深度学习2.0-31.CIFAR100与VGG13实战

首页 » 算法 » 正文

1.介绍

深度学习2.0-31.CIFAR100与VGG13实战

深度学习2.0-31.CIFAR100与VGG13实战
深度学习2.0-31.CIFAR100与VGG13实战

2.CIFAR100实战

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

# 解决了UnknownError: Failed to get convolution algorithm. This is probably 
# because cuDNN failed to initialize, so try looking to see if a warning log
#  message was printed above. [Op:Conv2D]
from tensorflow.compat.v1 import ConfigProto
from tensorflow.compat.v1 import InteractiveSession
config = ConfigProto()
config.gpu_options.allow_growth = True
session = InteractiveSession(config=config)

# 10层的卷积与3层的全连接层
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers,optimizers,datasets,Sequential

tf.random.set_seed(2345)


# 组建Sequential的list
conv_layers = [# 5 units of conv + max pooling
    # unit 1
    layers.Conv2D(64,kernel_size=[3,3],padding='same',activation=tf.nn.relu),
    layers.Conv2D(64,kernel_size=[3,3],padding='same',activation=tf.nn.relu),
    layers.MaxPool2D(pool_size=[2,2],strides=2,padding='same'),
    # unit 2
    layers.Conv2D(128,kernel_size=[3,3],padding='same',activation=tf.nn.relu),
    layers.Conv2D(128,kernel_size=[3,3],padding='same',activation=tf.nn.relu),
    layers.MaxPool2D(pool_size=[2,2],strides=2,padding='same'),
    # unit 3
    layers.Conv2D(256,kernel_size=[3,3],padding='same',activation=tf.nn.relu),
    layers.Conv2D(256,kernel_size=[3,3],padding='same',activation=tf.nn.relu),
    layers.MaxPool2D(pool_size=[2,2],strides=2,padding='same'),
    # unit 4
    layers.Conv2D(512,kernel_size=[3,3],padding='same',activation=tf.nn.relu),
    layers.Conv2D(512,kernel_size=[3,3],padding='same',activation=tf.nn.relu),
    layers.MaxPool2D(pool_size=[2,2],strides=2,padding='same'),
    # unit 5
    layers.Conv2D(512,kernel_size=[3,3],padding='same',activation=tf.nn.relu),
    layers.Conv2D(512,kernel_size=[3,3],padding='same',activation=tf.nn.relu),
    layers.MaxPool2D(pool_size=[2,2],strides=2,padding='same')
]

# 预处理函数
def preprocess(x,y):
    # [0-1]
    x = tf.cast(x,dtype=tf.float32) /255.
    y = tf.cast(y,dtype=tf.int32)
    return x,y

# 加载数据集
(x,y),(x_test,y_test) = datasets.cifar100.load_data()
# 消去y的1维度
y = tf.squeeze(y,axis=1)
y_test = tf.squeeze(y_test,axis=1)
print(x.shape,y.shape,x_test.shape,y_test.shape)
# (50000, 32, 32, 3) (50000, ) (10000, 32, 32, 3) (10000, )

train_db = tf.data.Dataset.from_tensor_slices((x,y))
train_db = train_db.map(preprocess).shuffle(10000).batch(128)

test_db = tf.data.Dataset.from_tensor_slices((x_test,y_test))
test_db = test_db.map(preprocess).batch(128)

sample = next(iter(train_db))
print('sample:',sample[0].shape,sample[1].shape,
      tf.reduce_min(sample[0]),tf.reduce_max(sample[0]))
# sample: (64, 32, 32, 3) (64, ) tf.Tensor(0.0, shape=(), dtype=float32) tf.Tensor(1.0, shape=(), dtype=float32)


def main():
    # 构建多层网络
    # [b,32,32,3] => [b,1,1,512]
    conv_net = Sequential(conv_layers)

    # 构建全连接层
    fc_net = Sequential([
        layers.Dense(256,activation=tf.nn.relu),
        layers.Dense(128,activation=tf.nn.relu),
        layers.Dense(100,activation=None),
    ])
    conv_net.build(input_shape=[None, 32, 32, 3])
    fc_net.build(input_shape=[None,512])

    # 所有的训练参数
    variables = conv_net.trainable_variables + fc_net.trainable_variables

    # 优化器
    optimizer = optimizers.Adam(lr=1e-4)

    for epoch in range(50):
        for step,(x,y) in enumerate(train_db):

            with tf.GradientTape() as tape:
                # [b,32,32,3] => [b,1,1,512]
                out = conv_net(x)
                # 相当于flatten层-打平
                out = tf.reshape(out,[-1,512])
                # [b,512] => [b,100]
                logits = fc_net(out)
                # [b] =>[b,100]
                y_onehot = tf.one_hot(y,depth=100)

                # compute loss
                loss = tf.losses.categorical_crossentropy(y_onehot,logits,from_logits=True)
                loss = tf.reduce_mean(loss)

            grads = tape.gradient(loss,variables)
            optimizer.apply_gradients(zip(grads,variables))

            if step % 100 ==0:
                print(epoch,step,'loss:',float(loss))


        total_num,total_correct = 0,0
        for x,y in test_db:
            out = conv_net(x)
            out = tf.reshape(out,[-1,512])
            logits = fc_net(out)
            prob = tf.nn.softmax(logits,axis=1)

            pred = tf.argmax(prob,axis=1)
            pred = tf.cast(pred,dtype=tf.int32)
            correct = tf.cast(tf.equal(pred,y),dtype=tf.int32)
            correct = tf.reduce_sum(correct)

            total_num += x.shape[0]
            total_correct += int(correct)

        acc = total_correct / total_num
        print(epoch,'acc:',acc)


if __name__ == '__main__':
    main()

未经允许不得转载:作者:1147-柳同学, 转载或复制请以 超链接形式 并注明出处 拜师资源博客
原文地址:《深度学习2.0-31.CIFAR100与VGG13实战》 发布于2020-10-12

分享到:
赞(0) 打赏

评论 抢沙发

评论前必须登录!

  注册



长按图片转发给朋友

觉得文章有用就打赏一下文章作者

支付宝扫一扫打赏

微信扫一扫打赏

Vieu3.3主题
专业打造轻量级个人企业风格博客主题!专注于前端开发,全站响应式布局自适应模板。

登录

忘记密码 ?

您也可以使用第三方帐号快捷登录

Q Q 登 录
微 博 登 录