Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_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: 0.11311887204647064
Norm Quadratic Average: 23.532934188842773
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12114143371582031
Inter Cos: 0.15130126476287842
Norm Quadratic Average: 39.08080291748047
Nearest Class Center Accuracy: 0.800875

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14651590585708618
Inter Cos: 0.1827818751335144
Norm Quadratic Average: 47.461387634277344
Nearest Class Center Accuracy: 0.763375

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15418806672096252
Inter Cos: 0.200980082154274
Norm Quadratic Average: 64.88768768310547
Nearest Class Center Accuracy: 0.753625

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17119355499744415
Inter Cos: 0.21729400753974915
Norm Quadratic Average: 42.062644958496094
Nearest Class Center Accuracy: 0.778375

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2052619904279709
Inter Cos: 0.2706305682659149
Norm Quadratic Average: 30.29668426513672
Nearest Class Center Accuracy: 0.826625

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2905912399291992
Inter Cos: 0.30597928166389465
Norm Quadratic Average: 16.42024803161621
Nearest Class Center Accuracy: 0.885

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.40659865736961365
Inter Cos: 0.3602219223976135
Norm Quadratic Average: 10.08253002166748
Nearest Class Center Accuracy: 0.933625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 24.01297950744629
Linear Weight Rank: 4031
Intra Cos: 0.5320481061935425
Inter Cos: 0.3497084081172943
Norm Quadratic Average: 41.63283920288086
Nearest Class Center Accuracy: 0.960625

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.830395698547363
Linear Weight Rank: 3669
Intra Cos: 0.612729549407959
Inter Cos: 0.3265835642814636
Norm Quadratic Average: 27.154582977294922
Nearest Class Center Accuracy: 0.968125

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.7959916591644287
Linear Weight Rank: 10
Intra Cos: 0.6454102396965027
Inter Cos: 0.3222198188304901
Norm Quadratic Average: 18.780521392822266
Nearest Class Center Accuracy: 0.969375

Output Layer:
Intra Cos: 0.6868899464607239
Inter Cos: 0.3855559229850769
Norm Quadratic Average: 13.884865760803223
Nearest Class Center Accuracy: 0.97025

Test Set:
Average Loss: 0.13547655582427978
Accuracy: 0.9585
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.1783226579427719, Weights: 0.03562619537115097
NC2 Equiangle: Features: 0.31333533393012153, Weights: 0.1999841054280599
NC3 Self-Duality: 0.19842857122421265
NC4 NCC Mismatch: 0.030000000000000027

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
Inter Cos: 0.11957792937755585
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: 0.14327828586101532
Inter Cos: 0.17213313281536102
Norm Quadratic Average: 37.698856353759766
Nearest Class Center Accuracy: 0.8

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15891453623771667
Inter Cos: 0.21620315313339233
Norm Quadratic Average: 45.867244720458984
Nearest Class Center Accuracy: 0.768

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17039074003696442
Inter Cos: 0.2407364845275879
Norm Quadratic Average: 62.624141693115234
Nearest Class Center Accuracy: 0.7555

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15403039753437042
Inter Cos: 0.24970442056655884
Norm Quadratic Average: 40.65383529663086
Nearest Class Center Accuracy: 0.777

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18486268818378448
Inter Cos: 0.3002890944480896
Norm Quadratic Average: 29.30426597595215
Nearest Class Center Accuracy: 0.826

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.263309121131897
Inter Cos: 0.2942345440387726
Norm Quadratic Average: 15.788910865783691
Nearest Class Center Accuracy: 0.8745

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.36349421739578247
Inter Cos: 0.3385397493839264
Norm Quadratic Average: 9.657645225524902
Nearest Class Center Accuracy: 0.912

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 24.01297950744629
Linear Weight Rank: 4031
Intra Cos: 0.46786221861839294
Inter Cos: 0.3373308479785919
Norm Quadratic Average: 39.89919662475586
Nearest Class Center Accuracy: 0.937

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.830395698547363
Linear Weight Rank: 3669
Intra Cos: 0.530161440372467
Inter Cos: 0.3565705120563507
Norm Quadratic Average: 26.04481315612793
Nearest Class Center Accuracy: 0.9465

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.7959916591644287
Linear Weight Rank: 10
Intra Cos: 0.5515881180763245
Inter Cos: 0.35338279604911804
Norm Quadratic Average: 18.032405853271484
Nearest Class Center Accuracy: 0.9455

Output Layer:
Intra Cos: 0.5776762366294861
Inter Cos: 0.4076557159423828
Norm Quadratic Average: 13.312859535217285
Nearest Class Center Accuracy: 0.942

