PyTorch深度学习实践05

Linear regression with pytorch

'''
def func(*args,**kwargs):print(args)#当不知道传入函数的参数的个数时可以用args，输出的args是以元祖的形式print(kwargs)#不知道参数名称和值的时候 传入的是词典func(1,2,4,5,x=3,y=5)(1, 2, 4, 5)
{'x': 3, 'y': 5}'''class Foobar:def __init__(self):passdef __call__(self, *args, **kwargs):print('hello'+str(args[0]))#所以同理 在call这个函数里面会实现forward这个函数foobar=Foobar()
foobar(1,2,3)#hello1

import os
import os
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"import matplotlib.pyplot as plt
import torch
#数据集是个三乘一的矩阵
x_data=torch.Tensor([[1.0],[2.0],[3.0]])
y_data=torch.Tensor([[2.0],[4.0],[6.0]])loss_list=[]
epoch_list=[]class LinearModel(torch.nn.Module):#init和forward必须重载 backward不一定要自己实现 module对象会自动根据计算图去实现backwarddef __init__(self):super(LinearModel,self).__init__()self.linear=torch.nn.Linear(1,1)#确定w和b 可以直接完成y_hat=xw+b的计算def forward(self,x):#重载forwardy_pre=self.linear(x)#由init可知实现forward的计算return y_pre
model =LinearModel()#实例化criterion=torch.nn.MSELoss(size_average=False)#MSEloss是损失函数 求loss
optimizer=torch.optim.Adam(model.parameters(),lr=0.01)#优化方法 分析优化器对哪些tensor进行优化或用梯度下降更新w的值for epoch in range(100):epoch_list.append(epoch)y_pre=model(x_data)loss=criterion(y_pre,y_data)loss_list.append(loss.item())print(epoch,loss.item())optimizer.zero_grad()#在backward求导数前必须权重清零loss.backward()optimizer.step()#更新wprint('w=',model.linear.weight.item())
print('b=',model.linear.bias.item())x_test=torch.Tensor([4.0])
y_test=model(x_test)
print('y_pre',y_test.data)plt.plot(epoch_list,loss_list)
plt.ylabel('Loss')
plt.xlabel('epoch')
plt.show()

当用Adam这个方法时且epoch=100时可以发现效果很不好理想的w=2，b=0，y_pre=8

1 39.28014373779297
2 38.61161804199219
3 37.94915008544922
4 37.29282760620117
5 36.642757415771484
6 35.999019622802734
7 35.36170959472656
8 34.73091125488281
9 34.106685638427734
10 33.489131927490234
11 32.8783073425293
12 32.27427673339844
13 31.677106857299805
14 31.08685302734375
15 30.503564834594727
16 29.927288055419922
17 29.358070373535156
18 28.795944213867188
19 28.240938186645508
20 27.69308853149414
21 27.15241241455078
22 26.618927001953125
23 26.092649459838867
24 25.57358169555664
25 25.06173324584961
26 24.557104110717773
27 24.0596866607666
28 23.56947135925293
29 23.086450576782227
30 22.610599517822266
31 22.14190673828125
32 21.680343627929688
33 21.22588348388672
34 20.77849769592285
35 20.338153839111328
36 19.904815673828125
37 19.478439331054688
38 19.058988571166992
39 18.64641761779785
40 18.240680694580078
41 17.84173011779785
42 17.449512481689453
43 17.063976287841797
44 16.685068130493164
45 16.312732696533203
46 15.946911811828613
47 15.587545394897461
48 15.234573364257812
49 14.887937545776367
50 14.547571182250977
51 14.21341323852539
52 13.885400772094727
53 13.563462257385254
54 13.247535705566406
55 12.937556266784668
56 12.633451461791992
57 12.335158348083496
58 12.042604446411133
59 11.755722045898438
60 11.474445343017578
61 11.198698043823242
62 10.928417205810547
63 10.663528442382812
64 10.40396499633789
65 10.149651527404785
66 9.90052318572998
67 9.656505584716797
68 9.417531967163086
69 9.1835298538208
70 8.954428672790527
71 8.730156898498535
72 8.510649681091309
73 8.295831680297852
74 8.085638999938965
75 7.879994869232178
76 7.678836822509766
77 7.48209285736084
78 7.289695739746094
79 7.101578712463379
80 6.917667865753174
81 6.73790168762207
82 6.562210559844971
83 6.390528678894043
84 6.2227888107299805
85 6.058926582336426
86 5.898874759674072
87 5.742569923400879
88 5.589945316314697
89 5.4409379959106445
90 5.295485973358154
91 5.153524398803711
92 5.014989852905273
93 4.879822731018066
94 4.747958183288574
95 4.619339466094971
96 4.493905067443848
97 4.371591567993164
98 4.252344608306885
99 4.136101722717285
w= 1.2186882495880127
b= 0.59620201587677
y_pre tensor([5.4710])

