Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_weight_decay_0.01.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: 0.11826486885547638
Inter Cos: 0.14062920212745667
Norm Quadratic Average: 42.27267837524414
Nearest Class Center Accuracy: 0.814

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15448015928268433
Inter Cos: 0.178163081407547
Norm Quadratic Average: 46.09392547607422
Nearest Class Center Accuracy: 0.783875

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16516025364398956
Inter Cos: 0.19494207203388214
Norm Quadratic Average: 59.230552673339844
Nearest Class Center Accuracy: 0.78125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18183274567127228
Inter Cos: 0.20103605091571808
Norm Quadratic Average: 35.44425964355469
Nearest Class Center Accuracy: 0.823375

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2045939564704895
Inter Cos: 0.2432798147201538
Norm Quadratic Average: 27.455923080444336
Nearest Class Center Accuracy: 0.8715

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.29022446274757385
Inter Cos: 0.23360435664653778
Norm Quadratic Average: 13.786423683166504
Nearest Class Center Accuracy: 0.924875

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.442383348941803
Inter Cos: 0.2603967487812042
Norm Quadratic Average: 9.124184608459473
Nearest Class Center Accuracy: 0.96725

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.74853515625
Linear Weight Rank: 4031
Intra Cos: 0.6369946002960205
Inter Cos: 0.2959558963775635
Norm Quadratic Average: 40.63793182373047
Nearest Class Center Accuracy: 0.9905

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.395891189575195
Linear Weight Rank: 3670
Intra Cos: 0.727375864982605
Inter Cos: 0.29498085379600525
Norm Quadratic Average: 27.704984664916992
Nearest Class Center Accuracy: 0.9965

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.1408326625823975
Linear Weight Rank: 10
Intra Cos: 0.757093608379364
Inter Cos: 0.2826838493347168
Norm Quadratic Average: 21.9578800201416
Nearest Class Center Accuracy: 0.996375

Output Layer:
Intra Cos: 0.7900316715240479
Inter Cos: 0.3272929787635803
Norm Quadratic Average: 16.866708755493164
Nearest Class Center Accuracy: 0.994875

Test Set:
Average Loss: 0.07432346379756928
Accuracy: 0.9755
NC1 Within Class Collapse: 2.934760570526123
NC2 Equinorm: Features: 0.13261778652668, Weights: 0.028008023276925087
NC2 Equiangle: Features: 0.2765192879570855, Weights: 0.12710914611816407
NC3 Self-Duality: 0.32342728972435
NC4 NCC Mismatch: 0.01649999999999996

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133808106184006
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: 0.13891035318374634
Inter Cos: 0.15937234461307526
Norm Quadratic Average: 40.9880256652832
Nearest Class Center Accuracy: 0.809

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17062591016292572
Inter Cos: 0.21280692517757416
Norm Quadratic Average: 44.681549072265625
Nearest Class Center Accuracy: 0.7845

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1842103898525238
Inter Cos: 0.24078842997550964
Norm Quadratic Average: 57.30370330810547
Nearest Class Center Accuracy: 0.783

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1613539755344391
Inter Cos: 0.24064072966575623
Norm Quadratic Average: 34.430809020996094
Nearest Class Center Accuracy: 0.824

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18104125559329987
Inter Cos: 0.27887260913848877
Norm Quadratic Average: 26.743228912353516
Nearest Class Center Accuracy: 0.8695

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2557535171508789
Inter Cos: 0.2644473612308502
Norm Quadratic Average: 13.397014617919922
Nearest Class Center Accuracy: 0.9215

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3898615837097168
Inter Cos: 0.2983247637748718
Norm Quadratic Average: 8.82484245300293
Nearest Class Center Accuracy: 0.9485

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.74853515625
Linear Weight Rank: 4031
Intra Cos: 0.5633938908576965
Inter Cos: 0.3151489198207855
Norm Quadratic Average: 39.10140609741211
Nearest Class Center Accuracy: 0.966

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.395891189575195
Linear Weight Rank: 3670
Intra Cos: 0.6459468007087708
Inter Cos: 0.2963797152042389
Norm Quadratic Average: 26.62641716003418
Nearest Class Center Accuracy: 0.972

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.1408326625823975
Linear Weight Rank: 10
Intra Cos: 0.6712139844894409
Inter Cos: 0.27110791206359863
Norm Quadratic Average: 21.121660232543945
Nearest Class Center Accuracy: 0.971

Output Layer:
Intra Cos: 0.6921730041503906
Inter Cos: 0.2979359030723572
Norm Quadratic Average: 16.194791793823242
Nearest Class Center Accuracy: 0.9705

