Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_979323_test_samples_None_train_samples_None_weight_decay_0.0005.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: 0.10967151820659637
Norm Quadratic Average: 23.567676544189453
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09471628814935684
Inter Cos: 0.10618168115615845
Norm Quadratic Average: 11.64904499053955
Nearest Class Center Accuracy: 0.85075

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16229906678199768
Inter Cos: 0.12372782081365585
Norm Quadratic Average: 7.988507270812988
Nearest Class Center Accuracy: 0.9078

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1939418613910675
Inter Cos: 0.1250874549150467
Norm Quadratic Average: 8.411521911621094
Nearest Class Center Accuracy: 0.9396166666666667

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.26028212904930115
Inter Cos: 0.09994164109230042
Norm Quadratic Average: 5.664931774139404
Nearest Class Center Accuracy: 0.98355

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.39675530791282654
Inter Cos: 0.1564786285161972
Norm Quadratic Average: 6.519196033477783
Nearest Class Center Accuracy: 0.9966833333333334

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5556603074073792
Inter Cos: 0.17368440330028534
Norm Quadratic Average: 5.0016865730285645
Nearest Class Center Accuracy: 0.9999

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8683186173439026
Inter Cos: 0.09570924937725067
Norm Quadratic Average: 3.921600818634033
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 14.685900688171387
Linear Weight Rank: 4031
Intra Cos: 0.9871919751167297
Inter Cos: -0.041110459715127945
Norm Quadratic Average: 42.18451690673828
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 6.2493977546691895
Linear Weight Rank: 3667
Intra Cos: 0.995611310005188
Inter Cos: -0.006369571201503277
Norm Quadratic Average: 26.999099731445312
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.048196315765381
Linear Weight Rank: 10
Intra Cos: 0.9960835576057434
Inter Cos: 0.009972159750759602
Norm Quadratic Average: 17.5206298828125
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.997646689414978
Inter Cos: 0.05475008487701416
Norm Quadratic Average: 12.032073020935059
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.016873667685338295
Accuracy: 0.9951
NC1 Within Class Collapse: 0.133106529712677
NC2 Equinorm: Features: 0.02950299344956875, Weights: 0.015025574713945389
NC2 Equiangle: Features: 0.08294897079467774, Weights: 0.038566427760654026
NC3 Self-Duality: 0.03687623515725136
NC4 NCC Mismatch: 0.00029999999999996696

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219582170248032
Inter Cos: 0.12048851698637009
Norm Quadratic Average: 23.595197677612305
Nearest Class Center Accuracy: 0.8229

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10359601676464081
Inter Cos: 0.10691199451684952
Norm Quadratic Average: 11.574902534484863
Nearest Class Center Accuracy: 0.8624

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17293742299079895
Inter Cos: 0.12206921726465225
Norm Quadratic Average: 7.938581466674805
Nearest Class Center Accuracy: 0.9173

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20794488489627838
Inter Cos: 0.12293544411659241
Norm Quadratic Average: 8.366634368896484
Nearest Class Center Accuracy: 0.9452

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2725963592529297
Inter Cos: 0.11002160608768463
Norm Quadratic Average: 5.641921520233154
Nearest Class Center Accuracy: 0.9825

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.40788137912750244
Inter Cos: 0.17124496400356293
Norm Quadratic Average: 6.505718231201172
Nearest Class Center Accuracy: 0.9908

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5576122403144836
Inter Cos: 0.18275634944438934
Norm Quadratic Average: 4.995761394500732
Nearest Class Center Accuracy: 0.9938

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8592336773872375
Inter Cos: 0.10564655065536499
Norm Quadratic Average: 3.9023585319519043
Nearest Class Center Accuracy: 0.9946

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 14.685900688171387
Linear Weight Rank: 4031
Intra Cos: 0.9698614478111267
Inter Cos: -0.029130104929208755
Norm Quadratic Average: 41.87907409667969
Nearest Class Center Accuracy: 0.9952

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 6.2493977546691895
Linear Weight Rank: 3667
Intra Cos: 0.9778205156326294
Inter Cos: 0.000365331768989563
Norm Quadratic Average: 26.793853759765625
Nearest Class Center Accuracy: 0.9951

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.048196315765381
Linear Weight Rank: 10
Intra Cos: 0.9786421656608582
Inter Cos: 0.015283983200788498
Norm Quadratic Average: 17.389734268188477
Nearest Class Center Accuracy: 0.9952

Output Layer:
Intra Cos: 0.981288731098175
Inter Cos: 0.05278954654932022
Norm Quadratic Average: 11.939900398254395
Nearest Class Center Accuracy: 0.9954