epoch=1000时，

1 73.64485931396484
2 72.73275756835938
3 71.82670593261719
4 70.92681121826172
5 70.03315734863281
6 69.14585876464844
7 68.26498413085938
8 67.390625
9 66.52285766601562
10 65.66177368164062
11 64.80744934082031
12 63.95995330810547
13 63.11935806274414
14 62.28571319580078
15 61.45909881591797
16 60.639556884765625
17 59.827152252197266
18 59.021915435791016
19 58.22390365600586
20 57.43315124511719
21 56.649696350097656
22 55.873565673828125
23 55.10478591918945
24 54.343387603759766
25 53.589385986328125
26 52.842796325683594
27 52.10362243652344
28 51.371883392333984
29 50.64757537841797
30 49.93070983886719
31 49.221275329589844
32 48.51927947998047
33 47.82469177246094
34 47.13752365112305
35 46.45774841308594
36 45.78535842895508
37 45.120323181152344
38 44.46263122558594
39 43.812255859375
40 43.16917037963867
41 42.533348083496094
42 41.904762268066406
43 41.28337860107422
44 40.669158935546875
45 40.06208419799805
46 39.46210861206055
47 38.86919403076172
48 38.283302307128906
49 37.70439910888672
50 37.13243103027344
51 36.56737518310547
52 36.00917053222656
53 35.457786560058594
54 34.913177490234375
55 34.37528610229492
56 33.844078063964844
57 33.31950378417969
58 32.80152130126953
59 32.290069580078125
60 31.785110473632812
61 31.28660011291504
62 30.794479370117188
63 30.30870246887207
64 29.829219818115234
65 29.355979919433594
66 28.888935089111328
67 28.428035736083984
68 27.97323226928711
69 27.52446746826172
70 27.081693649291992
71 26.644861221313477
72 26.21392250061035
73 25.788818359375
74 25.36949920654297
75 24.95591926574707
76 24.548019409179688
77 24.145755767822266
78 23.749069213867188
79 23.35791778564453
80 22.972244262695312
81 22.59199333190918
82 22.217117309570312
83 21.847570419311523
84 21.483293533325195
85 21.12424087524414
86 20.770357131958008
87 20.421592712402344
88 20.07790184020996
89 19.739225387573242
90 19.405517578125
91 19.07672882080078
92 18.7528076171875
93 18.433700561523438
94 18.119361877441406
95 17.809741973876953
96 17.504789352416992
97 17.204452514648438
98 16.90868377685547
99 16.617433547973633
100 16.330656051635742
101 16.048295974731445
102 15.77031135559082
103 15.496650695800781
104 15.227263450622559
105 14.962108612060547
106 14.701131820678711
107 14.444283485412598
108 14.191522598266602
109 13.942800521850586
110 13.698066711425781
111 13.457279205322266
112 13.220386505126953
113 12.987346649169922
114 12.758111953735352
115 12.532634735107422
116 12.310872077941895
117 12.092779159545898
118 11.878307342529297
119 11.667415618896484
120 11.460057258605957
121 11.256189346313477
122 11.055767059326172
123 10.858745574951172
124 10.665084838867188
125 10.474738121032715
126 10.287666320800781
127 10.103822708129883
128 9.923168182373047
129 9.745658874511719
130 9.571252822875977
131 9.399909973144531
132 9.231588363647461
133 9.066245079040527
134 8.90384292602539
135 8.744339942932129
136 8.587697982788086
137 8.43387508392334
138 8.282833099365234
139 8.134530067443848
140 7.988931655883789
141 7.845998764038086
142 7.705689430236816
143 7.567971229553223
144 7.432806015014648
145 7.300151348114014
146 7.1699748039245605
147 7.042239189147949
148 6.916906833648682
149 6.793943405151367
150 6.673313140869141
151 6.554978370666504
152 6.438908576965332
153 6.325067043304443
154 6.213418483734131
155 6.103930473327637
156 5.996567726135254
157 5.891299247741699
158 5.788090705871582
159 5.6869096755981445
160 5.5877251625061035
161 5.49050235748291
162 5.395212173461914
163 5.301821708679199
164 5.21030330657959
165 5.1206207275390625
166 5.032748222351074
167 4.946656227111816
168 4.862311840057373
169 4.779687881469727
170 4.698754787445068
171 4.619483947753906
172 4.541847229003906
173 4.465815544128418
174 4.391365051269531
