前向传播简单实践

前向传播

• out = relu{relu{relu[X@W1+b1]@W2+b2}@W3+b3}

• pred = argmax(out)

• loss=MSE(out,label)

• minimize loss 优化[W1’,b1’,W2’,b2’,W3’,b3’,]

构建数据集

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],
# y: [60k]
(x, y), _ = 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)

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))

#创建数据集
train_db = tf.data.Dataset.from_tensor_slices((x,y)).batch(128)
train_iter = iter(train_db)	#迭代器 可以对train做next
sample = next(train_iter)
print('batch:', sample[0].shape, sample[1].shape)
print(sample)

# [b, 784] => [b, 256] => [b, 128] => [b, 10]
# [dim_in, dim_out], [dim_out]
#这里使用Variable包装是因为tape.gradient只追踪Variable类型
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(10): # 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])
        #自动求导的过程 放在Gradient里面
        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 需要求解梯度的元素 //默认只会跟踪tf.Variable类型
        grads = tape.gradient(loss, [w1, b1, w2, b2, w3, b3])
        #print(grads)
        # w1 = w1 - lr * w1_grad
        # w1 = w1 - lr * grads[0] 经过相减运算后会返回tf.tensor类型而不是Variable类型，
        w1.assign_sub(lr * grads[0])#原地更新，不改变类型 如果还是想使用上面的操作，可以在每次 进入自动求导运算时将类型转变为Variable类型
        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))

打赏