CIFAR10
"""
cifar100数据集处理
使用 VGG13 网络层
"""
import os
import tensorflow as tf
from tensorflow.keras import layers, Sequential, datasets, optimizers
os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"
tf.random.set_seed(2345)
# GPU设置
gpu_lst = tf.config.experimental.list_physical_devices("GPU")
print("GPU:{}个".format(len(gpu_lst)))
for gpu in gpu_lst:
tf.config.experimental.set_memory_growth(gpu, True)
# 1.load data_sets 数据集的加载
def pre_process(x_data, y_data):
# 数据范围 (0-255) ==> (0-1])
x_data = tf.cast(x_data, dtype=tf.float32) / 255.
# 数据类型 tf.int32 y:(0-99)
y_data = tf.cast(y_data, dtype=tf.int32)
return x_data, y_data
# 加载默认数据集:cifar-100
(x, y), (x_test, y_test) = datasets.cifar10.load_data()
# y (50000,1) ==>(50000,)
y = tf.squeeze(y, axis=1)
# y_test (10000,1) ==>(10000,)
y_test = tf.squeeze(y_test, axis=1)
print(x.shape, y.shape, x_test.shape, y_test.shape)
# 训练集 dataset 数据集生成(做简单的预处理 + batch)
train_db = tf.data.Dataset.from_tensor_slices((x, y))
train_db = train_db.shuffle(1000).map(pre_process).batch(128)
# 测试集 dataset 数据集生成(做简单的预处理 + batch)
test_db = tf.data.Dataset.from_tensor_slices((x_test, y_test))
test_db = test_db.map(pre_process).batch(64)
# 数据维度确认
sample = next(iter(train_db))
# x,y的维度 x的最小值与最大值
print("sample:", sample[0].shape, sample[1].shape,
tf.reduce_min(sample[0]), tf.reduce_max(sample[0]))
# 2.build network 构建网络结构与创建
vgg16 = [ # 5 unit of conf + max pooling
# unit 1 [b, 32, 32, 3]
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"),
# [b, 16, 16, 64]
# 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"),
# [b, 8, 8, 128]
# 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.Conv2D(256, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
layers.MaxPool2D(pool_size=[2, 2], strides=2, padding="same"),
# [b, 4, 4, 256]
# 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.Conv2D(512, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
layers.MaxPool2D(pool_size=[2, 2], strides=2, padding="same"),
# [b, 2, 2, 512]
# 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.Conv2D(512, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
layers.MaxPool2D(pool_size=[2, 2], strides=2, padding="same"),
# [b, 1, 1, 512]
# [b, 1, 1, 512] ==> [b, 512]
layers.Flatten(),
# 全连接
layers.Dense(4096, activation=tf.nn.relu),
layers.Dense(4096, activation=tf.nn.relu),
layers.Dense(10,activation='softmax')
]
def main():
# 创建网络结构
vgg16_net = Sequential(vgg16)
# x = tf.random.normal([4, 32, 32, 3])
# vgg13 网络的创建
vgg16_net.build(input_shape=[None, 32, 32, 3])
# out = vgg13_net(x)
# print(out.shape)
# 设置优化器
optimizer = optimizers.Adam(lr=1e-4)
# 设置可训练参数
variables = vgg16_net.trainable_variables
# 3.Train 循环训练
for epoch in range(300):
for step, (x, y) in enumerate(train_db):
with tf.GradientTape() as tape:
# 前向传播
# [b, 32, 32,3] => [b, 100]
y_prd = vgg16_net(x)
# [b,] => [b, 100]
y_true = tf.one_hot(y, depth=10)
# 损失函数计算
loss = tf.losses.categorical_crossentropy(y_true, y_prd, from_logits=True)
loss = tf.reduce_mean(loss)
# 梯度计算
grads = tape.gradient(loss, variables)
# 优化器更新参数
optimizer.apply_gradients(zip(grads, variables))
# 打印结果
if step % 100 == 0:
print(epoch, step, "loss:", float(loss))
# 4.Test 计算正确率
total_num = 0
total_correct = 0
for x, y in test_db:
# 前向传播
y_prd = vgg16_net(x)
prob = tf.nn.softmax(y_prd, axis=1)
pred = tf.argmax(prob, axis=1)
pred = tf.cast(pred, dtype=tf.int32)
# 计算正确数
# [b, bool] ==> [b, int32]
correct = tf.cast(tf.equal(pred, y), dtype=tf.int32)
correct = tf.reduce_sum(correct)
# 累加总数与正确数
total_num += x.shape[0]
total_correct += int(correct)
# 计算正确率
acc = total_correct / total_num
print(epoch, "acc:", acc)
if __name__ == '__main__':
main()
CIFAR100
"""
cifar100数据集处理
使用 VGG13 网络层
"""
import os
import tensorflow as tf
from tensorflow.keras import layers, Sequential, datasets, optimizers
os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"
tf.random.set_seed(2345)
# GPU设置
gpu_lst = tf.config.experimental.list_physical_devices("GPU")
print("GPU:{}个".format(len(gpu_lst)))
for gpu in gpu_lst:
tf.config.experimental.set_memory_growth(gpu, True)
# 1.load data_sets 数据集的加载
def pre_process(x_data, y_data):
# 数据范围 (0-255) ==> (0-1])
x_data = tf.cast(x_data, dtype=tf.float32) / 255.
