CIFAR 100实战
- 思路(卷积层+池化层+…+卷积层+池化层+全连层+输出层)
- 加载数据集,数据集预处理
- 设定卷积层与池化层
- 设定全连接层(设定卷积层池化层与全连层的输入维度)
- 梯度下降,更新参数
- 测试(获得准确率)
- 代码
import tensorflow as tf
from tensorflow.keras import layers, optimizers, datasets, Sequential
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
def pre_process(x, y):
x = tf.cast(x, dtype=tf.float32) / 255.
y = tf.cast(y, dtype=tf.int32)
return x, y
batch_size = 129
(x, y), (x_test, y_test) = datasets.cifar100.load_data()
y = tf.squeeze(y, axis=1)
y_test = tf.squeeze(y_test, axis=1)
train_db = tf.data.Dataset.from_tensor_slices((x, y))
train_db = train_db.shuffle(1000).map(pre_process).batch(batch_size)
test_db = tf.data.Dataset.from_tensor_slices((x_test, y_test))
test_db = test_db.map(pre_process).batch(batch_size)
sample = next(iter(train_db))
conv_layers = [
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'),
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'),
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'),
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'),
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')
]
def main():
con_net = Sequential(conv_layers)
fc_net = Sequential([
layers.Dense(256, activation=tf.nn.relu),
layers.Dense(128, activation=tf.nn.relu),
layers.Dense(100, activation=tf.nn.relu)
])
con_net.build(input_shape=[None, 32, 32, 3])
fc_net.build(input_shape=[None, 512])
optimizer = optimizers.Adam(lr=1e-4)
variables = con_net.trainable_variables + fc_net.trainable_variables
for epoch in range(100):
for step, (x, y) in enumerate(train_db):
with tf.GradientTape() as tape:
out = con_net(x)
out = tf.reshape(out, [-1, 512])
output = fc_net(out)
y_onehot = tf.one_hot(y, depth=100)
loss = tf.losses.categorical_crossentropy(y_onehot, output, 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 = 0
total_correct = 0
for x,y in test_db:
out = con_net(x)
out = tf.reshape(out, [-1, 512])
output = fc_net(out)
prob = tf.nn.softmax(output, 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)
accuracy = total_correct / total_num
accuracy = accuracy * 100
print(epoch, '准确率', accuracy, "%")
if __name__ == '__main__':
main()