vgg13识别cifar100

用vgg13识别cifar100

import os

os.environ['TF_CPP_MIN_LOG_LEVEL']='2'
import tensorflow as tf
from tensorflow.keras import layers,optimizers,datasets,Sequential

tf.random.set_seed(2345)

conv_layers = [#5 unit 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'),

    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 preprocess(x,y):
    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,x_test.shape)

train_db = tf.data.Dataset.from_tensor_slices((x,y));
train_db = train_db.shuffle(1000).map(preprocess).batch(16);

test_db = tf.data.Dataset.from_tensor_slices((x_test,y_test));
test_db = test_db.map(preprocess).batch(16);

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

sample = next(iter(test_db))
print('test_dbsample:',sample[0].shape,sample[1].shape)


def main():
    conv_net = Sequential(conv_layers)

    '''
    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=tf.nn.relu)
    ])
    conv_net.build(input_shape=[None,32,32,3])
    fc_net.build(input_shape=[None,512])

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


    variables = conv_net.trainable_variables + fc_net.trainable_variables

    for epoch in range(50):
        for step, (x, y) in enumerate(train_db):
            #print(x.shape,y.shape)
            with tf.GradientTape() as tape:
                out = conv_net(x)
                out =tf.reshape(out,[-1,512])
                logits = fc_net(out)
                y_hot = tf.one_hot(y,depth=100)
                #loss
                loss = tf.losses.categorical_crossentropy(y_hot,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_sum = 0
        total_currect = 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_sum += x.shape[0]
            total_currect +=int(correct)


        acc = total_currect / total_sum

        print('acc: ',acc)


if __name__ == '__main__':
    main()

完结撒花！！！