The value of Miou is abnormally small，why?
zcc720 opened this issue · 2 comments
I'm a little confused about whether it's a data problem or a code problem
Here is the log information：
,epoch,train_loss,mIOU,time
0,1,0.7561731152236462,0.03367172123101207,172.40587258338928
1,2,0.748881900539765,0.03683467247028115,174.69739818572998
2,3,0.7231125767127826,0.03413524813319142,176.4995617866516
3,4,0.7103231128018636,0.034718840754135,175.68166756629944
4,5,0.6948323705448554,0.03985984205367289,176.37116837501526
5,6,0.6963401340091457,0.034812881275243984,175.4205687046051
6,7,0.670259090176282,0.039593741565003365,177.59505224227905
7,8,0.657163177903455,0.04566971232266198,177.0455219745636
8,9,0.6466049935955268,0.04648490031142609,175.9458737373352
9,10,0.6441954008948344,0.040296921257545505,175.44736456871033
10,11,0.6518893415251603,0.040108131647718384,173.6164116859436
11,12,0.6342953191353724,0.04960548057842536,174.7338092327118
12,13,0.627325470559299,0.04964727835046585,176.74344968795776
13,14,0.6132798489326468,0.05281939904056167,175.50420832633972
14,15,0.6002895892239534,0.055861818521504104,176.07024669647217
15,16,0.6025141052042062,0.05466266379947758,177.30515456199646
16,17,0.6029521900300796,0.04238770927785353,175.8492751121521
17,18,0.5934671195080647,0.07225978056218663,173.75626182556152
18,19,0.5773926787078381,0.048255481604236414,174.74913358688354
19,20,0.582425432673727,0.059308266458931364,176.88284063339233
20,21,0.5682540397661237,0.05038267338739297,174.98791122436523
21,22,0.5746843272533554,0.05538608518532103,173.91722106933594
22,23,0.5666266437619925,0.08541678590371297,174.55052709579468
23,24,0.5560441032911723,0.06600933025918862,175.00977063179016
24,25,0.5517762127833871,0.06934330535863947,178.28503155708313
25,26,0.5430047279940202,0.07609816247099357,173.69276547431946
26,27,0.5501473788888409,0.08342366132038433,177.11464619636536
27,28,0.5378253686313446,0.09859108165162175,176.39698958396912
28,29,0.5331599443721083,0.0678868360658615,176.34525656700134
29,30,0.5324760234126678,0.10438792503626895,176.21589493751526
30,31,0.5238752497646672,0.1128183428160334,175.78917503356934
31,32,0.5251926730315273,0.12039694674205649,176.04383778572083
32,33,0.5220876589345818,0.09766672767178268,174.95863962173462
33,34,0.5175259400588962,0.10621496236219143,176.0151607990265
34,35,0.5067871576175094,0.12684976035995407,177.03462433815002
35,36,0.49546105708353794,0.11654276929771637,176.7458143234253
36,37,0.494680989605303,0.124827549423532,176.56689929962158
37,38,0.506546473918626,0.13644115255903136,176.26826405525208
38,39,0.49985619039776236,0.13591350946832806,175.53716468811035
39,40,0.4863511062083909,0.1471462457362383,172.9881386756897
40,41,0.47111362118560535,0.16850882157957298,178.14349603652954
41,42,0.4635956700389775,0.17315480519723986,174.8266270160675
42,43,0.47008128091692924,0.1753281237951893,177.32808256149292
43,44,0.46045722468541217,0.16734526537605668,181.26892566680908
44,45,0.47051489163333404,0.1779139305812485,176.50252866744995
45,46,0.4693494217040447,0.1737308142689212,173.95223832130432
46,47,0.4636622975007273,0.17580288567626196,174.41174721717834
47,48,0.47545362876441616,0.18437971651423307,175.14617395401
48,49,0.48231911250891596,0.17996943729784323,175.4971604347229
49,50,0.4861245102678927,0.1646887044495716,172.72737431526184
50,51,0.4998336468751614,0.1784439646198613,178.50492978096008
51,52,0.5165176399481984,0.17607720511222485,177.06681728363037
52,53,0.5195794134902266,0.17282210617745608,177.14761924743652
53,54,0.5199347996654419,0.17748172026042575,173.87622380256653
54,55,0.527843453706457,0.17620730130932943,174.56411957740784
55,56,0.5464535670784804,0.1823876403320441,175.65909218788147
56,57,0.5455715203514466,0.17574022854965982,175.3632197380066
57,58,0.5364228865275016,0.18073436845138688,173.09280729293823
58,59,0.536486465913745,0.17925631794081523,181.71167612075806
59,60,0.5356380167202308,0.17350742104516761,174.03977036476135
After I motify the code in segmentation/main.py
line 157 :
total_loss = total_loss / (i + 1) --> total_loss = total_loss / (len(train_loader))
log looks normal than before.but The accuracy is worse than that mentioned in the paper!
