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_0.007.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: 0.06116371601819992
Inter Cos: 0.07897435873746872
Norm Quadratic Average: 2.5610125064849854
Nearest Class Center Accuracy: 0.8072333333333334

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10178308188915253
Inter Cos: 0.09506256878376007
Norm Quadratic Average: 1.5034884214401245
Nearest Class Center Accuracy: 0.8736333333333334

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1006295457482338
Inter Cos: 0.09540323913097382
Norm Quadratic Average: 1.2076389789581299
Nearest Class Center Accuracy: 0.8833

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17539818584918976
Inter Cos: 0.11771684885025024
Norm Quadratic Average: 0.7978781461715698
Nearest Class Center Accuracy: 0.93795

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23057051002979279
Inter Cos: 0.12991590797901154
Norm Quadratic Average: 0.6068652868270874
Nearest Class Center Accuracy: 0.9630833333333333

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3034222424030304
Inter Cos: 0.1387467384338379
Norm Quadratic Average: 0.5157021880149841
Nearest Class Center Accuracy: 0.9732

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3450184464454651
Inter Cos: 0.13349537551403046
Norm Quadratic Average: 0.4540095031261444
Nearest Class Center Accuracy: 0.9790833333333333

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4162890315055847
Inter Cos: 0.14995011687278748
Norm Quadratic Average: 0.2810335159301758
Nearest Class Center Accuracy: 0.99345

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6482048034667969
Inter Cos: 0.20952655375003815
Norm Quadratic Average: 0.18371795117855072
Nearest Class Center Accuracy: 0.9976833333333334

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8211827278137207
Inter Cos: 0.29122334718704224
Norm Quadratic Average: 0.16645380854606628
Nearest Class Center Accuracy: 0.9998

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.851577639579773
Inter Cos: 0.12767358124256134
Norm Quadratic Average: 0.1832103133201599
Nearest Class Center Accuracy: 0.9999166666666667

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9082863330841064
Inter Cos: 0.08835327625274658
Norm Quadratic Average: 0.17202869057655334
Nearest Class Center Accuracy: 0.9999666666666667

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9870970249176025
Inter Cos: 0.09203427284955978
Norm Quadratic Average: 0.215540811419487
Nearest Class Center Accuracy: 0.9999666666666667

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9965525269508362
Inter Cos: 0.10141546279191971
Norm Quadratic Average: 0.46525701880455017
Nearest Class Center Accuracy: 0.9999666666666667

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9981480240821838
Inter Cos: 0.1860332489013672
Norm Quadratic Average: 1.0727968215942383
Nearest Class Center Accuracy: 0.9999666666666667

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.0926308631896973
Linear Weight Rank: 9
Intra Cos: 0.9990482330322266
Inter Cos: 0.22630275785923004
Norm Quadratic Average: 24.6379451751709
Nearest Class Center Accuracy: 0.9999666666666667

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.0943055152893066
Linear Weight Rank: 1454
Intra Cos: 0.9992939829826355
Inter Cos: 0.21888546645641327
Norm Quadratic Average: 16.98412322998047
Nearest Class Center Accuracy: 0.9999666666666667

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.0952341556549072
Linear Weight Rank: 9
Intra Cos: 0.9994333386421204
Inter Cos: 0.19310590624809265
Norm Quadratic Average: 11.982844352722168
Nearest Class Center Accuracy: 0.9999666666666667

Output Layer:
Intra Cos: 0.9995370507240295
Inter Cos: 0.12209215760231018
Norm Quadratic Average: 8.906740188598633
Nearest Class Center Accuracy: 0.9999666666666667

Test Set:
Average Loss: 0.021059527142718436
Accuracy: 0.9951
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.03702216595411301, Weights: 0.007698626257479191
NC2 Equiangle: Features: 0.11266820695665147, Weights: 0.09242588678995768
NC3 Self-Duality: 0.034823812544345856
NC4 NCC Mismatch: 0.00019999999999997797

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: 0.0695270374417305
Inter Cos: 0.08160421252250671
Norm Quadratic Average: 2.553297996520996
Nearest Class Center Accuracy: 0.8205

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1114250123500824
Inter Cos: 0.09637385606765747
Norm Quadratic Average: 1.4941418170928955
Nearest Class Center Accuracy: 0.8858

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11030564457178116
Inter Cos: 0.09738068282604218
Norm Quadratic Average: 1.2051852941513062
Nearest Class Center Accuracy: 0.8911

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18787987530231476
Inter Cos: 0.12466634064912796
Norm Quadratic Average: 0.7951988577842712
Nearest Class Center Accuracy: 0.9436

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24605408310890198
Inter Cos: 0.1415686309337616
Norm Quadratic Average: 0.6056004762649536
Nearest Class Center Accuracy: 0.9654

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.31922608613967896
Inter Cos: 0.1515531688928604
Norm Quadratic Average: 0.5149833559989929
Nearest Class Center Accuracy: 0.9748

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3618362247943878
Inter Cos: 0.14672976732254028
Norm Quadratic Average: 0.4529756009578705
Nearest Class Center Accuracy: 0.9782

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.43020007014274597
Inter Cos: 0.16462182998657227
Norm Quadratic Average: 0.28037986159324646
Nearest Class Center Accuracy: 0.9898

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.659205436706543
Inter Cos: 0.22410187125205994
Norm Quadratic Average: 0.1838783174753189
Nearest Class Center Accuracy: 0.9924

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8214223384857178
Inter Cos: 0.30305641889572144
Norm Quadratic Average: 0.1668851375579834
Nearest Class Center Accuracy: 0.9942

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8528337478637695
Inter Cos: 0.13935516774654388
Norm Quadratic Average: 0.18318001925945282
Nearest Class Center Accuracy: 0.9946

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9053447842597961
Inter Cos: 0.09935056418180466
Norm Quadratic Average: 0.1717827171087265
Nearest Class Center Accuracy: 0.9952

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9748216271400452
Inter Cos: 0.09622756391763687
Norm Quadratic Average: 0.21490731835365295
Nearest Class Center Accuracy: 0.9952

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9767875075340271
Inter Cos: 0.10560072213411331
Norm Quadratic Average: 0.4635673463344574
Nearest Class Center Accuracy: 0.9952

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9789242148399353
Inter Cos: 0.18910549581050873
Norm Quadratic Average: 1.0692323446273804
Nearest Class Center Accuracy: 0.9953

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.0926308631896973
Linear Weight Rank: 9
Intra Cos: 0.9803738594055176
Inter Cos: 0.22725047171115875
Norm Quadratic Average: 24.55560874938965
Nearest Class Center Accuracy: 0.9953

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.0943055152893066
Linear Weight Rank: 1454
Intra Cos: 0.9807799458503723
Inter Cos: 0.21976879239082336
Norm Quadratic Average: 16.92378807067871
Nearest Class Center Accuracy: 0.9953

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.0952341556549072
Linear Weight Rank: 9
Intra Cos: 0.9808557033538818
Inter Cos: 0.19450423121452332
Norm Quadratic Average: 11.938043594360352
Nearest Class Center Accuracy: 0.9951

Output Layer:
Intra Cos: 0.9809523820877075
Inter Cos: 0.13439872860908508
Norm Quadratic Average: 8.871326446533203
Nearest Class Center Accuracy: 0.9952

