CIFAR100与VGG13实战

CIFAR100

13 Layers

cafar100_train

import tensorflow as tf
from tensorflow.keras import layers, optimizers, datasets, Sequential
import os

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

conv_layers = [
    # 5 units of conv + max polling
    # 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'),

    # unit2
    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'),

    # unit3
    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'),

    # unit4
    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'),

    # unit5
    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 preprocess(x, y):
    # [0-1]
    x = tf.cast(x, dtype=tf.float32) / 255.
    y = tf.cast(y, dtype=tf.int32)
    return x, y


(x, y), (x_test, y_test) = datasets.cifar100.load_data()
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)

train_db = tf.data.Dataset.from_tensor_slices((x, y))
train_db = train_db.shuffle(1000).map(preprocess).batch(64)

test_db = tf.data.Dataset.from_tensor_slices((x_test, y_test))
test_db = test_db.map(preprocess).batch(64)


def main():

    # [b,32,32,3]-->[b,1,1,512]
    conv_net = Sequential(conv_layers)
    conv_net.build(input_shape=[None, 32, 32, 3])
    #     x = tf.random.normal([4, 32, 32, 3])
    #     out = conv_net(x)
    #     print(out.shape)

    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])
    optimizer = optimizers.Adam(lr=1e-4)
    
    # [1,2]+[3,4] = [1,2,3,4]
    variables = conv_net.trainable_variables + fc_net.trainable_variables

    for epoch in range(3):
        for step, (x, y) in enumerate(train_db):
            with tf.GradientTape() as tape:
                # [b,32,32,3]
                out = conv_net(x)
                # flatten ==> [b,512]
                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 = 0
        total_correct = 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()