Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_314159_test_samples_None_train_samples_None_weight_decay_0.003.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09116754680871964
Inter Cos: 0.10967153310775757
Norm Quadratic Average: 23.567678451538086
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12223326414823532
Inter Cos: 0.14934168756008148
Norm Quadratic Average: 41.630680084228516
Nearest Class Center Accuracy: 0.8081333333333334

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17780175805091858
Inter Cos: 0.17654311656951904
Norm Quadratic Average: 44.181541442871094
Nearest Class Center Accuracy: 0.8249833333333333

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21055902540683746
Inter Cos: 0.19954697787761688
Norm Quadratic Average: 45.30291748046875
Nearest Class Center Accuracy: 0.8684166666666666

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20975902676582336
Inter Cos: 0.20029856264591217
Norm Quadratic Average: 22.804367065429688
Nearest Class Center Accuracy: 0.9152666666666667

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3085270822048187
Inter Cos: 0.2686173617839813
Norm Quadratic Average: 13.289178848266602
Nearest Class Center Accuracy: 0.9485

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.48828378319740295
Inter Cos: 0.31758612394332886
Norm Quadratic Average: 6.602684497833252
Nearest Class Center Accuracy: 0.9779666666666667

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7490208148956299
Inter Cos: 0.39437779784202576
Norm Quadratic Average: 5.978666305541992
Nearest Class Center Accuracy: 0.9912

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.116037607192993
Linear Weight Rank: 336
Intra Cos: 0.8277859687805176
Inter Cos: 0.33288976550102234
Norm Quadratic Average: 30.492799758911133
Nearest Class Center Accuracy: 0.9952333333333333

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.12812876701355
Linear Weight Rank: 2700
Intra Cos: 0.88930344581604
Inter Cos: 0.35084986686706543
Norm Quadratic Average: 25.817262649536133
Nearest Class Center Accuracy: 0.99785

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.1150925159454346
Linear Weight Rank: 9
Intra Cos: 0.906321108341217
Inter Cos: 0.34386348724365234
Norm Quadratic Average: 21.054636001586914
Nearest Class Center Accuracy: 0.9984

Output Layer:
Intra Cos: 0.934111475944519
Inter Cos: 0.4026482403278351
Norm Quadratic Average: 19.492633819580078
Nearest Class Center Accuracy: 0.9986333333333334

Test Set:
Average Loss: 0.024337753918813543
Accuracy: 0.9913
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.11087054759263992, Weights: 0.051295485347509384
NC2 Equiangle: Features: 0.26460338168674047, Weights: 0.23811806572808158
NC3 Self-Duality: 0.05935221165418625
NC4 NCC Mismatch: 0.0029000000000000137

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219582915306091
Inter Cos: 0.12048852443695068
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: 0.1358971744775772
Inter Cos: 0.16363252699375153
Norm Quadratic Average: 41.667633056640625
Nearest Class Center Accuracy: 0.8234

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19411581754684448
Inter Cos: 0.1913565695285797
Norm Quadratic Average: 44.096946716308594
Nearest Class Center Accuracy: 0.8411

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2256070077419281
Inter Cos: 0.21706929802894592
Norm Quadratic Average: 45.25856399536133
Nearest Class Center Accuracy: 0.8824

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2216430902481079
Inter Cos: 0.20484480261802673
Norm Quadratic Average: 22.7698974609375
Nearest Class Center Accuracy: 0.9278

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3184009790420532
Inter Cos: 0.27663055062294006
Norm Quadratic Average: 13.299126625061035
Nearest Class Center Accuracy: 0.9558

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5000296831130981
Inter Cos: 0.3412999212741852
Norm Quadratic Average: 6.636109352111816
Nearest Class Center Accuracy: 0.9764

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7606425285339355
Inter Cos: 0.3931546211242676
Norm Quadratic Average: 6.027079105377197
Nearest Class Center Accuracy: 0.9852

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.116037607192993
Linear Weight Rank: 336
Intra Cos: 0.827519416809082
Inter Cos: 0.35336804389953613
Norm Quadratic Average: 30.778196334838867
Nearest Class Center Accuracy: 0.9876

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.12812876701355
Linear Weight Rank: 2700
Intra Cos: 0.8857552409172058
Inter Cos: 0.37032243609428406
Norm Quadratic Average: 26.07357406616211
Nearest Class Center Accuracy: 0.99

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.1150925159454346
Linear Weight Rank: 9
Intra Cos: 0.901786744594574
Inter Cos: 0.3621951937675476
Norm Quadratic Average: 21.2675838470459
Nearest Class Center Accuracy: 0.9904

Output Layer:
Intra Cos: 0.9264582395553589
Inter Cos: 0.42029646039009094
Norm Quadratic Average: 19.696189880371094
Nearest Class Center Accuracy: 0.9904

