Model save path: ./New_Models/bn_True_dataset_CIFAR10_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_weight_decay_0.0001.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.021450400352478027
Inter Cos: 0.11371058970689774
Norm Quadratic Average: 27.691621780395508
Nearest Class Center Accuracy: 0.279125

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.022619707509875298
Inter Cos: 0.10056035965681076
Norm Quadratic Average: 87.20446014404297
Nearest Class Center Accuracy: 0.323875

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02505875565111637
Inter Cos: 0.08163824677467346
Norm Quadratic Average: 65.0418930053711
Nearest Class Center Accuracy: 0.360625

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.023679856210947037
Inter Cos: 0.06348434090614319
Norm Quadratic Average: 68.74226379394531
Nearest Class Center Accuracy: 0.38975

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.031294915825128555
Inter Cos: 0.07145306468009949
Norm Quadratic Average: 43.481903076171875
Nearest Class Center Accuracy: 0.417125

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03251653164625168
Inter Cos: 0.06238005310297012
Norm Quadratic Average: 44.8189582824707
Nearest Class Center Accuracy: 0.452875

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.04483489692211151
Inter Cos: 0.07658492773771286
Norm Quadratic Average: 28.76679039001465
Nearest Class Center Accuracy: 0.538125

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06352130323648453
Inter Cos: 0.07113534957170486
Norm Quadratic Average: 20.505311965942383
Nearest Class Center Accuracy: 0.815625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.89910125732422
Linear Weight Rank: 4031
Intra Cos: 0.1843196451663971
Inter Cos: 0.10061030089855194
Norm Quadratic Average: 108.32923889160156
Nearest Class Center Accuracy: 0.99975

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.78636932373047
Linear Weight Rank: 3670
Intra Cos: 0.4352235496044159
Inter Cos: 0.18160513043403625
Norm Quadratic Average: 56.88836669921875
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.5446393489837646
Linear Weight Rank: 10
Intra Cos: 0.6721374988555908
Inter Cos: 0.2751455307006836
Norm Quadratic Average: 40.131412506103516
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.8815765380859375
Inter Cos: 0.47212648391723633
Norm Quadratic Average: 28.25116729736328
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 2.8311976623535156
Accuracy: 0.5805
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.20114094018936157, Weights: 0.018771283328533173
NC2 Equiangle: Features: 0.4307599385579427, Weights: 0.08887681431240506
NC3 Self-Duality: 0.6278595328330994
NC4 NCC Mismatch: 0.137

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018480459228157997
Inter Cos: 0.09352368116378784
Norm Quadratic Average: 27.530664443969727
Nearest Class Center Accuracy: 0.2895

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.021901564672589302
Inter Cos: 0.08768153190612793
Norm Quadratic Average: 86.92967987060547
Nearest Class Center Accuracy: 0.3475

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.025433674454689026
Inter Cos: 0.07799594849348068
Norm Quadratic Average: 64.81234741210938
Nearest Class Center Accuracy: 0.3795

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.024613158777356148
Inter Cos: 0.06123236566781998
Norm Quadratic Average: 68.64901733398438
Nearest Class Center Accuracy: 0.4225

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.028536411002278328
Inter Cos: 0.06891589611768723
Norm Quadratic Average: 43.39805603027344
Nearest Class Center Accuracy: 0.4445

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02909480221569538
Inter Cos: 0.06041979789733887
Norm Quadratic Average: 44.73176956176758
Nearest Class Center Accuracy: 0.471

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0335092730820179
Inter Cos: 0.07272539287805557
Norm Quadratic Average: 28.648357391357422
Nearest Class Center Accuracy: 0.4855

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.034715332090854645
Inter Cos: 0.06650080531835556
Norm Quadratic Average: 20.324445724487305
Nearest Class Center Accuracy: 0.5485

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.89910125732422
Linear Weight Rank: 4031
Intra Cos: 0.05648331716656685
Inter Cos: 0.10142640769481659
Norm Quadratic Average: 104.5648193359375
Nearest Class Center Accuracy: 0.611

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.78636932373047
Linear Weight Rank: 3670
Intra Cos: 0.11896119266748428
Inter Cos: 0.19935666024684906
Norm Quadratic Average: 52.56864547729492
Nearest Class Center Accuracy: 0.5905

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.5446393489837646
Linear Weight Rank: 10
Intra Cos: 0.18602992594242096
Inter Cos: 0.3111792802810669
Norm Quadratic Average: 35.726707458496094
Nearest Class Center Accuracy: 0.5825

Output Layer:
Intra Cos: 0.27477794885635376
Inter Cos: 0.4845782518386841
Norm Quadratic Average: 24.425344467163086
Nearest Class Center Accuracy: 0.5625