# 数据类型 tf.int32 y:(0-99)
y_data = tf.cast(y_data, dtype=tf.int32)
return x_data, y_data
# 加载默认数据集:cifar-100
(x, y), (x_test, y_test) = datasets.cifar100.load_data()
# y (50000,1) ==>(50000,)
y = tf.squeeze(y, axis=1)
# y_test (10000,1) ==>(10000,)
y_test = tf.squeeze(y_test, axis=1)
print(x.shape, y.shape, x_test.shape, y_test.shape)
# 训练集 dataset 数据集生成(做简单的预处理 + batch)
train_db = tf.data.Dataset.from_tensor_slices((x, y))
train_db = train_db.shuffle(50000).map(pre_process).batch(128)
# 测试集 dataset 数据集生成(做简单的预处理 + batch)
test_db = tf.data.Dataset.from_tensor_slices((x_test, y_test))
test_db = test_db.map(pre_process).batch(64)
# 数据维度确认
sample = next(iter(train_db))
# x,y的维度 x的最小值与最大值
print("sample:", sample[0].shape, sample[1].shape,
tf.reduce_min(sample[0]), tf.reduce_max(sample[0]))
# 2.build network 构建网络结构与创建
vgg16 = [ # 5 unit of conf + max pooling
# unit 1 [b, 32, 32, 3]
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"),
# [b, 16, 16, 64]
# 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"),
# [b, 8, 8, 128]
# 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.Conv2D(256, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
layers.MaxPool2D(pool_size=[2, 2], strides=2, padding="same"),
# [b, 4, 4, 256]
# 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.Conv2D(512, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
layers.MaxPool2D(pool_size=[2, 2], strides=2, padding="same"),
# [b, 2, 2, 512]
# 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.Conv2D(512, kernel_size=[3, 3], padding="same", activation=tf.nn.relu),
layers.MaxPool2D(pool_size=[2, 2], strides=2, padding="same"),
# [b, 1, 1, 512]
# [b, 1, 1, 512] ==> [b, 512]
layers.Flatten(),
# 全连接
layers.Dense(4096, activation=tf.nn.relu),
layers.Dense(4096, activation=tf.nn.relu),
layers.Dense(100,activation='softmax')
]
def main():
# 创建网络结构
vgg16_net = Sequential(vgg16)
# x = tf.random.normal([4, 32, 32, 3])
# vgg13 网络的创建
vgg16_net.build(input_shape=[None, 32, 32, 3])
# out = vgg13_net(x)
# print(out.shape)
# 设置优化器
optimizer = optimizers.Adam(lr=1e-4)
# 设置可训练参数
variables = vgg16_net.trainable_variables
# 3.Train 循环训练
for epoch in range(300):
for step, (x, y) in enumerate(train_db):
with tf.GradientTape() as tape:
# 前向传播
# [b, 32, 32,3] => [b, 100]
y_prd = vgg16_net(x)
# [b,] => [b, 100]
y_true = tf.one_hot(y, depth=100)
# 损失函数计算
loss = tf.losses.categorical_crossentropy(y_true, y_prd, from_logits=True)
loss = tf.reduce_mean(loss)
# 梯度计算
grads = tape.gradient(loss, variables)
# 优化器更新参数
optimizer.apply_gradients(zip(grads, variables))
# 打印结果
if step % 100 == 0:
print(epoch, step, "loss:", float(loss))
# 4.Test 计算正确率
total_num = 0
total_correct = 0
for x, y in test_db:
# 前向传播
y_prd = vgg16_net(x)
prob = tf.nn.softmax(y_prd, axis=1)
pred = tf.argmax(prob, axis=1)
pred = tf.cast(pred, dtype=tf.int32)
# 计算正确数
# [b, bool] ==> [b, int32]
correct = tf.cast(tf.equal(pred, y), dtype=tf.int32)
correct = tf.reduce_sum(correct)
# 累加总数与正确数
total_num += x.shape[0]
total_correct += int(correct)
# 计算正确率
acc = total_correct / total_num
print(epoch, "acc:", acc)
if __name__ == '__main__':
main()