Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_weight_decay_0.0007.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: 0.10305530577898026
Inter Cos: 0.12475714087486267
Norm Quadratic Average: 85.5318374633789
Nearest Class Center Accuracy: 0.835375

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14727017283439636
Inter Cos: 0.13692454993724823
Norm Quadratic Average: 54.926025390625
Nearest Class Center Accuracy: 0.851375

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14590109884738922
Inter Cos: 0.12426843494176865
Norm Quadratic Average: 54.805694580078125
Nearest Class Center Accuracy: 0.873125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16785475611686707
Inter Cos: 0.10534101724624634
Norm Quadratic Average: 33.82252883911133
Nearest Class Center Accuracy: 0.904875

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1785118728876114
Inter Cos: 0.08841940760612488
Norm Quadratic Average: 34.997779846191406
Nearest Class Center Accuracy: 0.93475

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21125128865242004
Inter Cos: 0.10273271799087524
Norm Quadratic Average: 23.820575714111328
Nearest Class Center Accuracy: 0.96975

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2922280728816986
Inter Cos: 0.10646934807300568
Norm Quadratic Average: 18.478872299194336
Nearest Class Center Accuracy: 0.996

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.02171325683594
Linear Weight Rank: 4031
Intra Cos: 0.4991159439086914
Inter Cos: 0.1244753822684288
Norm Quadratic Average: 116.70389556884766
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.63072204589844
Linear Weight Rank: 3671
Intra Cos: 0.6299048662185669
Inter Cos: 0.1606682687997818
Norm Quadratic Average: 62.46370315551758
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.244349479675293
Linear Weight Rank: 10
Intra Cos: 0.7572238445281982
Inter Cos: 0.18426823616027832
Norm Quadratic Average: 39.56032180786133
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9082797765731812
Inter Cos: 0.24590624868869781
Norm Quadratic Average: 21.406232833862305
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.08596281200647354
Accuracy: 0.9775
NC1 Within Class Collapse: 1.6526048183441162
NC2 Equinorm: Features: 0.07479025423526764, Weights: 0.010822461917996407
NC2 Equiangle: Features: 0.2068405999077691, Weights: 0.0864927609761556
NC3 Self-Duality: 0.6386526823043823
NC4 NCC Mismatch: 0.006000000000000005

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: 0.12614160776138306
Inter Cos: 0.13136807084083557
Norm Quadratic Average: 84.09024810791016
Nearest Class Center Accuracy: 0.8275

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15555991232395172
Inter Cos: 0.15396302938461304
Norm Quadratic Average: 54.27985763549805
Nearest Class Center Accuracy: 0.844

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1507033407688141
Inter Cos: 0.13513541221618652
Norm Quadratic Average: 54.225250244140625
Nearest Class Center Accuracy: 0.869

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15981432795524597
Inter Cos: 0.1191265732049942
Norm Quadratic Average: 33.649497985839844
Nearest Class Center Accuracy: 0.905

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16842803359031677
Inter Cos: 0.10745246708393097
Norm Quadratic Average: 34.86941909790039
Nearest Class Center Accuracy: 0.9265

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19771674275398254
Inter Cos: 0.11523304879665375
Norm Quadratic Average: 23.769512176513672
Nearest Class Center Accuracy: 0.946

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2508714199066162
Inter Cos: 0.11846518516540527
Norm Quadratic Average: 18.338193893432617
Nearest Class Center Accuracy: 0.968

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.02171325683594
Linear Weight Rank: 4031
Intra Cos: 0.41274911165237427
Inter Cos: 0.13772350549697876
Norm Quadratic Average: 114.17396545410156
Nearest Class Center Accuracy: 0.9755

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.63072204589844
Linear Weight Rank: 3671
Intra Cos: 0.5357550382614136
Inter Cos: 0.17782430350780487
Norm Quadratic Average: 60.74048614501953
Nearest Class Center Accuracy: 0.9755

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.244349479675293
Linear Weight Rank: 10
Intra Cos: 0.6449600458145142
Inter Cos: 0.20890314877033234
Norm Quadratic Average: 38.3484001159668
Nearest Class Center Accuracy: 0.9765

Output Layer:
Intra Cos: 0.7943426370620728
Inter Cos: 0.2718895673751831
Norm Quadratic Average: 20.617359161376953
Nearest Class Center Accuracy: 0.9745

