Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

语义分割炼丹技巧:输入大小 #13

Open
gemfield opened this issue May 27, 2021 · 0 comments
Open

语义分割炼丹技巧:输入大小 #13

gemfield opened this issue May 27, 2021 · 0 comments

Comments

@gemfield
Copy link
Contributor

gemfield commented May 27, 2021

输入大小的pk

数据集

  • 训练集:clothes std 2.1
  • 验证集:LIP986

炼丹参数

  • config.core.cls_num = 4
  • config.aug.ImageWithMasksRandomRotateAug.max_angle = 45
  • config.core.batch_size = 8
  • config.core.mean = config.data['mean']
  • config.core.std = config.data['std']
  • config.core.model_path = "/opt/public/pretrain/ESPNetv2/imagenet/espnetv2_s_2.0.pth"
  • config.core.optimizer = torch.optim.SGD(config.core.net.parameters(), 5e-3, momentum=0.9)
  • config.core.scheduler = optim.lr_scheduler.MultiStepLR(config.core.optimizer, milestones=[20,40,55,70,80,90,100,110,120,130,140,150,160], gamma=0.27030)
  • config.core.train_loader_list = [scale1_train_loader, scale2_train_loader, scale4_train_loader, scale3_train_loader, last_train_loader] i.e. 2.0, 1.75, 1.5, 1.25, 1
  • config.core.criterion = torch.nn.CrossEntropyLoss(weight)
  • AugFactory('SpeckleAug@0.1 => GaussianAug@0.1 => HorlineAug@0.1 => VerlineAug@0.1 => LRmotionAug@0.1 =>UDmotionAug@0.1 => NoisyAug@0.1 => DarkAug@0.1 => ColorJitterAug@0.15 => BrightnessJitterAug@0.15 =>ContrastJitterAug@0.15 => ImageWithMasksRandomRotateAug@0.6 => ImageWithMasksNormalizeAug =>ImageWithMasksCenterCropAug => ImageWithMasksScaleAug => ImageWithMasksHFlipAug@0.5 =>ImageWithMasksToTensorAug', deepvac_config)