175 4.3184638023376465
176 4.247086524963379
177 4.177209377288818
178 4.108800888061523
179 4.041836738586426
180 3.976295232772827
181 3.9121463298797607
182 3.8493666648864746
183 3.787931442260742
184 3.727816104888916
185 3.6689963340759277
186 3.6114494800567627
187 3.555152416229248
188 3.5000805854797363
189 3.446211576461792
190 3.393522262573242
191 3.341992139816284
192 3.291597366333008
193 3.2423181533813477
194 3.194131851196289
195 3.147017478942871
196 3.100956916809082
197 3.0559258460998535
198 3.0119051933288574
199 2.9688799381256104
200 2.926823139190674
201 2.885720729827881
202 2.8455519676208496
203 2.80629825592041
204 2.76794171333313
205 2.730464458465576
206 2.6938467025756836
207 2.658074378967285
208 2.6231274604797363
209 2.5889902114868164
210 2.555644989013672
211 2.5230770111083984
212 2.4912686347961426
213 2.460205554962158
214 2.4298691749572754
215 2.400247573852539
216 2.371324062347412
217 2.3430824279785156
218 2.3155088424682617
219 2.2885916233062744
220 2.2623133659362793
221 2.236661672592163
222 2.211623191833496
223 2.187182664871216
224 2.163328170776367
225 2.140047550201416
226 2.1173276901245117
227 2.0951552391052246
228 2.0735201835632324
229 2.0524063110351562
230 2.031805992126465
231 2.0117058753967285
232 1.99209463596344
233 1.9729598760604858
234 1.9542920589447021
235 1.9360814094543457
236 1.918316125869751
237 1.9009848833084106
238 1.8840787410736084
239 1.8675884008407593
240 1.8515033721923828
241 1.8358139991760254
242 1.8205106258392334
243 1.8055843114852905
244 1.791025996208191
245 1.7768267393112183
246 1.7629787921905518
247 1.7494722604751587
248 1.7363014221191406
249 1.7234545946121216
250 1.7109260559082031
251 1.6987075805664062
252 1.686791181564331
253 1.6751692295074463
254 1.6638338565826416
255 1.652780294418335
256 1.6419994831085205
257 1.6314845085144043
258 1.6212302446365356
259 1.611228585243225
260 1.6014745235443115
261 1.5919599533081055
262 1.5826785564422607
263 1.573627233505249
264 1.564797043800354
265 1.5561835765838623
266 1.5477813482284546
267 1.539583444595337
268 1.531585454940796
269 1.5237834453582764
270 1.516170859336853
271 1.508741855621338
272 1.5014925003051758
273 1.4944188594818115
274 1.4875149726867676
275 1.4807758331298828
276 1.4741991758346558
277 1.4677786827087402
278 1.461510419845581
279 1.4553906917572021
280 1.4494149684906006
281 1.4435794353485107
282 1.4378809928894043
283 1.432314157485962
284 1.4268763065338135
285 1.4215648174285889
286 1.416374683380127
287 1.4113030433654785
288 1.4063470363616943
289 1.4015024900436401
290 1.3967658281326294
291 1.3921360969543457
292 1.3876075744628906
293 1.3831793069839478
294 1.3788474798202515
295 1.3746098279953003
296 1.3704642057418823
297 1.3664060831069946
298 1.3624346256256104
299 1.3585468530654907
300 1.3547394275665283
301 1.3510115146636963
302 1.3473589420318604
303 1.343780517578125
304 1.3402751684188843
305 1.3368384838104248
306 1.3334698677062988
307 1.3301657438278198
308 1.3269264698028564
309 1.3237487077713013
310 1.3206310272216797
311 1.317570686340332
312 1.3145663738250732
313 1.3116172552108765
314 1.3087208271026611
315 1.3058750629425049
316 1.30307936668396
317 1.3003323078155518
318 1.297631025314331
319 1.29497492313385
320 1.2923626899719238
321 1.289792776107788
322 1.2872636318206787
323 1.2847744226455688
324 1.2823233604431152
325 1.2799098491668701
326 1.2775323390960693
327 1.2751896381378174
328 1.2728803157806396
329 1.2706034183502197
330 1.2683587074279785
331 1.2661442756652832
332 1.2639589309692383
333 1.2618035078048706
334 1.2596746683120728
335 1.257573127746582
336 1.2554970979690552
337 1.253446102142334
338 1.2514185905456543
339 1.2494145631790161
340 1.247434139251709
341 1.2454745769500732
