使用torch以及tensorflow訓練一個最簡單網絡的基本步驟

torch： 

import torch
import torch.nn.functional as F
import matplotlib.pyplot as plt

x = torch.Tensor.unsqueeze(torch.Tensor.linspace(-1, 1, 100), dim=1)  # x data (tensor), shape=(100, 1)
y = x.pow(2) + 0.2 * torch.rand()


class Net(torch.nn.Module):
    def __init__(self, n_feature, n_hidden, n_output):
        super(Net, self).__init__() #繼承init
        #定義每層的形式
        self.hidden = torch.nn.Linear(n_feature, n_hidden)
        self.predict = torch.nn.Linear(n_hidden, n_output)

    def forward(self, x):
        #正向傳播輸入值，神經網絡分析出輸出值
        x = F.relu(self.hidden(x)) #激勵函數（隱藏層的線性值）
        x = self.predict(x) #輸出值
        return x

net = Net(n_feature=1, n_hidden=10, n_output=1)

print(net)

optimizer = torch.optim.SGD(net.parameters(), lr=0.2) #傳入net的所有參數，學習率
loss_func = torch.nn.MSELoss() #預測值和真實值的誤差計算公式（均方差）

for t in range(100):
    prediction = net(x)

    loss = loss_func(prediction, y)

 

 

tensorflow：

#--coding:utf-8--

import tensorflow as tf
from numpy.random import RandomState

batch_size = 8

#定義神經網絡參數
w1 = tf.Variable(tf.random_normal([2, 3], stddev=1, seed=1))
w2 = tf.Variable(tf.random_normal([3, 1], stddev=1, seed=1))

x = tf.placeholder(tf.float32, shape=(None, 2), name='x-input')
y_ = tf.placeholder(tf.float32, shape=(None, 1), name='y-input')

#前向傳播過程
a = tf.matmul(x, w1)
y = tf.matmul(a, w2)

#定義損失函數和反向傳播算法
y = tf.sigmoid(y)
cross_entropy = -tf.reduce_mean(
    y_ * tf.log(tf.clip_by_value(y, 1e-10, 1.0)) + (1 - y) * tf.log(tf.clip_by_value(1 - y, 1e-10, 1.0))
)

train_step = tf.train.AdamOptimizer(0.001).minimize(cross_entropy)

rdm = RandomState(1)
dataset_size = 128
X = rdm.rand(dataset_size, 2)
Y = [[int(x1 + x2 < 1)] for (x1, x2) in X]

with tf.Session() as sess:
    init_op = tf.global_variables_initializer()
    sess.run(init_op)

    print(sess.run(w1))
    print(sess.run(w2))

    #開始訓練
    STEPS = 5000
    for i in range(STEPS):
        start = (i * batch_size) % dataset_size
        end = min(start + batch_size, dataset_size)

        sess.run(train_step,
                 feed_dict={x: X[start:end], y_: Y[start:end]})

        if i % 1000 == 0:
            total_cross_entropy = sess.run(
                cross_entropy, feed_dict={x: X, y_: Y})
            print("After %d training steps, cross entropy on all data is %g" % (i, total_cross_entropy))

    print(sess.run(w1))
    print(sess.run(w2))