Train

224 * 224

Epoch No.: 0    TRAIN Loss = 0.7503      TRAIN mIOU = 0.6238
Epoch No.: 1    TRAIN Loss = 0.6713      TRAIN mIOU = 0.6503
Epoch No.: 2    TRAIN Loss = 0.6205      TRAIN mIOU = 0.6682
Epoch No.: 3    TRAIN Loss = 0.5997      TRAIN mIOU = 0.6793
Epoch No.: 4    TRAIN Loss = 0.5516      TRAIN mIOU = 0.6917
Epoch No.: 5    TRAIN Loss = 0.5643      TRAIN mIOU = 0.6878
Epoch No.: 6    TRAIN Loss = 0.5286      TRAIN mIOU = 0.7039
Epoch No.: 7    TRAIN Loss = 0.4977      TRAIN mIOU = 0.7162
Epoch No.: 8    TRAIN Loss = 0.5040      TRAIN mIOU = 0.7120
Epoch No.: 9    TRAIN Loss = 0.4753      TRAIN mIOU = 0.7239
Epoch No.: 10   TRAIN Loss = 0.4736      TRAIN mIOU = 0.7276
Epoch No.: 11   TRAIN Loss = 0.4596      TRAIN mIOU = 0.7330
Epoch No.: 12   TRAIN Loss = 0.4824      TRAIN mIOU = 0.7219
Epoch No.: 13   TRAIN Loss = 0.4568      TRAIN mIOU = 0.7305
Epoch No.: 14   TRAIN Loss = 0.4334      TRAIN mIOU = 0.7418
Epoch No.: 15   TRAIN Loss = 0.4432      TRAIN mIOU = 0.7351
Epoch No.: 16   TRAIN Loss = 0.4297      TRAIN mIOU = 0.7424
Epoch No.: 17   TRAIN Loss = 0.4261      TRAIN mIOU = 0.7426
Epoch No.: 18   TRAIN Loss = 0.4251      TRAIN mIOU = 0.7488
Epoch No.: 19   TRAIN Loss = 0.3926      TRAIN mIOU = 0.7578
Epoch No.: 20   TRAIN Loss = 0.3765      TRAIN mIOU = 0.7647
Epoch No.: 21   TRAIN Loss = 0.3777      TRAIN mIOU = 0.7656
Epoch No.: 22   TRAIN Loss = 0.3639      TRAIN mIOU = 0.7720
Epoch No.: 23   TRAIN Loss = 0.3645      TRAIN mIOU = 0.7768
Epoch No.: 24   TRAIN Loss = 0.3711      TRAIN mIOU = 0.7663
Epoch No.: 25   TRAIN Loss = 0.3508      TRAIN mIOU = 0.7807
Epoch No.: 26   TRAIN Loss = 0.3660      TRAIN mIOU = 0.7690
Epoch No.: 27   TRAIN Loss = 0.3565      TRAIN mIOU = 0.7756
Epoch No.: 28   TRAIN Loss = 0.3547      TRAIN mIOU = 0.7764
Epoch No.: 29   TRAIN Loss = 0.3532      TRAIN mIOU = 0.7725
Epoch No.: 30   TRAIN Loss = 0.3574      TRAIN mIOU = 0.7767
Epoch No.: 31   TRAIN Loss = 0.3525      TRAIN mIOU = 0.7748
Epoch No.: 32   TRAIN Loss = 0.3480      TRAIN mIOU = 0.7758
Epoch No.: 33   TRAIN Loss = 0.3450      TRAIN mIOU = 0.7801
Epoch No.: 34   TRAIN Loss = 0.3431      TRAIN mIOU = 0.7828
Epoch No.: 35   TRAIN Loss = 0.3487      TRAIN mIOU = 0.7782
Epoch No.: 36   TRAIN Loss = 0.3499      TRAIN mIOU = 0.7783
Epoch No.: 37   TRAIN Loss = 0.3369      TRAIN mIOU = 0.7802
Epoch No.: 38   TRAIN Loss = 0.3433      TRAIN mIOU = 0.7827
Epoch No.: 39   TRAIN Loss = 0.3399      TRAIN mIOU = 0.7770
Epoch No.: 40   TRAIN Loss = 0.3399      TRAIN mIOU = 0.7875
Epoch No.: 41   TRAIN Loss = 0.3366      TRAIN mIOU = 0.7849
Epoch No.: 42   TRAIN Loss = 0.3324      TRAIN mIOU = 0.7891
Epoch No.: 43   TRAIN Loss = 0.3333      TRAIN mIOU = 0.7851
Epoch No.: 44   TRAIN Loss = 0.3370      TRAIN mIOU = 0.7825
Epoch No.: 45   TRAIN Loss = 0.3273      TRAIN mIOU = 0.7892
Epoch No.: 46   TRAIN Loss = 0.3370      TRAIN mIOU = 0.7839
Epoch No.: 47   TRAIN Loss = 0.3342      TRAIN mIOU = 0.7854
Epoch No.: 48   TRAIN Loss = 0.3284      TRAIN mIOU = 0.7912
Epoch No.: 49   TRAIN Loss = 0.3266      TRAIN mIOU = 0.7904

