Keras高层API

基本就是4步：
Matrics
update_state
result().numpy()
reset_states(就是清除缓存)

tensorflow2.0代码很简单，就MNIST数据集演示：

import tensorflow as tf
from tensorflow.keras import datasets, layers, optimizers, Sequential, metricsdef 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, ybatchsz = 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=0.001),loss=tf.losses.CategoricalCrossentropy(from_logits=True),metrics=['accuracy'])network.fit(db, epochs=5, validation_data=ds_val, validation_freq=1)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)

结果：

Epoch 5/5
469/469 [==============================] - 2s 4ms/step - loss: 0.0850 - accuracy: 0.9769 - val_loss: 0.1236 - val_accuracy: 0.9688
79/79 [==============================] - 1s 9ms/step - loss: 0.1236 - accuracy: 0.9688
tf.Tensor(
[7 2 1 0 4 1 4 9 6 9 0 6 9 0 1 5 9 7 3 4 9 6 6 5 4 0 7 4 0 1 3 1 3 4 7 2 71 2 1 1 7 4 4 3 5 1 2 4 4 6 3 5 5 6 0 4 1 9 5 7 8 9 3 7 4 6 4 3 0 7 0 2 91 7 3 2 9 7 7 6 2 7 8 4 7 3 6 1 3 6 4 3 1 4 1 7 6 9 6 0 5 4 9 9 2 1 9 4 87 3 9 7 4 4 4 9 2 5 4 7 6 7 9 0 5], shape=(128,), dtype=int64)
tf.Tensor(
[7 2 1 0 4 1 4 9 5 9 0 6 9 0 1 5 9 7 3 4 9 6 6 5 4 0 7 4 0 1 3 1 3 4 7 2 71 2 1 1 7 4 2 3 5 1 2 4 4 6 3 5 5 6 0 4 1 9 5 7 8 9 3 7 4 6 4 3 0 7 0 2 91 7 3 2 9 7 7 6 2 7 8 4 7 3 6 1 3 6 9 3 1 4 1 7 6 9 6 0 5 4 9 9 2 1 9 4 87 3 9 7 4 4 4 9 2 5 4 7 6 7 9 0 5], shape=(128,), dtype=int64)

CIFAR10实战，利用自定义层处理

import tensorflow as tf
from tensorflow.keras import datasets, layers, optimizers, Sequential, metrics
from tensorflow import kerasdef preprocess(x, y):# 范围转换从[0,255] => [-1,1]x = 2 * tf.cast(x, dtype=tf.float32) / 255.0 - 1.0y = tf.cast(y, dtype=tf.float32)return x, ybatchsz = 128
# [50000,32,32,3], [50000,1,10]
(x, y), (x_val, y_val) = datasets.cifar10.load_data()
# 默认删除所有为1的维度
y = tf.squeeze(y)
y_val = tf.squeeze(y_val)
y = tf.one_hot(y, depth=10)  # [50000, 10]
y_val = tf.one_hot(y_val, depth=10)  # [10000, 10]
print("datasets:", x.shape, y.shape, x_val.shape, y_val.shape)train_db = tf.data.Dataset.from_tensor_slices((x, y))
train_db = train_db.map(preprocess).shuffle(10000).batch(batchsz)
test_db = tf.data.Dataset.from_tensor_slices((x_val, y_val))
test_db = test_db.map(preprocess).batch(batchsz)sample = next(iter(train_db))
print(sample[0].shape, sample[1].shape)class MyDense(layers.Layer):# 代替了标准的layers.Dense()def __init__(self, inp_dim, out_dim):super(MyDense, self).__init__()self.kernel = self.add_weight('w', [inp_dim, out_dim])# self.bias = self.add_variable('b', [out_dim])def call(self, inputs, training=None):x = inputs @ self.kernelreturn xclass MyNetwork(keras.Model):def __init__(self):super(MyNetwork, self).__init__()self.fc1 = MyDense(32 * 32 * 3, 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):''':param inputs: [b, 32, 32, 3]:param training::return:'''x = tf.reshape(inputs, [-1, 32 * 32 * 3])# 转换维度, [b, 32*32*3] => [b, 256]x = self.fc1(x)x = tf.nn.relu(x)# 转换维度, [b, 256] => [b, 128]x = self.fc2(x)x = tf.nn.relu(x)# 转换维度, [b, 128] => [b, 64]x = self.fc3(x)x = tf.nn.relu(x)# 转换维度, [b, 64] => [b, 32]x = self.fc4(x)x = tf.nn.relu(x)# 转换维度, [b, 32] => [b, 10]x = self.fc5(x)return xnetwork = MyNetwork()
network.compile(optimizer=optimizers.Adam(lr=1e-3),loss=tf.losses.CategoricalCrossentropy(from_logits=True),metrics=['accuracy'])
network.fit(train_db, epochs=15, validation_data=test_db, validation_freq=1)network.evaluate(test_db)
network.save_weights('ckpt/weights.ckpt')
del network
print("saved to ckpt/weights.ckpt")network = MyNetwork()
network.compile(optimizer=optimizers.Adam(lr=1e-3),loss=tf.losses.CategoricalCrossentropy(from_logits=True),metrics=['accuracy'])
network.load_weights('ckpt/weights.ckpt')
print("loaded weights from files")
network.evaluate(test_db)

