5 模型保存与加载

一 keras模型保存与加载

搭建模型并训练

import numpy as np
import tensorflow as tf
x_train = np.random.random((1000, 32))
y_train = np.random.randint(10, size=(1000, ))
x_val = np.random.random((200, 32))
y_val = np.random.randint(10, size=(200, ))
x_test = np.random.random((200, 32))
y_test = np.random.randint(10, size=(200, ))

# 函数式
def get_uncompiled_model():
    inputs = tf.keras.Input(shape=(32,), name='digits')
    x = tf.keras.layers.Dense(64, activation='relu', name='dense_1')(inputs)
    x = tf.keras.layers.Dense(64, activation='relu', name='dense_2')(x)
    outputs = tf.keras.layers.Dense(10, name='predictions')(x)
    model = tf.keras.Model(inputs=inputs, outputs=outputs)
    return model


def get_compiled_model():
    model = get_uncompiled_model()
    model.compile(optimizer=tf.keras.optimizers.RMSprop(learning_rate=1e-3),
                  loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
                  metrics=['sparse_categorical_accuracy'])
    return model

model = get_compiled_model()
model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_val, y_val))

四种保存加载方式

方法一有两种

# 保存与加载，只保存了权重，加载权重之前需要先把模型搭建出来
model.save_weights("adasd.h5")

model.load_weights("adasd.h5")
model.predict(x_test)

model.save_weights('./checkpoints/mannul_checkpoint')
model.load_weights('./checkpoints/mannul_checkpoint')
model.predict(x_test)

方法二

# 加载模型时不需要搭建模型
# Export the model to a SavedModel
model.save('keras_model_tf_version', save_format='tf')

# Recreate the exact same model
new_model = tf.keras.models.load_model('keras_model_tf_version')
new_model.predict(x_test)

方法三

# 保存hdf5格式
model.save('keras_model_hdf5_version.h5')

new_model = tf.keras.models.load_model('keras_model_hdf5_version.h5')
new_model.predict(x_test)

方法四常在模型部署时用到

# 保存模型部署的格式
tf.saved_model.save(model,'tf_saved_model_version')
restored_saved_model = tf.saved_model.load('tf_saved_model_version')
f = restored_saved_model.signatures["serving_default"]

f(digits = tf.constant(x_test.tolist()) )

# 显示需要的信息
!saved_model_cli show --dir tf_saved_model_version --all

2 自定义版本模型保存与加载

保存和加载方式除了方法三不能用，其它都是一样的

import tensorflow as tf
import numpy as np
x_train = np.random.random((1000, 32))
y_train = np.random.random((1000, 10))
x_val = np.random.random((200, 32))
y_val = np.random.random((200, 10))
x_test = np.random.random((200, 32))
y_test = np.random.random((200, 10))

class MyModel(tf.keras.Model):

    def __init__(self, num_classes=10):
        super(MyModel, self).__init__(name='my_model')
        self.num_classes = num_classes
        # 定义自己需要的层
        self.dense_1 = tf.keras.layers.Dense(32, activation='relu')
        self.dense_2 = tf.keras.layers.Dense(num_classes)
    
    @tf.function(input_signature=[tf.TensorSpec([None,32], tf.float32,name='digits')])
    def call(self, inputs):
        #定义前向传播
        # 使用在 (in `__init__`)定义的层
        x = self.dense_1(inputs)
        return self.dense_2(x)

# 优化器
optimizer = tf.keras.optimizers.SGD(learning_rate=1e-3)
# 损失函数
loss_fn = tf.keras.losses.CategoricalCrossentropy(from_logits=True)

# 准备metrics函数
train_acc_metric = tf.keras.metrics.CategoricalAccuracy()
val_acc_metric = tf.keras.metrics.CategoricalAccuracy()

# 准备训练数据集
batch_size = 64
train_dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train))
train_dataset = train_dataset.shuffle(buffer_size=1024).batch(batch_size)

# 准备测试数据集
val_dataset = tf.data.Dataset.from_tensor_slices((x_val, y_val))
val_dataset = val_dataset.batch(64)

model = MyModel(num_classes=10)
epochs = 3
for epoch in range(epochs):
    print('Start of epoch %d' % (epoch,))

    # 遍历数据集的batch_size
    for step, (x_batch_train, y_batch_train) in enumerate(train_dataset):
        with tf.GradientTape() as tape:
            logits = model(x_batch_train)
            loss_value = loss_fn(y_batch_train, logits)
        grads = tape.gradient(loss_value, model.trainable_weights)
        optimizer.apply_gradients(zip(grads, model.trainable_weights))

        # 更新训练集的metrics
        train_acc_metric(y_batch_train, logits)

        # 每200 batches打印一次.
        if step % 200 == 0:
            print('Training loss (for one batch) at step %s: %s' % (step, float(loss_value)))
            print('Seen so far: %s samples' % ((step + 1) * 64))

    # 在每个epoch结束时显示metrics。
    train_acc = train_acc_metric.result()
    print('Training acc over epoch: %s' % (float(train_acc),))
    # 在每个epoch结束时重置训练指标
    train_acc_metric.reset_states()

    # 在每个epoch结束时运行一个验证集。
    for x_batch_val, y_batch_val in val_dataset:
        val_logits = model(x_batch_val)
        # 更新验证集merics
        val_acc_metric(y_batch_val, val_logits)
    val_acc = val_acc_metric.result()
    val_acc_metric.reset_states()
    print('Validation acc: %s' % (float(val_acc),))

训练好之后就是保存模型了