标签：续训 local Tensorflow2.0 tf train test path model 断点

参考: https://www.bilibili.com/video/BV16A41157LW?p=17
视频及课件来源 北京大学 曹建
使用的识别图片

获取训练数据集

def get_mnist_data():
    # 参考: https://www.codenong.com/53310656/
    # 获取数据 return  (x_train, y_train), (x_test, y_test)
    (x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
    # 数据归一化 0-255之间的灰度值变成 变成0 或者 1
    # 把输入特征的数值变小 更利于神经网络的吸收
    x_train, x_test = (x_train > 128).astype(int), (x_test > 128).astype(int)
    return (x_train, y_train), (x_test, y_test)

加载训练模型

def local_load_weights(checkpoint_save_path):
    local_weights_model = tf.keras.models.Sequential([
        tf.keras.layers.Flatten(),
        tf.keras.layers.Dense(128, activation='relu'),
        tf.keras.layers.Dense(10, activation='softmax')
    ])
    local_weights_model.compile(optimizer='adam',
                                loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
                                metrics=['sparse_categorical_accuracy'])
    if os.path.exists(checkpoint_save_path + '.index'):
        tf.print('-------------load the model-----------------')
        local_weights_model.load_weights(checkpoint_save_path)
    return local_weights_model

断点续练

def weights_train(local_weights_model, checkpoint_save_path):
    # 回调函数 用于保存模型
    cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_save_path,  # 文件存储路径
                                                     save_weights_only=True,  # 是否只保留模型参数
                                                     save_best_only=True)  # 是否只保留最优结果
    (x_train, y_train), (x_test, y_test) = get_mnist_data()
    history = local_weights_model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test),
                                      validation_freq=1,
                                      callbacks=[cp_callback])  # fit中假如回调函数

还有一种方法
加载模型

def local_load_model(model_path):
    if os.path.exists(model_path + '/saved_model.pb'):
        tf.print('-------------load the model-----------------')
        local_model = tf.keras.models.load_model(model_path)
    else:
        local_model = tf.keras.models.Sequential([
            tf.keras.layers.Flatten(),  # 拉直层  将数据拉直成1维
            tf.keras.layers.Dense(128, activation='relu'),
            tf.keras.layers.Dense(10, activation='softmax')
        ])
        local_model.compile(optimizer='adam',
                            loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
                            metrics=['sparse_categorical_accuracy'])
    return local_model

训练

 (x_train, y_train), (x_test, y_test) = get_mnist_data()
    history = local_model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test),
                              validation_freq=1)

整个文件如下

# -*- coding: utf-8 -*-

import tensorflow as tf
import os
import numpy as np
from PIL import Image
from matplotlib import pyplot as plt


def get_mnist_data():
    # 参考: https://www.codenong.com/53310656/
    # 获取数据 return  (x_train, y_train), (x_test, y_test)
    (x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
    # 数据归一化 0-255之间的灰度值变成 变成0 或者 1
    # 把输入特征的数值变小 更利于神经网络的吸收
    x_train, x_test = (x_train > 128).astype(int), (x_test > 128).astype(int)
    return (x_train, y_train), (x_test, y_test)


def get_local_image():
    img = Image.open('./data/image/2.jpg')  # 载入自己的图片
    img = img.resize((28, 28))  # 设置图片大小
    gray_img = img.convert('L')
    mun_img = np.array(gray_img)
    # convert.show()
    mun_img = (mun_img > 64).astype(int)
    x_test__reshape = mun_img.reshape(1, 28, 28)
    return x_test__reshape


def local_load_weights(checkpoint_save_path):
    local_weights_model = tf.keras.models.Sequential([
        tf.keras.layers.Flatten(),
        tf.keras.layers.Dense(128, activation='relu'),
        tf.keras.layers.Dense(10, activation='softmax')
    ])
    local_weights_model.compile(optimizer='adam',
                                loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
                                metrics=['sparse_categorical_accuracy'])
    if os.path.exists(checkpoint_save_path + '.index'):
        tf.print('-------------load the model-----------------')
        local_weights_model.load_weights(checkpoint_save_path)
        tf.print("加载文件参数")
    return local_weights_model


