Model save path: ./New_Models/bn_False_dataset_CIFAR10_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_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: 0.021450398489832878
Inter Cos: 0.11371058225631714
Norm Quadratic Average: 27.691619873046875
Nearest Class Center Accuracy: 0.279125

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.024450985714793205
Inter Cos: 0.09511721879243851
Norm Quadratic Average: 32.72193145751953
Nearest Class Center Accuracy: 0.30425

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03171096369624138
Inter Cos: 0.10155313462018967
Norm Quadratic Average: 25.711008071899414
Nearest Class Center Accuracy: 0.371625

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03512166067957878
Inter Cos: 0.09742336720228195
Norm Quadratic Average: 31.25261878967285
Nearest Class Center Accuracy: 0.41275

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.051159944385290146
Inter Cos: 0.12195972353219986
Norm Quadratic Average: 20.139598846435547
Nearest Class Center Accuracy: 0.43925

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.061227019876241684
Inter Cos: 0.11816827952861786
Norm Quadratic Average: 18.652530670166016
Nearest Class Center Accuracy: 0.467875

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08330359309911728
Inter Cos: 0.13562391698360443
Norm Quadratic Average: 10.386090278625488
Nearest Class Center Accuracy: 0.51925

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11295436322689056
Inter Cos: 0.15604187548160553
Norm Quadratic Average: 7.74245023727417
Nearest Class Center Accuracy: 0.699375

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.92747497558594
Linear Weight Rank: 4031
Intra Cos: 0.30513522028923035
Inter Cos: 0.2770737111568451
Norm Quadratic Average: 31.052045822143555
Nearest Class Center Accuracy: 0.971125

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.84343338012695
Linear Weight Rank: 3671
Intra Cos: 0.5794504284858704
Inter Cos: 0.43087098002433777
Norm Quadratic Average: 26.8409481048584
Nearest Class Center Accuracy: 0.9985

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 3.272494316101074
Linear Weight Rank: 10
Intra Cos: 0.7258695960044861
Inter Cos: 0.5452439785003662
Norm Quadratic Average: 31.282169342041016
Nearest Class Center Accuracy: 0.99975

Output Layer:
Intra Cos: 0.8337236046791077
Inter Cos: 0.7131975293159485
Norm Quadratic Average: 38.46306610107422
Nearest Class Center Accuracy: 0.998625

Test Set:
Average Loss: 3.3406178588867186
Accuracy: 0.5905
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.2517595887184143, Weights: 0.04583229869604111
NC2 Equiangle: Features: 0.4528532240125868, Weights: 0.15848173565334744
NC3 Self-Duality: 0.46716246008872986
NC4 NCC Mismatch: 0.15349999999999997

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018480457365512848
Inter Cos: 0.09352367371320724
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: 0.02558475360274315
Inter Cos: 0.07838969677686691
Norm Quadratic Average: 32.51151657104492
Nearest Class Center Accuracy: 0.323

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03290886804461479
Inter Cos: 0.09276337176561356
Norm Quadratic Average: 25.594829559326172
Nearest Class Center Accuracy: 0.3825

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0346345454454422
Inter Cos: 0.08817890286445618
Norm Quadratic Average: 31.175647735595703
Nearest Class Center Accuracy: 0.44

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.046983249485492706
Inter Cos: 0.11138192564249039
Norm Quadratic Average: 20.10539436340332
Nearest Class Center Accuracy: 0.4545

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.05551525950431824
Inter Cos: 0.10672487318515778
Norm Quadratic Average: 18.63338279724121
Nearest Class Center Accuracy: 0.465

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0672137588262558
Inter Cos: 0.12995795905590057
Norm Quadratic Average: 10.361188888549805
Nearest Class Center Accuracy: 0.4825

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.07618721574544907
Inter Cos: 0.14642374217510223
Norm Quadratic Average: 7.6872639656066895
Nearest Class Center Accuracy: 0.527

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.92747497558594
Linear Weight Rank: 4031
Intra Cos: 0.130537748336792
Inter Cos: 0.24821965396404266
Norm Quadratic Average: 29.86576271057129
Nearest Class Center Accuracy: 0.5885

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.84343338012695
Linear Weight Rank: 3671
Intra Cos: 0.2041093409061432
Inter Cos: 0.37537097930908203
Norm Quadratic Average: 24.983829498291016
Nearest Class Center Accuracy: 0.578

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 3.272494316101074
Linear Weight Rank: 10
Intra Cos: 0.23798644542694092
Inter Cos: 0.4648806154727936
Norm Quadratic Average: 28.860212326049805
Nearest Class Center Accuracy: 0.5665

Output Layer:
Intra Cos: 0.27157020568847656
Inter Cos: 0.5794198513031006
Norm Quadratic Average: 35.33049011230469
Nearest Class Center Accuracy: 0.5345