342 1.243537187576294
343 1.2416186332702637
344 1.2397209405899048
345 1.2378422021865845
346 1.2359806299209595
347 1.2341375350952148
348 1.2323123216629028
349 1.2305020093917847
350 1.2287085056304932
351 1.2269303798675537
352 1.2251675128936768
353 1.2234179973602295
354 1.221683144569397
355 1.2199612855911255
356 1.218252182006836
357 1.2165557146072388
358 1.2148706912994385
359 1.2131974697113037
360 1.211535096168518
361 1.2098841667175293
362 1.2082427740097046
363 1.2066116333007812
364 1.204990029335022
365 1.2033777236938477
366 1.2017743587493896
367 1.2001795768737793
368 1.1985926628112793
369 1.1970137357711792
370 1.195443034172058
371 1.1938796043395996
372 1.192323088645935
373 1.1907728910446167
374 1.1892297267913818
375 1.187692642211914
376 1.1861613988876343
377 1.1846365928649902
378 1.183117389678955
379 1.1816024780273438
380 1.180093765258789
381 1.1785897016525269
382 1.177091121673584
383 1.1755962371826172
384 1.1741057634353638
385 1.1726197004318237
386 1.171137809753418
387 1.1696598529815674
388 1.1681857109069824
389 1.1667149066925049
390 1.165247917175293
391 1.1637840270996094
392 1.1623235940933228
393 1.1608657836914062
394 1.1594107151031494
395 1.157958745956421
396 1.1565097570419312
397 1.1550630331039429
398 1.1536190509796143
399 1.152176856994629
400 1.1507372856140137
401 1.1493000984191895
402 1.147864580154419
403 1.1464306116104126
404 1.1449998617172241
405 1.1435694694519043
406 1.1421420574188232
407 1.1407157182693481
408 1.1392905712127686
409 1.1378672122955322
410 1.13644540309906
411 1.1350250244140625
412 1.133606195449829
413 1.132188081741333
414 1.1307710409164429
415 1.1293559074401855
416 1.1279412508010864
417 1.1265281438827515
418 1.1251156330108643
419 1.123704433441162
420 1.1222939491271973
421 1.1208841800689697
422 1.119475245475769
423 1.1180672645568848
424 1.1166596412658691
425 1.1152534484863281
426 1.113847017288208
427 1.112441897392273
428 1.1110377311706543
429 1.1096336841583252
430 1.1082301139831543
431 1.106826901435852
432 1.1054246425628662
433 1.1040222644805908
434 1.1026207208633423
435 1.101219892501831
436 1.0998187065124512
437 1.0984185934066772
438 1.0970187187194824
439 1.0956188440322876
440 1.09421968460083
441 1.0928208827972412
442 1.0914225578308105
443 1.0900238752365112
444 1.0886261463165283
445 1.0872280597686768
446 1.0858312845230103
447 1.0844335556030273
448 1.0830364227294922
449 1.0816398859024048
450 1.0802432298660278
451 1.07884681224823
452 1.0774507522583008
453 1.0760548114776611
454 1.074658989906311
455 1.0732632875442505
456 1.071867823600769
457 1.070472240447998
458 1.0690771341323853
459 1.0676822662353516
460 1.0662869215011597
461 1.0648924112319946
462 1.0634981393814087
463 1.0621037483215332
464 1.060708999633789
465 1.0593152046203613
466 1.0579206943511963
467 1.0565274953842163
468 1.0551329851150513
469 1.0537396669387817
470 1.0523457527160645
471 1.050952672958374
472 1.0495595932006836
473 1.0481665134429932
474 1.046773076057434
475 1.045379877090454
476 1.0439872741699219
477 1.0425946712493896
478 1.0412020683288574
479 1.0398097038269043
480 1.038417100906372
481 1.0370252132415771
482 1.0356335639953613
483 1.0342413187026978
484 1.032849669456482
485 1.0314579010009766
486 1.0300660133361816
487 1.0286747217178345
488 1.0272836685180664
489 1.025892734527588
490 1.0245015621185303
491 1.0231103897094727
492 1.0217199325561523
493 1.0203297138214111
494 1.0189392566680908
495 1.0175485610961914
496 1.016158938407898
497 1.0147688388824463
498 1.0133793354034424
499 1.0119895935058594
500 1.0106004476547241
501 1.0092110633850098
502 1.007822036743164
503 1.0064334869384766
504 1.005044937133789
505 1.0036563873291016
506 1.0022687911987305
507 1.0008801221847534