384 * 384

Epoch No.: 0    TRAIN Loss = 0.7410      TRAIN mIOU = 0.6298
Epoch No.: 1    TRAIN Loss = 0.6346      TRAIN mIOU = 0.6695
Epoch No.: 2    TRAIN Loss = 0.5823      TRAIN mIOU = 0.6901
Epoch No.: 3    TRAIN Loss = 0.5556      TRAIN mIOU = 0.6985
Epoch No.: 4    TRAIN Loss = 0.5197      TRAIN mIOU = 0.7122
Epoch No.: 5    TRAIN Loss = 0.5197      TRAIN mIOU = 0.7111
Epoch No.: 6    TRAIN Loss = 0.4832      TRAIN mIOU = 0.7300
Epoch No.: 7    TRAIN Loss = 0.4737      TRAIN mIOU = 0.7334
Epoch No.: 8    TRAIN Loss = 0.4673      TRAIN mIOU = 0.7334
Epoch No.: 9    TRAIN Loss = 0.4544      TRAIN mIOU = 0.7406
Epoch No.: 10   TRAIN Loss = 0.4384      TRAIN mIOU = 0.7477
Epoch No.: 11   TRAIN Loss = 0.4404      TRAIN mIOU = 0.7451
Epoch No.: 12   TRAIN Loss = 0.4195      TRAIN mIOU = 0.7553
Epoch No.: 13   TRAIN Loss = 0.4145      TRAIN mIOU = 0.7527
Epoch No.: 14   TRAIN Loss = 0.4114      TRAIN mIOU = 0.7590
Epoch No.: 15   TRAIN Loss = 0.4026      TRAIN mIOU = 0.7625
Epoch No.: 16   TRAIN Loss = 0.3955      TRAIN mIOU = 0.7651
Epoch No.: 17   TRAIN Loss = 0.3965      TRAIN mIOU = 0.7600
Epoch No.: 18   TRAIN Loss = 0.3644      TRAIN mIOU = 0.7791
Epoch No.: 19   TRAIN Loss = 0.3848      TRAIN mIOU = 0.7707
Epoch No.: 20   TRAIN Loss = 0.3595      TRAIN mIOU = 0.7828
Epoch No.: 21   TRAIN Loss = 0.3410      TRAIN mIOU = 0.7878
Epoch No.: 22   TRAIN Loss = 0.3373      TRAIN mIOU = 0.7897
Epoch No.: 23   TRAIN Loss = 0.3347      TRAIN mIOU = 0.7900
Epoch No.: 24   TRAIN Loss = 0.3215      TRAIN mIOU = 0.7972
Epoch No.: 25   TRAIN Loss = 0.3285      TRAIN mIOU = 0.7950
Epoch No.: 26   TRAIN Loss = 0.3271      TRAIN mIOU = 0.7948
Epoch No.: 27   TRAIN Loss = 0.3280      TRAIN mIOU = 0.7967
Epoch No.: 28   TRAIN Loss = 0.3176      TRAIN mIOU = 0.7990
Epoch No.: 29   TRAIN Loss = 0.3174      TRAIN mIOU = 0.7997
Epoch No.: 30   TRAIN Loss = 0.3141      TRAIN mIOU = 0.7984
Epoch No.: 31   TRAIN Loss = 0.3192      TRAIN mIOU = 0.8005
Epoch No.: 32   TRAIN Loss = 0.3201      TRAIN mIOU = 0.8000
Epoch No.: 33   TRAIN Loss = 0.3105      TRAIN mIOU = 0.8026
Epoch No.: 34   TRAIN Loss = 0.3102      TRAIN mIOU = 0.8026
Epoch No.: 35   TRAIN Loss = 0.3039      TRAIN mIOU = 0.8049
Epoch No.: 36   TRAIN Loss = 0.3102      TRAIN mIOU = 0.8012
Epoch No.: 37   TRAIN Loss = 0.3084      TRAIN mIOU = 0.8028
Epoch No.: 38   TRAIN Loss = 0.3047      TRAIN mIOU = 0.8070
Epoch No.: 39   TRAIN Loss = 0.3096      TRAIN mIOU = 0.8071
Epoch No.: 40   TRAIN Loss = 0.3021      TRAIN mIOU = 0.8081
Epoch No.: 41   TRAIN Loss = 0.3000      TRAIN mIOU = 0.8061
Epoch No.: 42   TRAIN Loss = 0.2979      TRAIN mIOU = 0.8097
Epoch No.: 43   TRAIN Loss = 0.2945      TRAIN mIOU = 0.8095
Epoch No.: 44   TRAIN Loss = 0.2974      TRAIN mIOU = 0.8100
Epoch No.: 45   TRAIN Loss = 0.2967      TRAIN mIOU = 0.8093
Epoch No.: 46   TRAIN Loss = 0.2974      TRAIN mIOU = 0.8076
Epoch No.: 47   TRAIN Loss = 0.2954      TRAIN mIOU = 0.8126
Epoch No.: 48   TRAIN Loss = 0.2982      TRAIN mIOU = 0.8123
Epoch No.: 49   TRAIN Loss = 0.2986      TRAIN mIOU = 0.8078

