增加肌肉记忆，码一遍 龙哥的pytorch示例： ex_001, matMul；ex_002, autograd；ex_003, 线性函数的 gradient descent ＜梯度下降最简示例＞

import torch
import time

print(torch.__version__)
print(torch.cuda.is_available())

a = torch.randn(1024*8*16, 1000)
b = torch.randn(1000, 2000)

t0 = time.time()
c = torch.matmul(a, b)
t1 = time.time()
print(a.device, t1-t0, c.norm(2))

device = torch.device('cuda')
a = a.to(device)
b = b.to(device)

t0 = time.time()
c = torch.matmul(a, b)
t2 = time.time()
print(a.device, t2-t0, c.norm(2))

t0 = time.time()
c = torch.matmul(a, b)
t2 = time.time()
print(a.device, t2-t0, c.norm(2))

save as helloMatMul_cpu_gpu_time.py

$ python3 ./helloMatMul_cpu_gpu_time.py

output:

helloPytorch# python3 ./helloTorch.py
1.9.0a0+2ecb2c7
True
cpu 0.6934514045715332 tensor(507455.8750)
cuda:0 0.5243451595306396 tensor(512158.1562, device='cuda:0')
cuda:0 0.001405954360961914 tensor(512158.1562, device='cuda:0')

计算 A(1024*8*16  x  1000)   *     B(1000 x 2000)：

cpu 运行时间

gpu warming up 时间

gpu running time

—以下为—ex_002 autograd—————————————————————————————

import torch
from torch import autograd


x = torch.tensor(1.)
a = torch.tensor(1., requires_grad=True)
b = torch.tensor(2., requires_grad=True)
c = torch.tensor(3., requires_grad=True)

y = a**2 * x + b* x + c

#print('before0:', grads[0], grads[1], grads[2])
print('before:', a.grad, b.grad, c.grad)
grads = autograd.grad(y, [a, b, c])
print('after:', grads[0], grads[1], grads[2])
print('after2:', a.grad, b.grad, c.grad)

save as helloAutograd.py

output:

helloPytorch# python3 ./helloAutograd.py
before: None None None
after: tensor(2.) tensor(1.) tensor(1.)
after2: None None None

预先 a = 1.， b = 2.，c = 3.， x=1.

将系数视为待定的变量，训练的对象，对a,b,c 分别自动求导，结果为 2，1， 1

———ex_003—linear regression————————————————————————

代码：

import numpy as np

# y = wx + b
def compute_error_for_line_given_points(b, w, points):
    totalError = 0
    for i in range(0, len(points)):
        x = points[i, 0]
        y = points[i, 1]
        totalError += (y-(w*x+b))**2
    return totalError/float(len(points))


def step_gradient(b_current, w_current, points, learningRate):
    b_gradient = 0
    w_gradient = 0
    N = float(len(points))
    for i in range(0, len(points)):
        x = points[i, 0]
        y = points[i, 1]
        b_gradient += -(2/N) * (y - ((w_current*x) + b_current))
        w_gradient += -(2/N) * x * (y - ((w_current*x)+ b_current))

    new_b = b_current - (learningRate * b_gradient)
    new_w = w_current - (learningRate * w_gradient)
    return [new_b, new_w]

def gradient_descent_runner(points, starting_b, starting_w, 
                            learning_rate, num_iterations):
    b = starting_b
    w = starting_w
    for i in range(num_iterations):
        b, w = step_gradient(b, w, np.array(points), learning_rate)
    return [b, w]

def run():
    points = np.genfromtxt("randData.csv", delimiter=",")
    learning_rate = 0.00001
    initial_b = 0
    initial_w = 0
    num_iterations = 1000000
    print("Starting gradient descent at b = {0}, w = {1}, error = {2}"
            .format(initial_b, initial_w,
                    compute_error_for_line_given_points(initial_b, initial_w, points))
          )
    print("Running...")
    [b, w] = gradient_descent_runner(points, initial_b, initial_w, learning_rate, num_iterations)
    print("After {0} iterations learning_rate = {1}, b = {2} w = {3}, error = {4}"
            .format(num_iterations, learning_rate, b, w, 
                    compute_error_for_line_given_points(b, w, points))
         )

if __name__ == '__main__':
    run()

data file:

