标签：实战 val 自定义 CIFAR10 32 self db tf network

Tips:

人工智能难题不仅是计算机科学问题，更是数学、认知
科学和哲学问题。− François Chollet

代码

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import tensorflow as tf
from tensorflow.keras import datasets, layers, optimizers, Sequential, metrics
from tensorflow import keras


def preprocess(x, y):
    # [0, 255] --> [-1,1]
    x = 2 * tf.cast(x, dtype=tf.float32) / 255. - 1.
    y = tf.cast(y, dtype=tf.int32)

    return x, y


batch_size = 128
# x --> [32,32,3], y --> [10k, 1]
(x, y), (x_val, y_val) = datasets.cifar10.load_data()
y = tf.squeeze(y)  # [10k, 1] --> [10k]
y_val = tf.squeeze(y_val)
y = tf.one_hot(y, depth=10)  # [50k, 10]
y_val = tf.one_hot(y_val, depth=10)  # [10k, 10]
print('datasets:', x.shape, y.shape, x_val.shape, y_val.shape, x.min(),
      x.max())

# 构建数据集
train_db = tf.data.Dataset.from_tensor_slices((x, y))
train_db = train_db.map(preprocess).shuffle(10000).batch(batch_size)
test_db = tf.data.Dataset.from_tensor_slices((x_val, y_val))
test_db = test_db.map(preprocess).batch(batch_size)

sample = next(iter(train_db))
print('batch:', sample[0].shape, sample[1].shape)


# 新建网络对象
class MyDense(layers.Layer):
    # to replace standard layers.Dense()
    def __init__(self, inp_dim, outp_dim):
        super(MyDense, self).__init__()

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

    def call(self, inputs, training=None):
        x = inputs @ self.kernel
        return x


# 自定义网络层
class 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):
        """inputs: [b,32,32,3]"""
        x = tf.reshape(inputs, [-1, 32 * 32 * 3])
        # [b,32*32*3] --> [b, 256]
        x = self.fc1(x)
        x = tf.nn.relu(x)
        # [b, 256] --> [b,128]
        x = self.fc2(x)
        x = tf.nn.relu(x)
        # [b, 128] --> [b,64]
        x = self.fc3(x)
        x = tf.nn.relu(x)
        # [b, 64] --> [b,32]
        x = self.fc4(x)
        x = tf.nn.relu(x)
        # [b, 32] --> [b,10]
        x = self.fc5(x)

        return x


network = MyNetwork()
# 装配
network.compile(optimizer=optimizers.Adam(lr=1e-3),
                loss=tf.losses.CategoricalCrossentropy(from_logits=True),
                metrics=['accuracy'])
# 训练
network.fit(train_db, epochs=5, validation_data=test_db, validation_freq=1)

network.evaluate(test_db)
network.save_weights('ckpt/weights.ckpt')  # 模型的保存
del network
print('saved to ckpt/weights.ckpt')

# 模型的加载
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 file.')

network.evaluate(test_db)

标签：实战,val,自定义,CIFAR10,32,self,db,tf,network
来源： https://www.cnblogs.com/lanercifang/p/16574131.html

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。