VAL

224 * 224

Epoch No.: 0    VAL Loss = 0.9486        VAL mIOU = 0.5981
Epoch No.: 1    VAL Loss = 1.0930        VAL mIOU = 0.6254
Epoch No.: 2    VAL Loss = 0.6092        VAL mIOU = 0.6251
Epoch No.: 3    VAL Loss = 0.8239        VAL mIOU = 0.6337
Epoch No.: 4    VAL Loss = 0.6866        VAL mIOU = 0.6363
Epoch No.: 5    VAL Loss = 0.6907        VAL mIOU = 0.6463
Epoch No.: 6    VAL Loss = 0.3703        VAL mIOU = 0.6474
Epoch No.: 7    VAL Loss = 0.1954        VAL mIOU = 0.6546
Epoch No.: 8    VAL Loss = 0.5008        VAL mIOU = 0.6579
Epoch No.: 9    VAL Loss = 0.9468        VAL mIOU = 0.6589
Epoch No.: 10   VAL Loss = 0.3087        VAL mIOU = 0.6500
Epoch No.: 11   VAL Loss = 0.7298        VAL mIOU = 0.6609
Epoch No.: 12   VAL Loss = 0.3829        VAL mIOU = 0.6683
Epoch No.: 13   VAL Loss = 0.7058        VAL mIOU = 0.6331
Epoch No.: 14   VAL Loss = 0.5151        VAL mIOU = 0.6597
Epoch No.: 15   VAL Loss = 0.7313        VAL mIOU = 0.6593
Epoch No.: 16   VAL Loss = 0.3872        VAL mIOU = 0.6708
Epoch No.: 17   VAL Loss = 1.1026        VAL mIOU = 0.6637
Epoch No.: 18   VAL Loss = 0.3062        VAL mIOU = 0.6568
Epoch No.: 19   VAL Loss = 0.2992        VAL mIOU = 0.6666
Epoch No.: 20   VAL Loss = 0.5475        VAL mIOU = 0.6712
Epoch No.: 21   VAL Loss = 1.5159        VAL mIOU = 0.6695
Epoch No.: 22   VAL Loss = 0.7398        VAL mIOU = 0.6710
Epoch No.: 23   VAL Loss = 0.5196        VAL mIOU = 0.6742
Epoch No.: 24   VAL Loss = 0.2721        VAL mIOU = 0.6775
Epoch No.: 25   VAL Loss = 0.5670        VAL mIOU = 0.6809
Epoch No.: 26   VAL Loss = 0.3878        VAL mIOU = 0.6815
Epoch No.: 27   VAL Loss = 0.3445        VAL mIOU = 0.6746
Epoch No.: 28   VAL Loss = 0.3857        VAL mIOU = 0.6773
Epoch No.: 29   VAL Loss = 0.2027        VAL mIOU = 0.6803
Epoch No.: 30   VAL Loss = 0.2369        VAL mIOU = 0.6787
Epoch No.: 31   VAL Loss = 0.3696        VAL mIOU = 0.6804
Epoch No.: 32   VAL Loss = 1.2621        VAL mIOU = 0.6733
Epoch No.: 33   VAL Loss = 0.3596        VAL mIOU = 0.6756
Epoch No.: 34   VAL Loss = 0.2536        VAL mIOU = 0.6796
Epoch No.: 35   VAL Loss = 0.6286        VAL mIOU = 0.6788
Epoch No.: 36   VAL Loss = 0.3019        VAL mIOU = 0.6833
Epoch No.: 37   VAL Loss = 0.5164        VAL mIOU = 0.6773
Epoch No.: 38   VAL Loss = 0.8890        VAL mIOU = 0.6810
Epoch No.: 39   VAL Loss = 0.4940        VAL mIOU = 0.6731
Epoch No.: 40   VAL Loss = 0.2817        VAL mIOU = 0.6795
Epoch No.: 41   VAL Loss = 0.5478        VAL mIOU = 0.6739
Epoch No.: 42   VAL Loss = 0.3053        VAL mIOU = 0.6780
Epoch No.: 43   VAL Loss = 0.3638        VAL mIOU = 0.6782
Epoch No.: 44   VAL Loss = 0.8372        VAL mIOU = 0.6816
Epoch No.: 45   VAL Loss = 0.3126        VAL mIOU = 0.6803
Epoch No.: 46   VAL Loss = 0.7972        VAL mIOU = 0.6771
Epoch No.: 47   VAL Loss = 0.3211        VAL mIOU = 0.6827
Epoch No.: 48   VAL Loss = 0.2223        VAL mIOU = 0.6810
Epoch No.: 49   VAL Loss = 0.8816        VAL mIOU = 0.6790

