TensorFlow10.2 卷积神经网络-CIFAR100 实战

▪ Load datasets
▪ Build Network
▪ Train
▪ Test

这里先是进行卷积然后再进行全连接

Load datasets

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()
print(x.shape, y.shape, x_test.shape, y_test.shape)
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(128)

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

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

说一下这里为什么要tf.squeeze(y, axis=1)，因为你一开始下载下来其数据结构为(50000, 1)，是个竖着的，然后你要变成一维的(50000, )

Build Network

conv_net = Sequential([ # 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')

])

这里有一个5层的卷积神经网络，和一个三层的全连接神经网络。

Train+Test

def main():
    # [b, 32, 32, 3] => [b, 1, 1, 512] #这里也可以跟下面一样的定义。
  #  conv_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=None),
    ])
    # 这里一定不要忘了
    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(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)
                # 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()