Can you see what the problem is？
python main.py --data_dir ./datasets/VOCdevkit --batch_size 8 --alpha 1 --beta 50
log info:
,epoch,train_loss,mIOU,time
0,1,0.7261000863061502,0.057586553258071126,178.6142611503601
1,2,0.6097014355831422,0.063049190510802,176.03392815589905
2,3,0.5578123452858283,0.09731516895192038,176.24638843536377
3,4,0.5278288968122349,0.13828997719296643,177.99367380142212
4,5,0.49451022416066664,0.15140902059892525,176.5463833808899
5,6,0.4651602731945996,0.21775019007977517,178.41293025016785
6,7,0.4455281266441139,0.23862078347770282,180.37586116790771
7,8,0.41575628185931307,0.26695837222391916,178.89479088783264
8,9,0.4130474251265136,0.32087629934397516,177.45510625839233
9,10,0.38873763780037945,0.32781030099213915,174.56079411506653
10,11,0.38117676647379994,0.3048197474088396,182.20393657684326
11,12,0.35919564973133117,0.4124213468487616,183.22360110282898
12,13,0.33550255355210257,0.41639623208455734,183.23728203773499
13,14,0.32541378752256817,0.4728299750109155,184.2327709197998
14,15,0.31444430403196466,0.4658517832352009,184.49342918395996
15,16,0.37428842750019753,0.392436243520923,181.56962418556213
16,17,0.33512748763538325,0.42050666654903956,182.76143145561218
17,18,0.32322315230535775,0.4480134363244914,182.2139663696289
18,19,0.28664670393873865,0.48552067383069414,185.38020372390747
19,20,0.28094341405309164,0.5220441072274593,183.49661540985107
20,21,0.2946164899219114,0.393541376174548,181.4161877632141
21,22,0.29337784304068637,0.49082619493104124,183.75677299499512
22,23,0.27401041065772563,0.5364661445726908,180.77828073501587
23,24,0.2566435071460616,0.5399215858103634,178.4039568901062
24,25,0.24616063619032502,0.5783223556825947,178.20377564430237
25,26,0.23087580869189248,0.5738894415830091,182.93589401245117
26,27,0.23414199294235843,0.5694262227728241,182.06718802452087
27,28,0.22885445557319775,0.5771987586983848,177.92537093162537
28,29,0.21909973180243889,0.5587388255254337,181.48252606391907
29,30,0.21949142760310608,0.6043115007715125,180.9317126274109
30,31,0.2071511959298872,0.6227095083801766,182.16161012649536
31,32,0.2066417523086644,0.6117738408028581,181.3745265007019
32,33,0.19651665157065368,0.6332767287195358,179.28102684020996
33,34,0.19335692232617965,0.6123993044848869,175.07483530044556
34,35,0.18696148710576102,0.6195088758825039,180.53877449035645
35,36,0.18073981857070556,0.6635264246409703,183.4003143310547
36,37,0.17892846782118654,0.6464527752425618,174.13444089889526
37,38,0.1744404370771148,0.6148941087211162,180.02770280838013
38,39,0.17660696120359576,0.6519172054396049,174.07084894180298
39,40,0.17158483173877287,0.6382632054658569,180.72155785560608
40,41,0.15626109964572465,0.6910818167306936,183.64324831962585
41,42,0.14839063008100942,0.6883363737870288,182.43007469177246
42,43,0.1522352682122101,0.6930279778742292,177.73602676391602
43,44,0.14743588383022982,0.6914783321960248,182.26002144813538
44,45,0.15477619560148853,0.6917784234430908,175.00939202308655
45,46,0.15464300201990858,0.6909633731934169,183.01323437690735
46,47,0.1549238166771829,0.7007349276837773,182.09069061279297
47,48,0.1667104942115167,0.6867847013260989,182.8640763759613
48,49,0.1734646636312111,0.7087791198462656,183.59194421768188
49,50,0.17799107345322576,0.7027580132084397,184.87926125526428
50,51,0.18792614826144508,0.7006305947573652,182.03565168380737
51,52,0.2059784850392204,0.696934922429397,182.15200638771057
52,53,0.21193618649760118,0.6987400917458917,185.74256682395935
53,54,0.21584948109319577,0.6950729880454363,183.9695544242859
54,55,0.22595454378125185,0.7115041401829636,181.98568606376648
55,56,0.2355772555232621,0.6941329413567948,182.81696248054504
56,57,0.24157170593165433,0.6952093373924405,182.61140513420105
57,58,0.238704457341765,0.6996585254938276,184.6381494998932
58,59,0.23819306994286868,0.7075743043314172,180.01984882354736
59,60,0.24296376950895557,0.691716464811592,182.61791491508484
thx...
Excuse me, have you reproduced the results of the paper?