508 0.9994925856590271
509 0.9981048107147217
510 0.9967176914215088
511 0.9953306317329407
512 0.9939436912536621
513 0.9925569891929626
514 0.991170346736908
515 0.9897842407226562
516 0.9883979558944702
517 0.9870126247406006
518 0.9856271743774414
519 0.9842422008514404
520 0.9828568696975708
521 0.9814721345901489
522 0.9800871014595032
523 0.9787031412124634
524 0.977319061756134
525 0.9759358167648315
526 0.9745523929595947
527 0.9731693267822266
528 0.9717866778373718
529 0.9704040288925171
530 0.9690216183662415
531 0.9676398634910583
532 0.9662580490112305
533 0.9648770093917847
534 0.9634960889816284
535 0.9621152877807617
536 0.9607350826263428
537 0.9593547582626343
538 0.9579752683639526
539 0.9565959572792053
540 0.9552173614501953
541 0.9538382291793823
542 0.9524598717689514
543 0.9510821104049683
544 0.949704647064209
545 0.9483271837234497
546 0.9469503164291382
547 0.9455736875534058
548 0.9441971778869629
549 0.9428222179412842
550 0.9414463639259338
551 0.9400722980499268
552 0.9386969804763794
553 0.9373229742050171
554 0.9359492063522339
555 0.9345760345458984
556 0.9332026243209839
557 0.9318302869796753
558 0.9304581880569458
559 0.9290866851806641
560 0.9277158975601196
561 0.9263440370559692
562 0.9249739646911621
563 0.9236034154891968
564 0.9222346544265747
565 0.9208654165267944
566 0.9194968938827515
567 0.9181283712387085
568 0.9167606830596924
569 0.915393590927124
570 0.91402667760849
571 0.9126612544059753
572 0.9112955331802368
573 0.9099300503730774
574 0.9085650444030762
575 0.9072009325027466
576 0.9058372378349304
577 0.904474139213562
578 0.9031108021736145
579 0.901748776435852
580 0.9003862142562866
581 0.8990248441696167
582 0.8976646661758423
583 0.8963040113449097
584 0.8949441909790039
585 0.8935853838920593
586 0.8922266364097595
587 0.8908682465553284
588 0.8895108699798584
589 0.888153612613678
590 0.8867970705032349
591 0.8854413032531738
592 0.8840858936309814
593 0.8827314376831055
594 0.8813769817352295
595 0.8800232410430908
596 0.8786699771881104
597 0.877317488193512
598 0.8759661912918091
599 0.8746145367622375
600 0.873263955116272
601 0.8719136714935303
602 0.8705644607543945
603 0.8692153096199036
604 0.8678669929504395
605 0.8665192127227783
606 0.8651715517044067
607 0.8638256788253784
608 0.8624793887138367
609 0.8611346483230591
610 0.8597896099090576
611 0.8584458827972412
612 0.8571021556854248
613 0.8557597398757935
614 0.8544173836708069
615 0.8530756235122681
616 0.8517352342605591
617 0.8503947257995605
618 0.8490554094314575
619 0.8477169275283813
620 0.84637850522995
621 0.8450407981872559
622 0.8437040448188782
623 0.8423681855201721
624 0.8410332202911377
625 0.839698314666748
626 0.8383642435073853
627 0.8370309472084045
628 0.8356978297233582
629 0.8343659043312073
630 0.8330344557762146
631 0.8317039608955383
632 0.8303738236427307
633 0.8290453553199768
634 0.8277170062065125
635 0.8263890743255615
636 0.8250622153282166
637 0.8237359523773193
638 0.822409987449646
639 0.8210856318473816
640 0.8197613954544067
641 0.8184381723403931
642 0.817115843296051
643 0.8157939314842224
644 0.814472496509552
645 0.8131524324417114
646 0.8118323087692261
647 0.8105140328407288
648 0.8091951012611389
649 0.807878315448761
650 0.8065618276596069
651 0.8052458763122559
652 0.8039308786392212
653 0.8026171922683716
654 0.8013036251068115
655 0.7999911308288574
656 0.7986792325973511
657 0.7973682284355164
658 0.7960574626922607
659 0.7947486042976379
660 0.7934401035308838
661 0.7921321988105774
662 0.7908249497413635
663 0.7895179986953735
664 0.7882125973701477
665 0.7869082093238831
666 0.7856042385101318
667 0.7843017578125
668 0.7829991579055786
669 0.78169846534729
670 0.7803975343704224
671 0.7790980339050293
672 0.7777993679046631
673 0.7765015363693237