def local_load_model(model_path):
    if os.path.exists(model_path + '/saved_model.pb'):
        tf.print('-------------load the model-----------------')
        local_model = tf.keras.models.load_model(model_path)
    else:
        local_model = tf.keras.models.Sequential([
            tf.keras.layers.Flatten(),  # 拉直层  将数据拉直成1维
            tf.keras.layers.Dense(128, activation='relu'),
            tf.keras.layers.Dense(10, activation='softmax')
        ])
        local_model.compile(optimizer='adam',
                            loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
                            metrics=['sparse_categorical_accuracy'])
    return local_model


# 断点续练
def weights_train(local_weights_model, checkpoint_save_path):
    # 回调函数 用于保存模型
    cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_save_path,  # 文件存储路径
                                                     save_weights_only=True,  # 是否只保留模型参数
                                                     save_best_only=True)  # 是否只保留最优结果
    (x_train, y_train), (x_test, y_test) = get_mnist_data()
    history = local_weights_model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test),
                                      validation_freq=1,
                                      callbacks=[cp_callback])  # fit中假如回调函数
    local_weights_model.summary()
    show_train_line(history)


def show_train_line(history):
    # 显示训练集和验证集的acc和loss曲线
    acc = history.history['sparse_categorical_accuracy']
    val_acc = history.history['val_sparse_categorical_accuracy']
    loss = history.history['loss']
    val_loss = history.history['val_loss']

    plt.subplot(1, 2, 1)
    plt.plot(acc, label='Training Accuracy')
    plt.plot(val_acc, label='Validation Accuracy')
    plt.title('Training and Validation Accuracy')
    plt.legend()

    plt.subplot(1, 2, 2)
    plt.plot(loss, label='Training Loss')
    plt.plot(val_loss, label='Validation Loss')
    plt.title('Training and Validation Loss')
    plt.legend()
    plt.show()


def forecast_demo(model):
    # 预测
    local_image = get_local_image()
    loaded_evaluate = model.predict(local_image)
    print(loaded_evaluate)
    prediction = np.argmax(loaded_evaluate, axis=1)  # 找出最大值
    print('预测结果：', prediction)


def demo_1():
    checkpoint_path = "./data/model/checkpoint/mnist.ckpt"
    local_weights_model = local_load_weights(checkpoint_path)
    # 继续训练
    weights_train(local_weights_model, checkpoint_path)
    forecast_demo(local_weights_model)


def demo_2():
    model_path = "./data/model/breakpoint"
    local_model = local_load_model(model_path)
    (x_train, y_train), (x_test, y_test) = get_mnist_data()
    history = local_model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test),
                              validation_freq=1)
    show_train_line(history)
    local_model.summary()
    #   保存模型
    local_model.save(model_path, save_format="tf")
    forecast_demo(local_model)


if __name__ == '__main__':
    demo_1()
    # demo_2()

标签：续训,local,Tensorflow2.0,tf,train,test,path,model,断点
来源： https://blog.csdn.net/xy3233/article/details/122784726

本站声明： 1. iCode9 技术分享网（下文简称本站）提供的所有内容，仅供技术学习、探讨和分享；
2. 关于本站的所有留言、评论、转载及引用，纯属内容发起人的个人观点，与本站观点和立场无关；
3. 关于本站的所有言论和文字，纯属内容发起人的个人观点，与本站观点和立场无关；
4. 本站文章均是网友提供，不完全保证技术分享内容的完整性、准确性、时效性、风险性和版权归属；如您发现该文章侵犯了您的权益，可联系我们第一时间进行删除；
5. 本站为非盈利性的个人网站，所有内容不会用来进行牟利，也不会利用任何形式的广告来间接获益，纯粹是为了广大技术爱好者提供技术内容和技术思想的分享性交流网站。