Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_weight_decay_0.0003.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: 23.532934188842773
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11804766952991486
Inter Cos: 0.1372341811656952
Norm Quadratic Average: 47.96828842163086
Nearest Class Center Accuracy: 0.8175

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16353988647460938
Inter Cos: 0.1690727323293686
Norm Quadratic Average: 46.819427490234375
Nearest Class Center Accuracy: 0.804

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17838163673877716
Inter Cos: 0.18312418460845947
Norm Quadratic Average: 61.762794494628906
Nearest Class Center Accuracy: 0.81775

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18840391933918
Inter Cos: 0.17619633674621582
Norm Quadratic Average: 40.617923736572266
Nearest Class Center Accuracy: 0.857875

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21350429952144623
Inter Cos: 0.18648198246955872
Norm Quadratic Average: 39.6990966796875
Nearest Class Center Accuracy: 0.898875

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2918182909488678
Inter Cos: 0.1748974770307541
Norm Quadratic Average: 23.28256607055664
Nearest Class Center Accuracy: 0.941

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4105214774608612
Inter Cos: 0.20030838251113892
Norm Quadratic Average: 18.44222640991211
Nearest Class Center Accuracy: 0.974375

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.9307632446289
Linear Weight Rank: 4031
Intra Cos: 0.6364529728889465
Inter Cos: 0.22682902216911316
Norm Quadratic Average: 80.90462493896484
Nearest Class Center Accuracy: 0.997625

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.39875793457031
Linear Weight Rank: 3671
Intra Cos: 0.7457607388496399
Inter Cos: 0.25339072942733765
Norm Quadratic Average: 52.26132583618164
Nearest Class Center Accuracy: 0.999875

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.500775098800659
Linear Weight Rank: 10
Intra Cos: 0.7979723215103149
Inter Cos: 0.26620814204216003
Norm Quadratic Average: 40.74215316772461
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.8479915261268616
Inter Cos: 0.37680870294570923
Norm Quadratic Average: 29.271900177001953
Nearest Class Center Accuracy: 0.99975

Test Set:
Average Loss: 0.08408108145743609
Accuracy: 0.979
NC1 Within Class Collapse: 1.777050256729126
NC2 Equinorm: Features: 0.0934431180357933, Weights: 0.009479692205786705
NC2 Equiangle: Features: 0.23941726684570314, Weights: 0.0950399398803711
NC3 Self-Duality: 0.5444945096969604
NC4 NCC Mismatch: 0.011499999999999955

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133805871009827
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: 0.13284195959568024
Inter Cos: 0.1485765278339386
Norm Quadratic Average: 46.599613189697266
Nearest Class Center Accuracy: 0.8105

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16717948019504547
Inter Cos: 0.193314790725708
Norm Quadratic Average: 45.56135177612305
Nearest Class Center Accuracy: 0.799

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17326223850250244
Inter Cos: 0.21555249392986298
Norm Quadratic Average: 59.993900299072266
Nearest Class Center Accuracy: 0.8155

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16988898813724518
Inter Cos: 0.20701973140239716
Norm Quadratic Average: 39.57162094116211
Nearest Class Center Accuracy: 0.848

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19141636788845062
Inter Cos: 0.2209121435880661
Norm Quadratic Average: 38.73127746582031
Nearest Class Center Accuracy: 0.885

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25624799728393555
Inter Cos: 0.20317861437797546
Norm Quadratic Average: 22.63848114013672
Nearest Class Center Accuracy: 0.933

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.36093971133232117
Inter Cos: 0.21164283156394958
Norm Quadratic Average: 17.82366180419922
Nearest Class Center Accuracy: 0.9555

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.9307632446289
Linear Weight Rank: 4031
Intra Cos: 0.5649120807647705
Inter Cos: 0.2488202601671219
Norm Quadratic Average: 77.62348175048828
Nearest Class Center Accuracy: 0.969

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.39875793457031
Linear Weight Rank: 3671
Intra Cos: 0.6734833121299744
Inter Cos: 0.25202521681785583
Norm Quadratic Average: 50.03510284423828
Nearest Class Center Accuracy: 0.973

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.500775098800659
Linear Weight Rank: 10
Intra Cos: 0.7235145568847656
Inter Cos: 0.2687538266181946
Norm Quadratic Average: 39.00120162963867
Nearest Class Center Accuracy: 0.975

Output Layer:
Intra Cos: 0.7683823704719543
Inter Cos: 0.35205918550491333
Norm Quadratic Average: 28.002458572387695
Nearest Class Center Accuracy: 0.975

