方法1:只保存模型的权重和偏置
这种方法不会保存整个网络的结构,只是保存模型的权重和偏置,所以在后期恢复模型之前,必须手动创建和之前模型一模一样的模型,以保证权重和偏置的维度和保存之前的相同。
tf.keras.model类中的save_weights方法和load_weights方法,参数解释我就直接搬运官网的内容了。
save_weights( filepath, overwrite=True, save_format=None )
Arguments:
filepath: String, path to the file to save the weights to. When saving in TensorFlow format, this is the prefix used for checkpoint files (multiple files are generated). Note that the '.h5' suffix causes weights to be saved in HDF5 format.
overwrite: Whether to silently overwrite any existing file at the target location, or provide the user with a manual prompt.
save_format: Either 'tf' or 'h5'. A filepath ending in '.h5' or '.keras' will default to HDF5 if save_format is None. Otherwise None defaults to 'tf'.
load_weights( filepath, by_name=False )
实例1:
import tensorflow as tf from tensorflow import keras from tensorflow.keras import datasets, layers, optimizers # step1 加载训练集和测试集合 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 # step2 创建模型 def create_model(): return tf.keras.models.Sequential([ tf.keras.layers.Flatten(input_shape=(28, 28)), tf.keras.layers.Dense(512, activation='relu'), tf.keras.layers.Dropout(0.2), tf.keras.layers.Dense(10, activation='softmax') ]) model = create_model() # step3 编译模型 主要是确定优化方法,损失函数等 model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy']) # step4 模型训练 训练一个epochs model.fit(x=x_train, y=y_train, epochs=1, ) # step5 模型测试 loss, acc = model.evaluate(x_test, y_test) print("train model, accuracy:{:5.2f}%".format(100 * acc)) # step6 保存模型的权重和偏置 model.save_weights('./save_weights/my_save_weights') # step7 删除模型 del model # step8 重新创建模型 model = create_model() model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy']) # step9 恢复权重 model.load_weights('./save_weights/my_save_weights') # step10 测试模型 loss, acc = model.evaluate(x_test, y_test) print("Restored model, accuracy:{:5.2f}%".format(100 * acc))
train model, accuracy:96.55%
Restored model, accuracy:96.55%
可以看到在模型的权重和偏置恢复之后,在测试集合上同样达到了训练之前相同的准确率。
方法2:直接保存整个模型
这种方法会将网络的结构,权重和优化器的状态等参数全部保存下来,后期恢复的时候就没必要创建新的网络了。
tf.keras.model类中的save方法和load_model方法
save( filepath, overwrite=True, include_optimizer=True, save_format=None )
Arguments:
filepath: String, path to SavedModel or H5 file to save the model.
overwrite: Whether to silently overwrite any existing file at the target location, or provide the user with a manual prompt.
include_optimizer: If True, save optimizer's state together.
save_format: Either 'tf' or 'h5', indicating whether to save the model to Tensorflow SavedModel or HDF5. The default is currently 'h5', but will switch to 'tf' in TensorFlow 2.0. The 'tf' option is currently disabled (use tf.keras.experimental.export_saved_model instead).
实例2:
import tensorflow as tf from tensorflow import keras from tensorflow.keras import datasets, layers, optimizers # step1 加载训练集和测试集合 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 # step2 创建模型 def create_model(): return tf.keras.models.Sequential([ tf.keras.layers.Flatten(input_shape=(28, 28)), tf.keras.layers.Dense(512, activation='relu'), tf.keras.layers.Dropout(0.2), tf.keras.layers.Dense(10, activation='softmax') ]) model = create_model() # step3 编译模型 主要是确定优化方法,损失函数等 model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy']) # step4 模型训练 训练一个epochs model.fit(x=x_train, y=y_train, epochs=1, ) # step5 模型测试 loss, acc = model.evaluate(x_test, y_test) print("train model, accuracy:{:5.2f}%".format(100 * acc)) # step6 保存模型的权重和偏置 model.save('my_model.h5') # creates a HDF5 file 'my_model.h5' # step7 删除模型 del model # deletes the existing model # step8 恢复模型 # returns a compiled model # identical to the previous one restored_model = tf.keras.models.load_model('my_model.h5') # step9 测试模型 loss, acc = restored_model.evaluate(x_test, y_test) print("Restored model, accuracy:{:5.2f}%".format(100 * acc))
train model, accuracy:96.94%
Restored model, accuracy:96.94%
方法3:使用tf.keras.callbacks.ModelCheckpoint方法在训练过程中保存模型
该方法继承自tf.keras.callbacks类,一般配合mode.fit函数使用
以上这篇tensorflow2.0保存和恢复模型3种方法就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持。
免责声明:本站资源来自互联网收集,仅供用于学习和交流,请遵循相关法律法规,本站一切资源不代表本站立场,如有侵权、后门、不妥请联系本站删除!
更新日志
- 凤飞飞《我们的主题曲》飞跃制作[正版原抓WAV+CUE]
- 刘嘉亮《亮情歌2》[WAV+CUE][1G]
- 红馆40·谭咏麟《歌者恋歌浓情30年演唱会》3CD[低速原抓WAV+CUE][1.8G]
- 刘纬武《睡眠宝宝竖琴童谣 吉卜力工作室 白噪音安抚》[320K/MP3][193.25MB]
- 【轻音乐】曼托凡尼乐团《精选辑》2CD.1998[FLAC+CUE整轨]
- 邝美云《心中有爱》1989年香港DMIJP版1MTO东芝首版[WAV+CUE]
- 群星《情叹-发烧女声DSD》天籁女声发烧碟[WAV+CUE]
- 刘纬武《睡眠宝宝竖琴童谣 吉卜力工作室 白噪音安抚》[FLAC/分轨][748.03MB]
- 理想混蛋《Origin Sessions》[320K/MP3][37.47MB]
- 公馆青少年《我其实一点都不酷》[320K/MP3][78.78MB]
- 群星《情叹-发烧男声DSD》最值得珍藏的完美男声[WAV+CUE]
- 群星《国韵飘香·贵妃醉酒HQCD黑胶王》2CD[WAV]
- 卫兰《DAUGHTER》【低速原抓WAV+CUE】
- 公馆青少年《我其实一点都不酷》[FLAC/分轨][398.22MB]
- ZWEI《迟暮的花 (Explicit)》[320K/MP3][57.16MB]