Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg19_rand_seed_314159_test_samples_None_train_samples_None_weight_decay_0.001.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09116753935813904
Inter Cos: 0.10967151075601578
Norm Quadratic Average: 23.567678451538086
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06005748733878136
Inter Cos: 0.07744811475276947
Norm Quadratic Average: 6.5353593826293945
Nearest Class Center Accuracy: 0.8180333333333333

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.093763068318367
Inter Cos: 0.09196943789720535
Norm Quadratic Average: 4.37184476852417
Nearest Class Center Accuracy: 0.8745166666666667

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09596022218465805
Inter Cos: 0.09086154401302338
Norm Quadratic Average: 4.1935224533081055
Nearest Class Center Accuracy: 0.8848166666666667

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1605757474899292
Inter Cos: 0.10893869400024414
Norm Quadratic Average: 3.1751868724823
Nearest Class Center Accuracy: 0.9378833333333333

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19681140780448914
Inter Cos: 0.1234695315361023
Norm Quadratic Average: 2.260335922241211
Nearest Class Center Accuracy: 0.9602

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23413044214248657
Inter Cos: 0.1126723438501358
Norm Quadratic Average: 2.0856192111968994
Nearest Class Center Accuracy: 0.97455

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2736138105392456
Inter Cos: 0.10613351315259933
Norm Quadratic Average: 2.0176632404327393
Nearest Class Center Accuracy: 0.98045

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.358288049697876
Inter Cos: 0.11828413605690002
Norm Quadratic Average: 1.6375938653945923
Nearest Class Center Accuracy: 0.9945833333333334

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5598574876785278
Inter Cos: 0.1632901132106781
Norm Quadratic Average: 1.1515575647354126
Nearest Class Center Accuracy: 0.9987833333333334

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7262369990348816
Inter Cos: 0.12854468822479248
Norm Quadratic Average: 1.0344085693359375
Nearest Class Center Accuracy: 0.9997

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8269509077072144
Inter Cos: 0.05841577798128128
Norm Quadratic Average: 0.8448413014411926
Nearest Class Center Accuracy: 0.9999666666666667

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9062581658363342
Inter Cos: 0.05739935487508774
Norm Quadratic Average: 0.692261278629303
Nearest Class Center Accuracy: 0.9999833333333333

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9797552227973938
Inter Cos: -0.023636674508452415
Norm Quadratic Average: 0.5781360864639282
Nearest Class Center Accuracy: 1.0

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.995274007320404
Inter Cos: -0.041350364685058594
Norm Quadratic Average: 0.6423110365867615
Nearest Class Center Accuracy: 1.0

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9989449977874756
Inter Cos: -0.05841977521777153
Norm Quadratic Average: 1.0590636730194092
Nearest Class Center Accuracy: 1.0

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 3.089102029800415
Linear Weight Rank: 4028
Intra Cos: 0.9996545314788818
Inter Cos: -0.04418790712952614
Norm Quadratic Average: 26.431734085083008
Nearest Class Center Accuracy: 1.0

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.474844217300415
Linear Weight Rank: 3637
Intra Cos: 0.9996694326400757
Inter Cos: 0.012113463133573532
Norm Quadratic Average: 18.723892211914062
Nearest Class Center Accuracy: 1.0

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2965197563171387
Linear Weight Rank: 9
Intra Cos: 0.9996464848518372
Inter Cos: 0.03582951799035072
Norm Quadratic Average: 13.635222434997559
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9998531341552734
Inter Cos: 0.0907408744096756
Norm Quadratic Average: 10.67595100402832
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.021072007498145102
Accuracy: 0.9962
NC1 Within Class Collapse: 0.07300063222646713
NC2 Equinorm: Features: 0.025985797867178917, Weights: 0.009245888330042362
NC2 Equiangle: Features: 0.07967308892144097, Weights: 0.05045428276062012
NC3 Self-Duality: 0.014195473864674568
NC4 NCC Mismatch: 9.999999999998899e-05

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219582915306091
Inter Cos: 0.12048851698637009
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: 0.06799910217523575
Inter Cos: 0.07943562418222427
Norm Quadratic Average: 6.504978179931641
Nearest Class Center Accuracy: 0.8321

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10263336449861526
Inter Cos: 0.09397555142641068
Norm Quadratic Average: 4.334968090057373
Nearest Class Center Accuracy: 0.8862

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10491183400154114
Inter Cos: 0.09254978597164154
Norm Quadratic Average: 4.166207313537598
Nearest Class Center Accuracy: 0.8959

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.170576810836792
Inter Cos: 0.11890441179275513
Norm Quadratic Average: 3.1538944244384766
Nearest Class Center Accuracy: 0.9446

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2090161144733429
Inter Cos: 0.13469910621643066
Norm Quadratic Average: 2.2484092712402344
Nearest Class Center Accuracy: 0.9635

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.245936319231987
Inter Cos: 0.12493179738521576
Norm Quadratic Average: 2.0779523849487305
Nearest Class Center Accuracy: 0.9735

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.28311121463775635
Inter Cos: 0.11718965321779251
Norm Quadratic Average: 2.0131616592407227
Nearest Class Center Accuracy: 0.9777

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3666135370731354
Inter Cos: 0.12317310273647308
Norm Quadratic Average: 1.6358779668807983
Nearest Class Center Accuracy: 0.9898

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.562580943107605
Inter Cos: 0.16151735186576843
Norm Quadratic Average: 1.151319146156311
Nearest Class Center Accuracy: 0.9932

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7239755392074585
Inter Cos: 0.12544956803321838
Norm Quadratic Average: 1.0343433618545532
Nearest Class Center Accuracy: 0.9949

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8218701481819153
Inter Cos: 0.05464273691177368
Norm Quadratic Average: 0.8441317081451416
Nearest Class Center Accuracy: 0.9958

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8974331617355347
Inter Cos: 0.05550295114517212
Norm Quadratic Average: 0.6913956999778748
Nearest Class Center Accuracy: 0.9959

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9604886770248413
Inter Cos: -0.026644928380846977
Norm Quadratic Average: 0.5770493745803833
Nearest Class Center Accuracy: 0.9962

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9725462794303894
Inter Cos: -0.04058957099914551
Norm Quadratic Average: 0.6407625675201416
Nearest Class Center Accuracy: 0.9961

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9776995182037354
Inter Cos: -0.057126279920339584
Norm Quadratic Average: 1.0562732219696045
Nearest Class Center Accuracy: 0.9962

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 3.089102029800415
Linear Weight Rank: 4028
Intra Cos: 0.9799255728721619
Inter Cos: -0.042749445885419846
Norm Quadratic Average: 26.358253479003906
Nearest Class Center Accuracy: 0.9962

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.474844217300415
Linear Weight Rank: 3637
Intra Cos: 0.980609655380249
Inter Cos: 0.012236388400197029
Norm Quadratic Average: 18.672327041625977
Nearest Class Center Accuracy: 0.9962

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2965197563171387
Linear Weight Rank: 9
Intra Cos: 0.9811183214187622
Inter Cos: 0.03720458969473839
Norm Quadratic Average: 13.598691940307617
Nearest Class Center Accuracy: 0.9963

Output Layer:
Intra Cos: 0.9825069308280945
Inter Cos: 0.09731797128915787
Norm Quadratic Average: 10.64636516571045
Nearest Class Center Accuracy: 0.9963

