TensorFlow 手写数字问题实战

导入模块

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

加载数据并处理数据

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()
db = tf.data.Dataset.from_tensor_slices((x,y))
db = db.map(preprocess).shuffle(10000).batch(200)
db_test = tf.data.Dataset.from_tensor_slices((x_test,y_test))
db_test = db_test.map(preprocess).shuffle(10000).batch(200)

创建网络和优化器

#[b,784] => [b,512] => [b,256] => [b,128] => [b,64] => [b,10]
model = Sequential([
    layers.Dense(512,activation='relu'),
    layers.Dense(256,activation='relu'),
    layers.Dense(128,activation='relu'),
    layers.Dense(64,activation='relu'),
    layers.Dense(10)
    ])
model.build(input_shape=[None,28*28])
optimizer = optimizers.Adam(learning_rate=0.001)

数据更新

for epoch in range(30):
    for step,(x,y) in enumerate(db):     
        x = tf.reshape(x,[-1,28*28])
        with tf.GradientTape() as tape:
            logits = model(x)
            y_onehot = tf.one_hot(y,depth=10)
            loss_ce = tf.reduce_mean(tf.losses.categorical_crossentropy(y_onehot,logits,from_logits=True))
            loss_mse = tf.reduce_mean(tf.losses.MSE(y_onehot,logits))
        grads = tape.gradient(loss_ce,model.trainable_variables)
        optimizer.apply_gradients(zip(grads,model.trainable_variables))
        with summary_writer.as_default():
            tf.summary.scalar('loss',float(loss_ce),step=epoch)
                
        if step%100==0:
            print(epoch,step,'loss:',float(loss_ce))

测试

    total_correct = 0
    total_num = 0
    for x,y in db_test:
        x = tf.reshape(x,[-1,28*28])
        logits = model(x)
        prod = tf.nn.softmax(logits,axis=1)#将值转为[0~1]且和为1
        pred = tf.argmax(prod,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_correct += correct
        total_num += x.shape[0]
    acc = total_correct/total_num*100
    print('准确率',int(acc),'%',sep='')