tensorflow保存模型_tensorflow中模型的保存与加载

这个部分讲了三种方法

第一种是只保存模型参数

（剧透一下，只有这个成功了）

这个方法只保留参数，

因此导入的时候要先正常把模型先搭建好，compile完了再把参数赋予给模型

第二个方法，使用model.save方法保存整个模型

用这个方法保存的时候发现不可以用，原因是我的这个网络不是Functional model or a Sequential model。可能是因为我的网络里有自定义层？anyway，前面那个方法能用问题就不大了。

第三个方法是保存为saved_model形式。

据说这个形式适合工业化，适合把模型交付给其他的语言使用。

但是我运行的时候也有点问题，我怀疑是用到的signatures方法没有导入还是啥的，报错是这个

同样，因为有第一个方法兜底，以后有需要用到这个第三种方法的时候再去debug吧！

下面照例贴代码

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

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

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)

class MyDense(layers.Layer):

    def __init__(self, inp_dim, outp_dim):
        super(MyDense, self).__init__()

        self.kernel = self.add_variable('w', [inp_dim, outp_dim])
        self.bias = self.add_variable('b', [outp_dim])

    def call(self, inputs, training = None):

        out = inputs @ self.kernel + self.bias

        return out

class MyModel(keras.Model):

    def __init__(self):
        super(MyModel, self).__init__()

        self.fc1 = MyDense(28*28, 256)
        self.fc2 = MyDense(256, 128)
        self.fc3 = MyDense(128, 64)
        self.fc4 = MyDense(64, 32)
        self.fc5 = MyDense(32, 10)

    def call(self, inputs, training=None):

        x = self.fc1(inputs)
        x = tf.nn.relu(x)
        x = self.fc2(x)
        x = tf.nn.relu(x)
        x = self.fc3(x)
        x = tf.nn.relu(x)
        x = self.fc4(x)
        x = tf.nn.relu(x)
        x = self.fc5(x)

        return x

network = MyModel()

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']   # test
                )

network.fit(db, epochs=10, validation_data=ds_val, validation_freq=2)

network.evaluate(ds_val)



sample = next(iter(ds_val))
x = sample[0]
y = sample[1]  # one-hot
pred = network.predict(x)  # [b, 10]
# convert back to number
y = tf.argmax(y, axis=1)
pred = tf.argmax(pred, axis=1)

print(pred)
print(y)


#第一种方法
#save the weights
network.save_weights('/home/bluecai/pyproject/checkpoints/my_checkpoint')

#restore the weights
reload_model = MyModel()
reload_model.load_weights('/home/bluecai/pyproject/checkpoints/my_checkpoint')
reload_model.compile(optimizer=optimizers.Adam(lr=0.01),
                loss=tf.losses.CategoricalCrossentropy(from_logits=True),
                metrics=['accuracy']   # test
                )
loss, acc = reload_model.evaluate(ds_val)
print("restored model, accuracy: {:5.2f}%".format(100*acc))

#第二种方法
#Saving the model to HDF5 format requires the model to be a Functional model
# or a Sequential model. It does not work for subclassed models,
# because such models are defined via the body of a Python method,
# which isn't safely serializable. Consider saving to the Tensorflow SavedModel format
# (by setting save_format="tf") or using `save_weights`.

# network.save('saved_network.h5')
# print('saved total model.')
#
# print('load model from file')
# reload_model_2 = tf.keras.models.load_model('saved_network.h5')
# loss_2, acc_2 = reload_model_2.evaluate(ds_val)
# print("restored model_2, accuracy: {:5.2f}%".format(100*acc_2))


#第三种方法
# tf.saved_model.save(network, '/home/bluecai/pyproject/tmp/saved_model/')
#
# imported = tf.saved_model.load('/home/bluecai/pyproject/tmp/saved_model/')
# f = imported.signatures["serving_default"]
# print(f(x = tf.ones([1,28,28,3])))