674 0.7752041220664978
675 0.7739077210426331
676 0.7726120948791504
677 0.7713176608085632
678 0.7700244784355164
679 0.768731415271759
680 0.7674394845962524
681 0.7661483883857727
682 0.7648578882217407
683 0.7635684609413147
684 0.7622798085212708
685 0.7609926462173462
686 0.7597064971923828
687 0.7584200501441956
688 0.757135272026062
689 0.7558512687683105
690 0.7545679807662964
691 0.7532857656478882
692 0.7520039081573486
693 0.7507238984107971
694 0.7494442462921143
695 0.7481656670570374
696 0.746887743473053
697 0.7456105351448059
698 0.7443349361419678
699 0.7430600523948669
700 0.7417857646942139
701 0.7405126094818115
702 0.7392405867576599
703 0.7379692792892456
704 0.7366986274719238
705 0.7354295253753662
706 0.734160840511322
707 0.7328929901123047
708 0.7316263318061829
709 0.7303608655929565
710 0.7290961742401123
711 0.7278319597244263
712 0.7265700101852417
713 0.7253075838088989
714 0.7240464687347412
715 0.7227869033813477
716 0.7215279340744019
717 0.7202697396278381
718 0.7190126180648804
719 0.7177562713623047
720 0.7165012359619141
721 0.7152470350265503
722 0.713994026184082
723 0.7127417325973511
724 0.7114908695220947
725 0.7102402448654175
726 0.708991289138794
727 0.7077429294586182
728 0.7064957618713379
729 0.7052496075630188
730 0.7040042281150818
731 0.7027602791786194
732 0.7015162706375122
733 0.7002747058868408
734 0.6990330219268799
735 0.6977927088737488
736 0.6965535283088684
737 0.6953158378601074
738 0.6940786242485046
739 0.6928420066833496
740 0.6916073560714722
741 0.6903733611106873
742 0.6891401410102844
743 0.687907874584198
744 0.6866771578788757
745 0.6854472160339355
746 0.6842181086540222
747 0.6829899549484253
748 0.6817634105682373
749 0.6805371046066284
750 0.6793124079704285
751 0.6780890822410583
752 0.6768659949302673
753 0.6756446361541748
754 0.6744242310523987
755 0.673204243183136
756 0.67198646068573
757 0.6707682013511658
758 0.6695523262023926
759 0.6683372259140015
760 0.6671223044395447
761 0.6659096479415894
762 0.6646977066993713
763 0.6634865999221802
764 0.6622768640518188
765 0.6610680222511292
766 0.6598601937294006
767 0.6586534976959229
768 0.657447874546051
769 0.6562433242797852
770 0.65503990650177
771 0.6538375616073608
772 0.6526364088058472
773 0.6514362692832947
774 0.6502371430397034
775 0.6490389108657837
776 0.6478418111801147
777 0.6466465592384338
778 0.6454519629478455
779 0.6442580819129944
780 0.6430658102035522
781 0.6418745517730713
782 0.6406842470169067
783 0.6394948363304138
784 0.6383069157600403
785 0.6371200680732727
786 0.6359342932701111
787 0.6347496509552002
788 0.63356614112854
789 0.6323837041854858
790 0.6312023401260376
791 0.6300224661827087
792 0.6288437247276306
793 0.6276652812957764
794 0.6264888048171997
795 0.625313401222229
796 0.6241387128829956
797 0.6229650974273682
798 0.6217929124832153
799 0.6206222176551819
800 0.6194519400596619
801 0.6182833909988403
802 0.6171156167984009
803 0.6159493327140808
804 0.614783763885498
805 0.6136201620101929
806 0.6124567985534668
807 0.6112948060035706
808 0.6101344227790833
809 0.6089747548103333
810 0.6078166365623474
811 0.6066591143608093
812 0.6055030822753906
813 0.6043481230735779
814 0.6031947135925293
815 0.6020423173904419
816 0.6008907556533813
817 0.5997405052185059
818 0.5985913872718811
819 0.5974433422088623
820 0.5962969064712524
821 0.5951517820358276
822 0.5940070748329163
823 0.592863917350769
824 0.5917217135429382
825 0.5905809998512268
826 0.5894414186477661
827 0.5883033275604248
828 0.5871662497520447
829 0.5860303640365601
830 0.5848957300186157
831 0.5837616324424744
832 0.5826293230056763
833 0.5814980864524841
834 0.580367922782898
835 0.5792388916015625
836 0.5781115889549255
837 0.5769854784011841
838 0.5758597254753113
