使用tensorflow实现简单的前向传播
前向传播
将上一层的输出作为下一层的输入,并计算下一层的输出,一直到运算到输出层为止。
下面是代码实现:
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import datasets
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
#mnist数据集,6000张图片,像素28*28
(x,y), _ =datasets.mnist.load_data()
#转换为张量
#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))
#从张量的切片读取数据
train_db = tf.data.Dataset.from_tensor_slices((x,y)).batch(128)
#batch (128, 28, 28) (128,)
train_iter = iter(train_db)
#创建迭代器对象
sample = next(train_iter)
print('batch',sample[0].shape,sample[1].shape)
#创建权值
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):
#迭代10次
for step, (x,y) in enumerate(train_db):
# h1 = x@w1 + b1
x = tf.reshape(x,[-1, 28*28])
with tf.GradientTape() as tape:
h1 = x@w1 + b1
#tf.nn.relu()函数将输入小于0的值幅值为0,输入大于0的值不变
h1 = tf.nn.relu(h1)
h2 = h1@w2 + b2
h2 = tf.nn.relu(h2)
out = h2@w3 + b3
#compute loss
y_onehot = tf.one_hot(y,depth=10)
loss = tf.square(y_onehot - out)
loss = tf.reduce_mean(loss)
#compute gradients
grads = tape.gradient(loss,[w1,b1,w2,b2,w3,b3])
w1.assign_sub(lr * grads[0])
#原地更新
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])
# w1 = w1 - lr * grads[0]
#b1 = b1 - lr * grads[1]
#w2 = w2 - lr * grads[2]
#b2 = b2 - lr * grads[3]
#w3 = w3 - lr * grads[4]
#b3 = b3 - lr * grads[5]
#print(isinstance(b3, tf.Variable))
#print(isinstance(b3, tf.Tensor))
if step % 100 == 0:
print(step, 'loss',float(loss))
在迭代10次后,loss取得明显下降