Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_weight_decay_0.007.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: 23.532936096191406
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1030978187918663
Inter Cos: 0.12467873841524124
Norm Quadratic Average: 63.22581481933594
Nearest Class Center Accuracy: 0.835375

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14872466027736664
Inter Cos: 0.1373482644557953
Norm Quadratic Average: 40.696895599365234
Nearest Class Center Accuracy: 0.852875

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14819219708442688
Inter Cos: 0.12557455897331238
Norm Quadratic Average: 40.552066802978516
Nearest Class Center Accuracy: 0.87675

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17231757938861847
Inter Cos: 0.10497228801250458
Norm Quadratic Average: 24.993009567260742
Nearest Class Center Accuracy: 0.913

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18873219192028046
Inter Cos: 0.09226986765861511
Norm Quadratic Average: 25.83783531188965
Nearest Class Center Accuracy: 0.94425

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22667858004570007
Inter Cos: 0.10674572736024857
Norm Quadratic Average: 17.581907272338867
Nearest Class Center Accuracy: 0.982375

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3541158437728882
Inter Cos: 0.1197236105799675
Norm Quadratic Average: 13.773210525512695
Nearest Class Center Accuracy: 0.998375

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 72.4490966796875
Linear Weight Rank: 4031
Intra Cos: 0.6016407012939453
Inter Cos: 0.13477326929569244
Norm Quadratic Average: 95.19744873046875
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 29.30028533935547
Linear Weight Rank: 3671
Intra Cos: 0.7564390897750854
Inter Cos: 0.1659359335899353
Norm Quadratic Average: 45.801612854003906
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.8334808349609375
Linear Weight Rank: 10
Intra Cos: 0.8605470061302185
Inter Cos: 0.17186421155929565
Norm Quadratic Average: 26.83879852294922
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9291262030601501
Inter Cos: 0.25983643531799316
Norm Quadratic Average: 13.937857627868652
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.06762686729431153
Accuracy: 0.9775
NC1 Within Class Collapse: 1.43537175655365
NC2 Equinorm: Features: 0.07272838056087494, Weights: 0.013660253956913948
NC2 Equiangle: Features: 0.20708622402615018, Weights: 0.08224773406982422
NC3 Self-Duality: 0.46760866045951843
NC4 NCC Mismatch: 0.0044999999999999485

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: 0.12624509632587433
Inter Cos: 0.13151921331882477
Norm Quadratic Average: 62.16761016845703
Nearest Class Center Accuracy: 0.828

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15530109405517578
Inter Cos: 0.15480318665504456
Norm Quadratic Average: 40.229366302490234
Nearest Class Center Accuracy: 0.8455

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1530928909778595
Inter Cos: 0.13757747411727905
Norm Quadratic Average: 40.14018630981445
Nearest Class Center Accuracy: 0.871

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1652364730834961
Inter Cos: 0.12354599684476852
Norm Quadratic Average: 24.887460708618164
Nearest Class Center Accuracy: 0.912

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17808200418949127
Inter Cos: 0.11533496528863907
Norm Quadratic Average: 25.760602951049805
Nearest Class Center Accuracy: 0.9325

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21375492215156555
Inter Cos: 0.11756071448326111
Norm Quadratic Average: 17.547683715820312
Nearest Class Center Accuracy: 0.9605

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.29975807666778564
Inter Cos: 0.12919870018959045
Norm Quadratic Average: 13.669995307922363
Nearest Class Center Accuracy: 0.974

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 72.4490966796875
Linear Weight Rank: 4031
Intra Cos: 0.5102945566177368
Inter Cos: 0.15014702081680298
Norm Quadratic Average: 92.81214904785156
Nearest Class Center Accuracy: 0.9795

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 29.30028533935547
Linear Weight Rank: 3671
Intra Cos: 0.6531748175621033
Inter Cos: 0.18757253885269165
Norm Quadratic Average: 44.3690185546875
Nearest Class Center Accuracy: 0.978

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.8334808349609375
Linear Weight Rank: 10
Intra Cos: 0.7434272170066833
Inter Cos: 0.1969703882932663
Norm Quadratic Average: 25.950559616088867
Nearest Class Center Accuracy: 0.9775

Output Layer:
Intra Cos: 0.8155484795570374
Inter Cos: 0.2393551468849182
Norm Quadratic Average: 13.426506042480469
Nearest Class Center Accuracy: 0.974