839 0.5747359991073608
840 0.573613166809082
841 0.5724914073944092
842 0.5713709592819214
843 0.5702520608901978
844 0.5691338777542114
845 0.5680175423622131
846 0.5669018030166626
847 0.5657879710197449
848 0.5646744966506958
849 0.5635623931884766
850 0.5624518394470215
851 0.561342716217041
852 0.5602341890335083
853 0.5591272711753845
854 0.558022141456604
855 0.5569171905517578
856 0.5558139085769653
857 0.5547115802764893
858 0.5536109209060669
859 0.5525111556053162
860 0.5514127612113953
861 0.5503158569335938
862 0.5492197275161743
863 0.5481252670288086
864 0.5470314621925354
865 0.5459392666816711
866 0.5448483824729919
867 0.5437586307525635
868 0.5426698923110962
869 0.5415827035903931
870 0.540496826171875
871 0.5394120812416077
872 0.5383283495903015
873 0.5372465252876282
874 0.5361652970314026
875 0.5350855588912964
876 0.53400719165802
877 0.5329298973083496
878 0.5318533778190613
879 0.5307788848876953
880 0.5297055244445801
881 0.5286327600479126
882 0.5275626182556152
883 0.5264925360679626
884 0.5254241228103638
885 0.5243571996688843
886 0.5232908129692078
887 0.5222263336181641
888 0.5211629271507263
889 0.520100474357605
890 0.5190395712852478
891 0.5179795622825623
892 0.5169217586517334
893 0.5158646106719971
894 0.5148086547851562
895 0.5137540698051453
896 0.5127005577087402
897 0.5116487145423889
898 0.5105979442596436
899 0.509548544883728
900 0.5084999799728394
901 0.5074533820152283
902 0.5064074993133545
903 0.5053631067276001
904 0.5043204426765442
905 0.5032788515090942
906 0.5022381544113159
907 0.5011982917785645
908 0.5001605153083801
909 0.49912387132644653
910 0.4980884790420532
911 0.4970548152923584
912 0.4960212707519531
913 0.4949900507926941
914 0.49395957589149475
915 0.49293094873428345
916 0.491903156042099
917 0.4908769130706787
918 0.48985159397125244
919 0.48882779479026794
920 0.4878048896789551
921 0.4867837429046631
922 0.48576343059539795
923 0.4847453832626343
924 0.48372775316238403
925 0.4827115535736084
926 0.4816969633102417
927 0.48068317770957947
928 0.4796709716320038
929 0.47865986824035645
930 0.47765088081359863
931 0.47664231061935425
932 0.4756356477737427
933 0.47463005781173706
934 0.47362545132637024
935 0.472622275352478
936 0.47162050008773804
937 0.4706196188926697
938 0.4696205258369446
939 0.4686221480369568
940 0.46762579679489136
941 0.46663016080856323
942 0.4656361937522888
943 0.46464356780052185
944 0.46365243196487427
945 0.4626621603965759
946 0.4616733193397522
947 0.46068620681762695
948 0.4596996605396271
949 0.45871496200561523
950 0.4577317535877228
951 0.4567490220069885
952 0.4557684063911438
953 0.4547886550426483
954 0.45381033420562744
955 0.452833354473114
956 0.4518572688102722
957 0.45088309049606323
958 0.44991010427474976
959 0.448938250541687
960 0.4479675889015198
961 0.446998655796051
962 0.44603046774864197
963 0.4450642168521881
964 0.4440993070602417
965 0.4431350827217102
966 0.44217222929000854
967 0.4412113428115845
968 0.4402511715888977
969 0.43929266929626465
970 0.4383354187011719
971 0.43737953901290894
972 0.4364246726036072
973 0.4354711174964905
974 0.4345192313194275
975 0.43356844782829285
976 0.43261921405792236
977 0.43167102336883545
978 0.43072405457496643
979 0.4297788441181183
980 0.4288349151611328
981 0.42789143323898315
982 0.426950067281723
983 0.4260098338127136
984 0.42507117986679077
985 0.42413392663002014
986 0.4231972098350525
987 0.4222624897956848
988 0.4213288426399231
989 0.4203967750072479
990 0.41946542263031006
991 0.4185360074043274
992 0.4176079034805298
993 0.4166807234287262
994 0.4157549738883972
995 0.41483068466186523
996 0.4139077961444855
997 0.41298624873161316
998 0.41206538677215576
999 0.4111466407775879
w= 1.5620301961898804
b= 0.970091700553894
y_pre tensor([7.2182])

