, [K]), name="B1")
Similarly, W2, B2, W3, .....
步骤2:在模型Saver中保存会话并保存它
model_saver = tf.train.Saver()
# Train the model and save it in the end
model_saver.save(session, "saved_models/CNN_New.ckpt")
步骤3:恢复模型
with tf.Session(graph=graph_cnn) as session:
model_saver.restore(session, "saved_models/CNN_New.ckpt")
print("Model restored.")
print('Initialized')
步骤4:检查变量
W1 = session.run(W1)
print(W1)
在不同的python实例中运行时,使用
with tf.Session() as sess:
# Restore latest checkpoint
saver.restore(sess, tf.train.latest_checkpoint('saved_model/.'))
# Initalize the variables
sess.run(tf.global_variables_initializer())
# Get default graph (supply your custom graph if you have one)
graph = tf.get_default_graph()
# It will give tensor object
W1 = graph.get_tensor_by_name('W1:0')
# To get the value (numpy array)
W1_value = session.run(W1)
这里所有的答案都很棒,但我想补充两点。
首先,详细说明@user7505159的答案,“。添加到要恢复的文件名的开头可能很重要。
例如,您可以保存没有“的图形。/"在文件名中如下所示:
# Some graph defined up here with specific names
saver = tf.train.Saver()
save_file = 'model.ckpt'
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver.save(sess, save_file)
但是为了恢复图形,您可能需要在前面加上一个"。/"到file_name:
# Same graph defined up here
saver = tf.train.Saver()
save_file = './' + 'model.ckpt' # String addition used for emphasis
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver.restore(sess, save_file)
你并不总是需要“。/”,但是它会根据你的环境和TensorFlow版本而导致问题。
它还想提到sess.run(tf.global_variables_initializer())在恢复会话之前可能很重要。
如果在尝试恢复保存的会话时收到关于未初始化变量的错误,请确保在保存程序之前包含sess.run(tf.global_variables_initializer())。恢复(sess, save_file)行。这样你就不用头疼了。