Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_314159_test_samples_None_train_samples_None_weight_decay_0.02.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: 0.10648319125175476
Inter Cos: 0.11124173551797867
Norm Quadratic Average: 2.077484130859375
Nearest Class Center Accuracy: 0.854

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18103770911693573
Inter Cos: 0.1431232988834381
Norm Quadratic Average: 1.012241244316101
Nearest Class Center Accuracy: 0.9118

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2300555408000946
Inter Cos: 0.17027579247951508
Norm Quadratic Average: 0.6130723357200623
Nearest Class Center Accuracy: 0.9504666666666667

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3288649320602417
Inter Cos: 0.14620958268642426
Norm Quadratic Average: 0.25987038016319275
Nearest Class Center Accuracy: 0.9888333333333333

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6975363492965698
Inter Cos: 0.22578534483909607
Norm Quadratic Average: 0.20235691964626312
Nearest Class Center Accuracy: 0.9993333333333333

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8921177983283997
Inter Cos: 0.29108452796936035
Norm Quadratic Average: 0.29291966557502747
Nearest Class Center Accuracy: 0.9999666666666667

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9872402548789978
Inter Cos: 0.37643954157829285
Norm Quadratic Average: 0.6665178537368774
Nearest Class Center Accuracy: 0.9999666666666667

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.9600961208343506
Linear Weight Rank: 8
Intra Cos: 0.997031569480896
Inter Cos: 0.34400054812431335
Norm Quadratic Average: 23.189624786376953
Nearest Class Center Accuracy: 0.9999666666666667

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.9610463380813599
Linear Weight Rank: 1458
Intra Cos: 0.9978845715522766
Inter Cos: 0.301323801279068
Norm Quadratic Average: 16.0106201171875
Nearest Class Center Accuracy: 0.9999666666666667

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9623278379440308
Linear Weight Rank: 8
Intra Cos: 0.9982881546020508
Inter Cos: 0.25153180956840515
Norm Quadratic Average: 11.215314865112305
Nearest Class Center Accuracy: 0.9999666666666667

Output Layer:
Intra Cos: 0.9981433749198914
Inter Cos: 0.2840404808521271
Norm Quadratic Average: 8.421137809753418
Nearest Class Center Accuracy: 0.9999666666666667

Test Set:
Average Loss: 0.02296781269013882
Accuracy: 0.996
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.033642951399087906, Weights: 0.009511826559901237
NC2 Equiangle: Features: 0.16661468082004124, Weights: 0.15731271107991537
NC3 Self-Duality: 0.03999767825007439
NC4 NCC Mismatch: 0.0004999999999999449

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: 0.11701487004756927
Inter Cos: 0.11154244095087051
Norm Quadratic Average: 2.069640636444092
Nearest Class Center Accuracy: 0.8672

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1930234432220459
Inter Cos: 0.14073161780834198
Norm Quadratic Average: 1.0080854892730713
Nearest Class Center Accuracy: 0.9197

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24467156827449799
Inter Cos: 0.1667485386133194
Norm Quadratic Average: 0.6120139360427856
Nearest Class Center Accuracy: 0.9528

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.34086644649505615
Inter Cos: 0.14874929189682007
Norm Quadratic Average: 0.2593093514442444
Nearest Class Center Accuracy: 0.9868

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6990600228309631
Inter Cos: 0.24294032156467438
Norm Quadratic Average: 0.20249496400356293
Nearest Class Center Accuracy: 0.9942

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8856654167175293
Inter Cos: 0.3020991086959839
Norm Quadratic Average: 0.29285284876823425
Nearest Class Center Accuracy: 0.9958

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9726129770278931
Inter Cos: 0.37289226055145264
Norm Quadratic Average: 0.6640695929527283
Nearest Class Center Accuracy: 0.996

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.9600961208343506
Linear Weight Rank: 8
Intra Cos: 0.9788824915885925
Inter Cos: 0.3412916660308838
Norm Quadratic Average: 23.094146728515625
Nearest Class Center Accuracy: 0.996

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.9610463380813599
Linear Weight Rank: 1458
Intra Cos: 0.9806369543075562
Inter Cos: 0.29935309290885925
Norm Quadratic Average: 15.943358421325684
Nearest Class Center Accuracy: 0.9959

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9623278379440308
Linear Weight Rank: 8
Intra Cos: 0.9816768765449524
Inter Cos: 0.2503514587879181
Norm Quadratic Average: 11.167123794555664
Nearest Class Center Accuracy: 0.9959

Output Layer:
Intra Cos: 0.9838237762451172
Inter Cos: 0.28372514247894287
Norm Quadratic Average: 8.385161399841309
Nearest Class Center Accuracy: 0.9959