save as randData.csv

32.502345269453031,31.70700584656992
53.426804033275019,68.77759598163891
61.530358025636438,62.562382297945803
47.475639634786098,71.546632233567777
59.813207869512318,87.230925133687393
55.142188413943821,78.211518270799232
52.211796692214001,79.64197304980874
39.299566694317065,59.171489321869508
48.10504169176825,75.331242297063056
52.550014442733818,71.300879886850353
45.419730144973755,55.165677145959123
54.351634881228918,82.478846757497919
44.164049496773352,62.008923245725825
58.16847071685779,75.392870425994957
56.727208057096611,81.43619215887864
48.955888566093719,60.723602440673965
44.687196231480904,82.892503731453715
60.297326851333466,97.379896862166078
45.618643772955828,48.847153317355072
38.816817537445637,56.877213186268506
66.189816606752601,83.878564664602763
65.41605174513407,118.59121730252249
47.48120860786787,57.251819462268969
41.57564261748702,51.391744079832307
51.84518690563943,75.380651665312357
59.370822011089523,74.765564032151374
57.31000343834809,95.455052922574737
63.615561251453308,95.229366017555307
46.737619407976972,79.052406169565586
50.556760148547767,83.432071421323712
52.223996085553047,63.358790317497878
35.567830047746632,41.412885303700563
42.436476944055642,76.617341280074044
58.16454011019286,96.769566426108199
57.504447615341789,74.084130116602523
45.440530725319981,66.588144414228594
61.89622268029126,77.768482417793024
33.093831736163963,50.719588912312084
36.436009511386871,62.124570818071781
37.675654860850742,60.810246649902211
44.555608383275356,52.682983366387781
43.318282631865721,58.569824717692867
50.073145632289034,82.905981485070512
43.870612645218372,61.424709804339123
62.997480747553091,115.24415280079529
32.669043763467187,45.570588823376085
40.166899008703702,54.084054796223612
53.575077531673656,87.994452758110413
33.864214971778239,52.725494375900425
64.707138666121296,93.576118692658241
38.119824026822805,80.166275447370964
44.502538064645101,65.101711570560326
40.599538384552318,65.562301260400375
41.720676356341293,65.280886920822823
51.088634678336796,73.434641546324301
55.078095904923202,71.13972785861894
41.377726534895203,79.102829683549857
62.494697427269791,86.520538440347153
49.203887540826003,84.742697807826218
41.102685187349664,59.358850248624933
41.182016105169822,61.684037524833627
50.186389494880601,69.847604158249183
52.378446219236217,86.098291205774103
50.135485486286122,59.108839267699643
33.644706006191782,69.89968164362763
39.557901222906828,44.862490711164398
56.130388816875467,85.498067778840223
57.362052133238237,95.536686846467219
60.269214393997906,70.251934419771587
35.678093889410732,52.721734964774988
31.588116998132829,50.392670135079896
53.66093226167304,63.642398775657753
46.682228649471917,72.247251068662365
43.107820219102464,57.812512976181402
70.34607561504933,104.25710158543822
44.492855880854073,86.642020318822006
57.50453330326841,91.486778000110135
36.930076609191808,55.231660886212836
55.805733357942742,79.550436678507609
38.954769073377065,44.847124242467601
56.901214702247074,80.207523139682763
56.868900661384046,83.14274979204346
34.33312470421609,55.723489260543914
59.04974121466681,77.634182511677864
57.788223993230673,99.051414841748269
54.282328705967409,79.120646274680027
51.088719898979143,69.588897851118475
50.282836348230731,69.510503311494389
44.211741752090113,73.687564318317285
38.005488008060688,61.366904537240131
32.940479942618296,67.170655768995118
53.691639571070056,85.668203145001542
68.76573426962166,114.85387123391394
46.230966498310252,90.123572069967423
68.319360818255362,97.919821035242848
50.030174340312143,81.536990783015028
49.239765342753763,72.111832469615663
50.039575939875988,85.232007342325673
48.149858891028863,66.224957888054632
25.128484647772304,53.454394214850524

改变学习率或学习次数后的 output：

root@defdc4d0972f:/home/yy/ex/pytorchTest/helloPytorch# python3 ./linearRegression.py
Starting gradient descent at b = 0, w = 0, error = 5565.107834483211
Running...
After 1000 iterations learning_rate = 0.0001, b = 0.08893651993741346 w = 1.4777440851894448, error = 112.61481011613473
root@defdc4d0972f:/home/yy/ex/pytorchTest/helloPytorch# python3 ./linearRegression.py
Starting gradient descent at b = 0, w = 0, error = 5565.107834483211
Running...
After 100000 iterations learning_rate = 1e-05, b = 0.6078967069728876 w = 1.4675440808343854, error = 112.3153353259074
root@defdc4d0972f:/home/yy/ex/pytorchTest/helloPytorch# python3 ./linearRegression.py
Starting gradient descent at b = 0, w = 0, error = 5565.107834483211
Running...
After 1000000 iterations learning_rate = 1e-05, b = 4.24797484458317 w = 1.395999454129054, error = 110.78632200941048
root@defdc4d0972f:/home/yy/ex/pytorchTest/helloPytorch#

loss值越小，b的值越大的。主要是因为数据集距离原点有点远，斜率w的一点点变化，就明显影响b的值。