tensorflow 2.0 随机梯度下降 之 FashionMNIST实战

版权声明：本文为博主（[email protected]）原创文章，未经博主允许不得转载。 https://blog.csdn.net/z_feng12489/article/details/89918987

数据预处理

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.fashion_mnist.load_data()
x.shape, y.shape   # (60000, 28, 28) (60000,)

batchsz = 128

db = tf.data.Dataset.from_tensor_slices((x, y))
db = db.map(preprocess).shuffle(10000).batch(batchsz)

db_test = tf.data.Dataset.from_tensor_slices((x_test, y_test))
db_test = db_test.map(preprocess).batch(batchsz)

db_iter = iter(db)
sample = next(db_iter)
sample[0].shape, sample[1].shape   # batch: (128, 28, 28) (128,)

建立网络

model = Sequential([
    layers.Dense(256, activation=tf.nn.relu),  # [b, 784] => [b, 256]
    layers.Dense(128, activation=tf.nn.relu),  # [b, 256] => [b, 128]
    layers.Dense(64, activation=tf.nn.relu),  # [b, 128] => [b, 64]
    layers.Dense(32, activation=tf.nn.relu),  # [b, 64] => [b, 32]
    layers.Dense(10)  # [b, 32] => [b, 10], 330 = 32*10 + 10
])
model.build(input_shape=[None, 28 * 28])
model.summary()

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense (Dense)                multiple                  200960    
_________________________________________________________________
dense_1 (Dense)              multiple                  32896     
_________________________________________________________________
dense_2 (Dense)              multiple                  8256      
_________________________________________________________________
dense_3 (Dense)              multiple                  2080      
_________________________________________________________________
dense_4 (Dense)              multiple                  330       
=================================================================
Total params: 244,522
Trainable params: 244,522
Non-trainable params: 0
_________________________________________________________________

前向传播 梯度回传

	# x: [b, 28, 28] => [b, 784]
    # y: [b]
    x = tf.reshape(x, [-1, 28 * 28])

    with tf.GradientTape() as tape:
        # [b, 784] => [b, 10]
        logits = model(x)
        y_onehot = tf.one_hot(y, depth=10)
        # [b]
        loss_mse = tf.reduce_mean(tf.losses.MSE(y_onehot, logits))
        loss_ce = tf.losses.categorical_crossentropy(
            y_onehot, logits, from_logits=True)
        loss_ce = tf.reduce_mean(loss_ce)

    grads = tape.gradient(loss_ce, model.trainable_variables)
    optimizer.apply_gradients(zip(grads, model.trainable_variables))

测试

	# test
    total_correct = 0
    total_num = 0
    for x, y in db_test:

        # x: [b, 28, 28] => [b, 784]
        # y: [b]
        x = tf.reshape(x, [-1, 28 * 28])
        # [b, 10]
        logits = model(x)
        # logits => prob, [b, 10]
        prob = tf.nn.softmax(logits, axis=1)
        # [b, 10] => [b], int64
        pred = tf.argmax(prob, axis=1)
        pred = tf.cast(pred, dtype=tf.int32)
        # pred:[b]
        # y: [b]
        # correct: [b], True: equal, False: not equal
        correct = tf.equal(pred, y)
        correct = tf.reduce_sum(tf.cast(correct, dtype=tf.int32))

        total_correct += int(correct)
        total_num += x.shape[0]
        
    acc = total_correct / total_num

完整代码

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

import os

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


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.fashion_mnist.load_data()
print(x.shape, y.shape)

batchsz = 128

db = tf.data.Dataset.from_tensor_slices((x, y))
db = db.map(preprocess).shuffle(10000).batch(batchsz)

db_test = tf.data.Dataset.from_tensor_slices((x_test, y_test))
db_test = db_test.map(preprocess).batch(batchsz)

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


model = Sequential([
    layers.Dense(256, activation=tf.nn.relu),  # [b, 784] => [b, 256]
    layers.Dense(128, activation=tf.nn.relu),  # [b, 256] => [b, 128]
    layers.Dense(64, activation=tf.nn.relu),  # [b, 128] => [b, 64]
    layers.Dense(32, activation=tf.nn.relu),  # [b, 64] => [b, 32]
    layers.Dense(10)  # [b, 32] => [b, 10], 330 = 32*10 + 10
])
model.build(input_shape=[None, 28 * 28])
model.summary()
# w = w - lr*grad
optimizer = optimizers.Adam(lr=1e-3)


def main():

    for epoch in range(30):

        for step, (x, y) in enumerate(db):

            # x: [b, 28, 28] => [b, 784]
            # y: [b]
            x = tf.reshape(x, [-1, 28 * 28])

            with tf.GradientTape() as tape:
                # [b, 784] => [b, 10]
                logits = model(x)
                y_onehot = tf.one_hot(y, depth=10)
                # [b]
                loss_mse = tf.reduce_mean(tf.losses.MSE(y_onehot, logits))
                loss_ce = tf.losses.categorical_crossentropy(
                    y_onehot, logits, from_logits=True)
                loss_ce = tf.reduce_mean(loss_ce)

            grads = tape.gradient(loss_ce, model.trainable_variables)
            optimizer.apply_gradients(zip(grads, model.trainable_variables))

            if step % 100 == 0:
                print(epoch, step, 'loss:', float(loss_ce), float(loss_mse))

        # test
        total_correct = 0
        total_num = 0
        for x, y in db_test:

            # x: [b, 28, 28] => [b, 784]
            # y: [b]
            x = tf.reshape(x, [-1, 28 * 28])
            # [b, 10]
            logits = model(x)
            # logits => prob, [b, 10]
            prob = tf.nn.softmax(logits, axis=1)
            # [b, 10] => [b], int64
            pred = tf.argmax(prob, axis=1)
            pred = tf.cast(pred, dtype=tf.int32)
            # pred:[b]
            # y: [b]
            # correct: [b], True: equal, False: not equal
            correct = tf.equal(pred, y)
            correct = tf.reduce_sum(tf.cast(correct, dtype=tf.int32))

            total_correct += int(correct)
            total_num += x.shape[0]

        acc = total_correct / total_num
        print(epoch, 'test acc:', acc)


if __name__ == '__main__':
    main()