tensorflow(十八)：神经网络验证测试

import  tensorflow as tf
from    tensorflow import keras
from    tensorflow.keras import datasets
import  os

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

# x: [60k, 28, 28], [10, 28, 28]
# y: [60k], [10k]
(x, y), (x_test, y_test) = datasets.mnist.load_data()
# x: [0~255] => [0~1.]
x = tf.convert_to_tensor(x, dtype=tf.float32) / 255.
y = tf.convert_to_tensor(y, dtype=tf.int32)
x_test = tf.convert_to_tensor(x_test, dtype=tf.float32) / 255.
y_test = tf.convert_to_tensor(y_test, dtype=tf.int32)

print(x.shape, y.shape, x.dtype, y.dtype)
print(tf.reduce_min(x), tf.reduce_max(x))
print(tf.reduce_min(y), tf.reduce_max(y))


train_db = tf.data.Dataset.from_tensor_slices((x,y)).batch(128)
test_db = tf.data.Dataset.from_tensor_slices((x_test,y_test)).batch(128)
train_iter = iter(train_db)
sample = next(train_iter)
print(‘batch:‘, sample[0].shape, sample[1].shape)


# [b, 784] => [b, 256] => [b, 128] => [b, 10]
# [dim_in, dim_out], [dim_out]
w1 = tf.Variable(tf.random.truncated_normal([784, 256], stddev=0.1))
b1 = tf.Variable(tf.zeros([256]))
w2 = tf.Variable(tf.random.truncated_normal([256, 128], stddev=0.1))
b2 = tf.Variable(tf.zeros([128]))
w3 = tf.Variable(tf.random.truncated_normal([128, 10], stddev=0.1))
b3 = tf.Variable(tf.zeros([10]))

lr = 1e-3

for epoch in range(100): # iterate db for 10
    for step, (x, y) in enumerate(train_db): # for every batch
        # x:[128, 28, 28]
        # y: [128]

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

        with tf.GradientTape() as tape: # tf.Variable
            # x: [b, 28*28]
            # h1 = x@w1 + b1
            # [b, 784]@[784, 256] + [256] => [b, 256] + [256] => [b, 256] + [b, 256]
            h1 = x@w1 + tf.broadcast_to(b1, [x.shape[0], 256])
            h1 = tf.nn.relu(h1)
            # [b, 256] => [b, 128]
            h2 = h1@w2 + b2
            h2 = tf.nn.relu(h2)
            # [b, 128] => [b, 10]
            out = h2@w3 + b3

            # compute loss
            # out: [b, 10]
            # y: [b] => [b, 10]
            y_onehot = tf.one_hot(y, depth=10)

            # mse = mean(sum(y-out)^2)
            # [b, 10]
            loss = tf.square(y_onehot - out)
            # mean: scalar
            loss = tf.reduce_mean(loss)

        # compute gradients
        grads = tape.gradient(loss, [w1, b1, w2, b2, w3, b3])
        # print(grads)
        # w1 = w1 - lr * w1_grad
        w1.assign_sub(lr * grads[0])
        b1.assign_sub(lr * grads[1])
        w2.assign_sub(lr * grads[2])
        b2.assign_sub(lr * grads[3])
        w3.assign_sub(lr * grads[4])
        b3.assign_sub(lr * grads[5])


        if step % 100 == 0:
            print(epoch, step, ‘loss:‘, float(loss))


    # test/evluation
    # [w1, b1, w2, b2, w3, b3]
    total_correct, total_num = 0, 0
    for step, (x,y) in enumerate(test_db):

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

        # [b, 784] => [b, 256] => [b, 128] => [b, 10]
        h1 = tf.nn.relu(x@w1 + b1)
        h2 = tf.nn.relu(h1@w2 + b2)
        out = h2@w3 +b3

        # out: [b, 10] ~ R
        # prob: [b, 10] ~ [0, 1]
        prob = tf.nn.softmax(out, axis=1)
        # [b, 10] => [b]
        # int64!!!
        pred = tf.argmax(prob, axis=1)
        pred = tf.cast(pred, dtype=tf.int32)
        # y: [b]
        # [b], int32
        # print(pred.dtype, y.dtype)
        correct = tf.cast(tf.equal(pred, y), dtype=tf.int32)
        correct = tf.reduce_sum(correct)

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

    acc = total_correct / total_num
    print(‘test acc:‘, acc)

import tensorflow as tf
import tensorflow.keras as keras
import os

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

def prepare_mnist_features_and_labels(x,y):
    x = tf.cast(x, tf.float32) / 255.0
    y = tf.cast(y, tf.int64)
    return x,y

def mnist_dataset():
    (x,y), (x_test,y_test) = keras.datasets.fashion_mnist.load_data() #numpy中的格式

    y = tf.one_hot(y, depth=10)                     #[10k] ==> [10k,10]的tensor
    y_test = tf.one_hot(y_test, depth=10)

    ds = tf.data.Dataset.from_tensor_slices((x,y))
    ds = ds.map(prepare_mnist_features_and_labels)  #数据预处理,注意：tf.map中传进的参数
    ds = ds.shuffle(60000).batch(100)               #随机打散，读取一个batch的样本

    ds_val = tf.data.Dataset.from_tensor_slices((x_test,y_test))
    ds_val = ds_val.map(prepare_mnist_features_and_labels)
    ds_val = ds_val.shuffle(10000).batch(100)
    return ds, ds_val


def main():
    ds, ds_val = mnist_dataset()

    print("训练集信息如下：")
    iteration_ds = iter(ds)
    iter_ds = next(iteration_ds)
    print(iter_ds[0].shape, iter_ds[1].shape)

    print("测试集信息如下：")
    iteration_ds_val = iter(ds_val)
    iter_ds_val = next(iteration_ds_val)
    print(iter_ds_val[0].shape, iter_ds_val[1].shape)

if __name__ == ‘__main__‘:
    main()