Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg19_rand_seed_979323_test_samples_None_train_samples_None_weight_decay_0.005.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09116754680871964
Inter Cos: 0.10967149585485458
Norm Quadratic Average: 23.567672729492188
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06131010130047798
Inter Cos: 0.07721762359142303
Norm Quadratic Average: 2.8888158798217773
Nearest Class Center Accuracy: 0.81275

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10510315746068954
Inter Cos: 0.09751921147108078
Norm Quadratic Average: 1.7371867895126343
Nearest Class Center Accuracy: 0.8767833333333334

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10823135077953339
Inter Cos: 0.1005600243806839
Norm Quadratic Average: 1.3908876180648804
Nearest Class Center Accuracy: 0.8897

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18376752734184265
Inter Cos: 0.12631218135356903
Norm Quadratic Average: 0.9539685845375061
Nearest Class Center Accuracy: 0.9394833333333333

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23973821103572845
Inter Cos: 0.14555276930332184
Norm Quadratic Average: 0.7185708284378052
Nearest Class Center Accuracy: 0.9618833333333333

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3005930781364441
Inter Cos: 0.14519402384757996
Norm Quadratic Average: 0.6065925359725952
Nearest Class Center Accuracy: 0.97355

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.33243465423583984
Inter Cos: 0.13736110925674438
Norm Quadratic Average: 0.515495240688324
Nearest Class Center Accuracy: 0.9778666666666667

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3822880685329437
Inter Cos: 0.14841009676456451
Norm Quadratic Average: 0.34529316425323486
Nearest Class Center Accuracy: 0.9929333333333333

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6051536798477173
Inter Cos: 0.22575756907463074
Norm Quadratic Average: 0.21454358100891113
Nearest Class Center Accuracy: 0.9978833333333333

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.811673641204834
Inter Cos: 0.2603491246700287
Norm Quadratic Average: 0.18349972367286682
Nearest Class Center Accuracy: 0.9994

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8360216617584229
Inter Cos: 0.2018403857946396
Norm Quadratic Average: 0.19774816930294037
Nearest Class Center Accuracy: 0.9999333333333333

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8789102435112
Inter Cos: 0.16006365418434143
Norm Quadratic Average: 0.25468888878822327
Nearest Class Center Accuracy: 0.9999666666666667

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9773944020271301
Inter Cos: 0.040874794125556946
Norm Quadratic Average: 0.2863636016845703
Nearest Class Center Accuracy: 0.9999833333333333

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9941818118095398
Inter Cos: -0.016319960355758667
Norm Quadratic Average: 0.5372648239135742
Nearest Class Center Accuracy: 0.9999833333333333

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9979243278503418
Inter Cos: -0.003689957084134221
Norm Quadratic Average: 1.1135592460632324
Nearest Class Center Accuracy: 0.9999833333333333

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.1482841968536377
Linear Weight Rank: 10
Intra Cos: 0.9991520047187805
Inter Cos: 0.06110524386167526
Norm Quadratic Average: 25.317541122436523
Nearest Class Center Accuracy: 0.9999833333333333

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.150773286819458
Linear Weight Rank: 1367
Intra Cos: 0.9992685914039612
Inter Cos: 0.1378994584083557
Norm Quadratic Average: 17.20020866394043
Nearest Class Center Accuracy: 0.9999833333333333

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.150831699371338
Linear Weight Rank: 9
Intra Cos: 0.9993239045143127
Inter Cos: 0.1293203979730606
Norm Quadratic Average: 11.919897079467773
Nearest Class Center Accuracy: 0.9999833333333333

Output Layer:
Intra Cos: 0.9994093179702759
Inter Cos: 0.11193934828042984
Norm Quadratic Average: 8.751309394836426
Nearest Class Center Accuracy: 0.9999833333333333