当用SGD且epcho=100

当用SGD且epcho=1000

PyTorch深度学习实践05相关推荐

《PyTorch深度学习实践》
[<PyTorch深度学习实践>完结合集] https://www.bilibili.com/video/BV1Y7411d7Ys/?share_source=copy_web&v ...
【刘二大人】PyTorch深度学习实践
文章目录一.overview 1 机器学习二.Linear_Model(线性模型) 1 例子引入三.Gradient_Descent(梯度下降法) 1 梯度下降 2 梯度下降与随机梯度下降(SG ...
PyTorch深度学习实践
根据学习情况随时更新. 2020.08.14更新完成. 参考课程-刘二大人<PyTorch深度学习实践> 文章目录 (一)课程概述 (二)线性模型 (三)梯度下降算法 (四)反向传播 (五 ...
【Pytorch深度学习实践】B站up刘二大人之SoftmaxClassifier-代码理解与实现(8/9)
这是刘二大人系列课程笔记的倒数第二个博客了,介绍的是多分类器的原理和代码实现,下一个笔记就是basicCNN和advancedCNN了: 写在前面: 这节课的内容,主要是两个部分的修改: 一是数据集: ...
【Pytorch深度学习实践】B站up刘二大人课程笔记——目录与索引（已完结）
从有代码的课程开始讨论 [Pytorch深度学习实践]B站up刘二大人之LinearModel -代码理解与实现(1/9) [Pytorch深度学习实践]B站up刘二大人之 Gradient Desc ...
《PyTorch 深度学习实践》第10讲卷积神经网络（基础篇）
文章目录 1 卷积层 1.1 torch.nn.Conv2d相关参数 1.2 填充:padding 1.3 步长:stride 2 最大池化层 3 手写数字识别该专栏内容为对该视频的学习记录:[&l ...
PyTorch 深度学习实践第13讲
PyTorch 深度学习实践第13讲引言代码结果引言近期学习了B站刘二大人的PyTorch深度学习实践,传送门PyTorch 深度学习实践--循环神经网络(高级篇),感觉受益匪浅,发现网 ...
刘二大人 PyTorch深度学习实践笔记 P6 逻辑斯蒂回归
刘二大人 PyTorch深度学习实践笔记 P6 逻辑斯蒂回归 P6 逻辑斯蒂回归 1.torchversion 提供的数据集 2.基本概念 3.代码实现 P6 逻辑斯蒂回归 1.torchversi ...
《PyTorch深度学习实践》课堂笔记 Lesson7 神经网络多维特征输入的原理推导与实现
文章目录 1.为什么使用多维的特征输入 2. 多维特征向量输入推导 3.实现过程 3.1源代码 3.2训练结果写在最后 1.为什么使用多维的特征输入对于现实世界来说,影响一个事物发展的因素有很多种 ...

PyTorch深度学习实践05

Linear regression with pytorch

PyTorch深度学习实践05相关推荐

最新文章

热门文章