结果：

Epoch 15/15
391/391 [==============================] - 2s 6ms/step - loss: 0.7328 - accuracy: 0.7411 - val_loss: 1.7053 - val_accuracy: 0.5153
79/79 [==============================] - 0s 4ms/step - loss: 1.7053 - accuracy: 0.5153
saved to ckpt/weights.ckpt
loaded weights from files
79/79 [==============================] - 0s 4ms/step - loss: 1.7053 - accuracy: 0.5153

模型的保存和加载

保存权值

上个cifar10例子就有保存权值的例子。

保存整个模型（包括权值）

import  os
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'import  tensorflow as tf
from    tensorflow.keras import datasets, layers, optimizers, Sequential, metricsdef 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,ybatchsz = 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 networkprint('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)

其实都是差不多的，只是再加载时，不用创建网络模型了，加载时直接加载整个模型和权值，然后再直接训练，虽然可以完整保存和加载，但占用的存储空间很大，加载时也很慢，所以我们一般只保存权值参数，网络模型一般是不变的，所以不用保存。

本站所有文章均为原创，欢迎转载，请注明文章出处：https://blog.csdn.net/weixin_45092662。百度和各类采集站皆不可信，搜索请谨慎鉴别。技术类文章一般都有时效性，本人习惯不定期对自己的博文进行修正和更新，因此请访问出处以查看本文的最新版本。

tensorflow2.0学习笔记（五）相关推荐

TensorFlow2.0 学习笔记（三）：卷积神经网络（CNN）
欢迎关注WX公众号:[程序员管小亮] 专栏--TensorFlow学习笔记文章目录欢迎关注WX公众号:[程序员管小亮] 专栏--TensorFlow学习笔记一.神经网络的基本单位:神经元二.卷 ...
Tensorflow2.0学习笔记（一）
Tensorflow2.0学习笔记(一)--MNIST入门文章目录 Tensorflow2.0学习笔记(一)--MNIST入门前言一.MNIST是什么? 二.实现步骤及代码 1.引入库 2.下载 ...
Tensorflow2.0学习笔记（二）
Tensorflow2.0学习笔记(二)--Keras练习文章目录 Tensorflow2.0学习笔记(二)--Keras练习前言二.使用步骤 1.实现步骤及代码 2.下载 Fashion MN ...
Tensorflow2.0学习笔记（一）北大曹健老师教学视频1-4讲
Tensorflow2.0学习笔记(一)北大曹健老师教学视频1-4讲返回目录这个笔记现在是主要根据北京大学曹健老师的视频写的,这个视频超级棒,非常推荐. 第一讲常用函数的使用(包含了很多琐碎的函 ...
Tensorflow2.0学习笔记（二）北大曹健老师教学视频第五讲
Tensorflow2.0学习笔记(二)北大曹健老师教学视频第五讲返回目录理论部分主要写点以前看吴恩达视频没有的或者不太熟悉的了. 5.1卷积计算过程实际项目中的照片多是高分辨率彩色图,但待优化 ...
Tensorflow2.0学习（五） — Keras基础应用（IMDb电影集情感分析)
今天这一节内容是关于Keras应用分析的最后一节,在熟悉了Keras的基础知识之后,下面几节我们就可以正式接触Tensorflow2.0.根据博主多处查阅,最终还是发现Tensorflow的官方教程好 ...
tensorflow2.0 学习笔记：一、神经网络计算
mooc课程Tensorflow2.0 笔记人工智能三学派行为主义:基于控制论,构建感知-动作控制系统(自适应控制系统) 符号主义:基于算数逻辑表达式,求解问题时先把问题描述为表达式,再求解表达式 ...
TensorFlow2.0学习笔记2-tf2.0两种方式搭建神经网络
目录一,TensorFlow2.0搭建神经网络八股 1)import [引入相关模块] 2)train,test [告知喂入网络的训练集测试集以及相应的标签] 3)model=tf.keras. ...
神经网络与深度学习——TensorFlow2.0实战(笔记)(五)(NumPy科学计算库＜1＞python)
多维数组形状(Shape): 是一个元组,描述数组的维度,以及各个维度的长度. 长度(Length): 某个维度中的元素个数. 数字单门课程成绩 1*课程成绩一维数组多门课程成绩 n*课程成绩 ...

tensorflow2.0学习笔记（五）