Test Set:
Average Loss: 0.01916337500400841
Accuracy: 0.9951
NC1 Within Class Collapse: 0.07831154018640518
NC2 Equinorm: Features: 0.019509926438331604, Weights: 0.005764804780483246
NC2 Equiangle: Features: 0.09076454374525282, Weights: 0.048516162236531574
NC3 Self-Duality: 0.017755553126335144
NC4 NCC Mismatch: 0.00019999999999997797

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219583660364151
Inter Cos: 0.12048852443695068
Norm Quadratic Average: 23.595197677612305
Nearest Class Center Accuracy: 0.8229

Layer 1: Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06960531324148178
Inter Cos: 0.07950254529714584
Norm Quadratic Average: 2.879215717315674
Nearest Class Center Accuracy: 0.8234

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11549194902181625
Inter Cos: 0.09855300933122635
Norm Quadratic Average: 1.725399136543274
Nearest Class Center Accuracy: 0.8878

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11910005658864975
Inter Cos: 0.1019810289144516
Norm Quadratic Average: 1.3862909078598022
Nearest Class Center Accuracy: 0.8994

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19620680809020996
Inter Cos: 0.12753449380397797
Norm Quadratic Average: 0.950198233127594
Nearest Class Center Accuracy: 0.9438

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25553181767463684
Inter Cos: 0.1427573263645172
Norm Quadratic Average: 0.7170592546463013
Nearest Class Center Accuracy: 0.9632

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.31485193967819214
Inter Cos: 0.14364340901374817
Norm Quadratic Average: 0.6057758927345276
Nearest Class Center Accuracy: 0.9736

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.34666967391967773
Inter Cos: 0.15001808106899261
Norm Quadratic Average: 0.5142253637313843
Nearest Class Center Accuracy: 0.9772

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.39465898275375366
Inter Cos: 0.1634644716978073
Norm Quadratic Average: 0.3443315625190735
Nearest Class Center Accuracy: 0.989

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6158000230789185
Inter Cos: 0.24193540215492249
Norm Quadratic Average: 0.21439997851848602
Nearest Class Center Accuracy: 0.9928

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8143805861473083
Inter Cos: 0.2763682007789612
Norm Quadratic Average: 0.18382349610328674
Nearest Class Center Accuracy: 0.9945

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8409832119941711
Inter Cos: 0.21635960042476654
Norm Quadratic Average: 0.19768735766410828
Nearest Class Center Accuracy: 0.9955

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8779062032699585
Inter Cos: 0.1537897288799286
Norm Quadratic Average: 0.25418996810913086
Nearest Class Center Accuracy: 0.9953

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9655593037605286
Inter Cos: 0.05451616644859314
Norm Quadratic Average: 0.2856118381023407
Nearest Class Center Accuracy: 0.9953

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9783614277839661
Inter Cos: -0.012686577625572681
Norm Quadratic Average: 0.5355960130691528
Nearest Class Center Accuracy: 0.9953

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.979923665523529
Inter Cos: 0.0024416944943368435
Norm Quadratic Average: 1.109696865081787
Nearest Class Center Accuracy: 0.9953

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.1482841968536377
Linear Weight Rank: 10
Intra Cos: 0.9815147519111633
Inter Cos: 0.06581660360097885
Norm Quadratic Average: 25.235761642456055
Nearest Class Center Accuracy: 0.9953

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.150773286819458
Linear Weight Rank: 1367
Intra Cos: 0.9823283553123474
Inter Cos: 0.14096564054489136
Norm Quadratic Average: 17.144392013549805
Nearest Class Center Accuracy: 0.9954

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.150831699371338
Linear Weight Rank: 9
Intra Cos: 0.982433557510376
Inter Cos: 0.13246697187423706
Norm Quadratic Average: 11.881108283996582
Nearest Class Center Accuracy: 0.9953

Output Layer:
Intra Cos: 0.9829855561256409
Inter Cos: 0.11548081040382385
Norm Quadratic Average: 8.721810340881348
Nearest Class Center Accuracy: 0.9954