384 * 384

Epoch No.: 0    VAL Loss = 0.4397        VAL mIOU = 0.6157
Epoch No.: 1    VAL Loss = 1.0275        VAL mIOU = 0.6647
Epoch No.: 2    VAL Loss = 1.0030        VAL mIOU = 0.6670
Epoch No.: 3    VAL Loss = 0.9768        VAL mIOU = 0.6272
Epoch No.: 4    VAL Loss = 0.9051        VAL mIOU = 0.6783
Epoch No.: 5    VAL Loss = 0.4021        VAL mIOU = 0.6695
Epoch No.: 6    VAL Loss = 0.1785        VAL mIOU = 0.6677
Epoch No.: 7    VAL Loss = 0.2535        VAL mIOU = 0.6786
Epoch No.: 8    VAL Loss = 0.2187        VAL mIOU = 0.6725
Epoch No.: 9    VAL Loss = 0.3153        VAL mIOU = 0.6861
Epoch No.: 10   VAL Loss = 0.3899        VAL mIOU = 0.6830
Epoch No.: 11   VAL Loss = 0.8716        VAL mIOU = 0.6870
Epoch No.: 12   VAL Loss = 0.3529        VAL mIOU = 0.6922
Epoch No.: 13   VAL Loss = 0.5868        VAL mIOU = 0.6852
Epoch No.: 14   VAL Loss = 0.6046        VAL mIOU = 0.6880
Epoch No.: 15   VAL Loss = 0.2905        VAL mIOU = 0.6948
Epoch No.: 16   VAL Loss = 0.1958        VAL mIOU = 0.6816
Epoch No.: 17   VAL Loss = 0.4475        VAL mIOU = 0.6891
Epoch No.: 18   VAL Loss = 0.1578        VAL mIOU = 0.6989
Epoch No.: 19   VAL Loss = 0.2862        VAL mIOU = 0.7041
Epoch No.: 20   VAL Loss = 0.4287        VAL mIOU = 0.7104
Epoch No.: 21   VAL Loss = 0.4995        VAL mIOU = 0.7036
Epoch No.: 22   VAL Loss = 0.4040        VAL mIOU = 0.7047
Epoch No.: 23   VAL Loss = 0.2101        VAL mIOU = 0.7023
Epoch No.: 24   VAL Loss = 0.4608        VAL mIOU = 0.7026
Epoch No.: 25   VAL Loss = 0.3806        VAL mIOU = 0.7033
Epoch No.: 26   VAL Loss = 0.3756        VAL mIOU = 0.7023
Epoch No.: 27   VAL Loss = 0.5805        VAL mIOU = 0.7032
Epoch No.: 28   VAL Loss = 0.3759        VAL mIOU = 0.7094
Epoch No.: 29   VAL Loss = 0.4081        VAL mIOU = 0.6970
Epoch No.: 30   VAL Loss = 0.1993        VAL mIOU = 0.7078
Epoch No.: 31   VAL Loss = 0.3640        VAL mIOU = 0.7071
Epoch No.: 32   VAL Loss = 0.3213        VAL mIOU = 0.7089
Epoch No.: 33   VAL Loss = 0.4832        VAL mIOU = 0.7085
Epoch No.: 34   VAL Loss = 0.2025        VAL mIOU = 0.7097
Epoch No.: 35   VAL Loss = 0.1654        VAL mIOU = 0.7108
Epoch No.: 36   VAL Loss = 0.4561        VAL mIOU = 0.7117
Epoch No.: 37   VAL Loss = 0.4685        VAL mIOU = 0.7139
Epoch No.: 38   VAL Loss = 0.6386        VAL mIOU = 0.7068
Epoch No.: 39   VAL Loss = 0.2288        VAL mIOU = 0.7123
Epoch No.: 40   VAL Loss = 0.1666        VAL mIOU = 0.7111
Epoch No.: 41   VAL Loss = 0.3827        VAL mIOU = 0.7101
Epoch No.: 42   VAL Loss = 0.3823        VAL mIOU = 0.7052
Epoch No.: 43   VAL Loss = 0.2659        VAL mIOU = 0.7132
Epoch No.: 44   VAL Loss = 0.4662        VAL mIOU = 0.7042
Epoch No.: 45   VAL Loss = 0.2377        VAL mIOU = 0.7075
Epoch No.: 46   VAL Loss = 0.4985        VAL mIOU = 0.7081
Epoch No.: 47   VAL Loss = 0.2234        VAL mIOU = 0.7029
Epoch No.: 48   VAL Loss = 0.1307        VAL mIOU = 0.7111
Epoch No.: 49   VAL Loss = 0.2732        VAL mIOU = 0.7076
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant