Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_weight_decay_0.03.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946067094802856
Inter Cos: 0.11311887949705124
Norm Quadratic Average: 23.53293800354004
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10549041628837585
Inter Cos: 0.12683576345443726
Norm Quadratic Average: 20.599346160888672
Nearest Class Center Accuracy: 0.834875

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15514680743217468
Inter Cos: 0.14623932540416718
Norm Quadratic Average: 13.6271390914917
Nearest Class Center Accuracy: 0.859875

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15935859084129333
Inter Cos: 0.14657074213027954
Norm Quadratic Average: 13.307762145996094
Nearest Class Center Accuracy: 0.88

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20553699135780334
Inter Cos: 0.13353726267814636
Norm Quadratic Average: 8.299428939819336
Nearest Class Center Accuracy: 0.939375

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24626339972019196
Inter Cos: 0.13276170194149017
Norm Quadratic Average: 8.224101066589355
Nearest Class Center Accuracy: 0.97475

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3725923001766205
Inter Cos: 0.12685588002204895
Norm Quadratic Average: 5.709881782531738
Nearest Class Center Accuracy: 0.99825

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7078037858009338
Inter Cos: 0.13231761753559113
Norm Quadratic Average: 4.71038293838501
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 23.995140075683594
Linear Weight Rank: 4031
Intra Cos: 0.943367600440979
Inter Cos: 0.16004568338394165
Norm Quadratic Average: 52.765323638916016
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.790335655212402
Linear Weight Rank: 3670
Intra Cos: 0.9795013666152954
Inter Cos: 0.1818629503250122
Norm Quadratic Average: 25.483699798583984
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.5688058137893677
Linear Weight Rank: 10
Intra Cos: 0.9838080406188965
Inter Cos: 0.19095684587955475
Norm Quadratic Average: 14.432984352111816
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9883378744125366
Inter Cos: 0.3112381100654602
Norm Quadratic Average: 8.633892059326172
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.07083014607429504
Accuracy: 0.981
NC1 Within Class Collapse: 0.7254703640937805
NC2 Equinorm: Features: 0.0642203837633133, Weights: 0.018666420131921768
NC2 Equiangle: Features: 0.21404743194580078, Weights: 0.12132393519083659
NC3 Self-Duality: 0.09282735735177994
NC4 NCC Mismatch: 0.0030000000000000027

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133807361125946
Inter Cos: 0.11957792192697525
Norm Quadratic Average: 22.82430076599121
Nearest Class Center Accuracy: 0.809

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12640368938446045
Inter Cos: 0.13127246499061584
Norm Quadratic Average: 20.239126205444336
Nearest Class Center Accuracy: 0.8275

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1618715524673462
Inter Cos: 0.16012202203273773
Norm Quadratic Average: 13.480628967285156
Nearest Class Center Accuracy: 0.8495

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16517707705497742
Inter Cos: 0.15948177874088287
Norm Quadratic Average: 13.179086685180664
Nearest Class Center Accuracy: 0.8765

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19687631726264954
Inter Cos: 0.14372685551643372
Norm Quadratic Average: 8.274433135986328
Nearest Class Center Accuracy: 0.9285

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24022258818149567
Inter Cos: 0.13933518528938293
Norm Quadratic Average: 8.202533721923828
Nearest Class Center Accuracy: 0.9605

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3474118113517761
Inter Cos: 0.13586468994617462
Norm Quadratic Average: 5.669783592224121
Nearest Class Center Accuracy: 0.9775

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6162086725234985
Inter Cos: 0.1515902429819107
Norm Quadratic Average: 4.602526664733887
Nearest Class Center Accuracy: 0.9815

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 23.995140075683594
Linear Weight Rank: 4031
Intra Cos: 0.8430326581001282
Inter Cos: 0.17399369180202484
Norm Quadratic Average: 50.55720520019531
Nearest Class Center Accuracy: 0.981

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.790335655212402
Linear Weight Rank: 3670
Intra Cos: 0.8913678526878357
Inter Cos: 0.19289658963680267
Norm Quadratic Average: 24.40248680114746
Nearest Class Center Accuracy: 0.9835

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.5688058137893677
Linear Weight Rank: 10
Intra Cos: 0.8975290060043335
Inter Cos: 0.1870846450328827
Norm Quadratic Average: 13.859495162963867
Nearest Class Center Accuracy: 0.983

Output Layer:
Intra Cos: 0.9102760553359985
Inter Cos: 0.2966378927230835
Norm Quadratic Average: 8.28226375579834
Nearest Class Center Accuracy: 0.984

