TensorFlow2_200729系列---21、Keras模型保存与加载

TensorFlow2_200729系列---21、Keras模型保存与加载

一、总结

一句话总结：

模型保存：save方法：network.save('model.h5')

模型加载：load_model方法：network = tf.keras.models.load_model('model.h5', compile=False)

二、Keras模型保存与加载

博客对应课程的视频位置：

import  os
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'

import  tensorflow as tf
from    tensorflow.keras import datasets, layers, optimizers, Sequential, metrics


def preprocess(x, y):
    """
    x is a simple image, not a batch
    """
    x = tf.cast(x, dtype=tf.float32) / 255.
    x = tf.reshape(x, [28*28])
    y = tf.cast(y, dtype=tf.int32)
    y = tf.one_hot(y, depth=10)
    return x,y


batchsz = 128
(x, y), (x_val, y_val) = datasets.mnist.load_data()
print('datasets:', x.shape, y.shape, x.min(), x.max())



db = tf.data.Dataset.from_tensor_slices((x,y))
db = db.map(preprocess).shuffle(60000).batch(batchsz)
ds_val = tf.data.Dataset.from_tensor_slices((x_val, y_val))
ds_val = ds_val.map(preprocess).batch(batchsz) 

sample = next(iter(db))
print(sample[0].shape, sample[1].shape)


network = Sequential([layers.Dense(256, activation='relu'),
                     layers.Dense(128, activation='relu'),
                     layers.Dense(64, activation='relu'),
                     layers.Dense(32, activation='relu'),
                     layers.Dense(10)])
network.build(input_shape=(None, 28*28))
network.summary()




network.compile(optimizer=optimizers.Adam(lr=0.01),
		loss=tf.losses.CategoricalCrossentropy(from_logits=True),
		metrics=['accuracy']
	)

network.fit(db, epochs=3, validation_data=ds_val, validation_freq=2)
 
network.evaluate(ds_val)

network.save('model.h5')
print('saved total model.')
del network

print('loaded model from file.')
network = tf.keras.models.load_model('model.h5', compile=False)
network.compile(optimizer=optimizers.Adam(lr=0.01),
        loss=tf.losses.CategoricalCrossentropy(from_logits=True),
        metrics=['accuracy']
    )
x_val = tf.cast(x_val, dtype=tf.float32) / 255.
x_val = tf.reshape(x_val, [-1, 28*28])
y_val = tf.cast(y_val, dtype=tf.int32)
y_val = tf.one_hot(y_val, depth=10)
ds_val = tf.data.Dataset.from_tensor_slices((x_val, y_val)).batch(128)
network.evaluate(ds_val)

datasets: (60000, 28, 28) (60000,) 0 255
(128, 784) (128, 10)
Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense (Dense)                multiple                  200960    
_________________________________________________________________
dense_1 (Dense)              multiple                  32896     
_________________________________________________________________
dense_2 (Dense)              multiple                  8256      
_________________________________________________________________
dense_3 (Dense)              multiple                  2080      
_________________________________________________________________
dense_4 (Dense)              multiple                  330       
=================================================================
Total params: 244,522
Trainable params: 244,522
Non-trainable params: 0
_________________________________________________________________
Epoch 1/3
469/469 [==============================] - 2s 4ms/step - loss: 0.2773 - accuracy: 0.9168
Epoch 2/3
469/469 [==============================] - 3s 7ms/step - loss: 0.1314 - accuracy: 0.9639 - val_loss: 0.1501 - val_accuracy: 0.9580
Epoch 3/3
469/469 [==============================] - 2s 4ms/step - loss: 0.1028 - accuracy: 0.9711
79/79 [==============================] - 1s 10ms/step - loss: 0.1232 - accuracy: 0.9662
saved total model.
loaded model from file.
79/79 [==============================] - 0s 2ms/step - loss: 0.1232 - accuracy: 0.9662

Out[1]:

[0.12320274859666824, 0.9661999940872192]

In [ ]: