Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_weight_decay_0.0001.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946066349744797
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: 0.10026070475578308
Inter Cos: 0.1240093931555748
Norm Quadratic Average: 83.54485321044922
Nearest Class Center Accuracy: 0.830375

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13736391067504883
Inter Cos: 0.13368655741214752
Norm Quadratic Average: 56.195884704589844
Nearest Class Center Accuracy: 0.84625

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13966019451618195
Inter Cos: 0.1225697249174118
Norm Quadratic Average: 57.178375244140625
Nearest Class Center Accuracy: 0.867

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1567007601261139
Inter Cos: 0.10284330695867538
Norm Quadratic Average: 34.50462341308594
Nearest Class Center Accuracy: 0.897

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16302962601184845
Inter Cos: 0.0845281109213829
Norm Quadratic Average: 35.543251037597656
Nearest Class Center Accuracy: 0.926

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1937832236289978
Inter Cos: 0.08967728167772293
Norm Quadratic Average: 24.386205673217773
Nearest Class Center Accuracy: 0.96875

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.26995614171028137
Inter Cos: 0.10264234989881516
Norm Quadratic Average: 18.719457626342773
Nearest Class Center Accuracy: 0.99625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.87727355957031
Linear Weight Rank: 4031
Intra Cos: 0.4746496379375458
Inter Cos: 0.10777804255485535
Norm Quadratic Average: 118.4555435180664
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.782100677490234
Linear Weight Rank: 3670
Intra Cos: 0.6181222200393677
Inter Cos: 0.12733444571495056
Norm Quadratic Average: 64.31256103515625
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.297445058822632
Linear Weight Rank: 10
Intra Cos: 0.7430704832077026
Inter Cos: 0.15760686993598938
Norm Quadratic Average: 41.03877258300781
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.8994842767715454
Inter Cos: 0.24502137303352356
Norm Quadratic Average: 22.08313751220703
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.09642388892173767
Accuracy: 0.9735
NC1 Within Class Collapse: 1.7533783912658691
NC2 Equinorm: Features: 0.05672387406229973, Weights: 0.008791511878371239
NC2 Equiangle: Features: 0.1976165771484375, Weights: 0.0899038314819336
NC3 Self-Duality: 0.6385006904602051
NC4 NCC Mismatch: 0.008000000000000007

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: 0.12320926040410995
Inter Cos: 0.1289624720811844
Norm Quadratic Average: 81.99443817138672
Nearest Class Center Accuracy: 0.823

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14311031997203827
Inter Cos: 0.14801821112632751
Norm Quadratic Average: 55.46149826049805
Nearest Class Center Accuracy: 0.8405

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14217790961265564
Inter Cos: 0.13887503743171692
Norm Quadratic Average: 56.51076126098633
Nearest Class Center Accuracy: 0.8595

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14981529116630554
Inter Cos: 0.11535996943712234
Norm Quadratic Average: 34.32140350341797
Nearest Class Center Accuracy: 0.8905

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1538584679365158
Inter Cos: 0.10543521493673325
Norm Quadratic Average: 35.39099884033203
Nearest Class Center Accuracy: 0.9155

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18833263218402863
Inter Cos: 0.10514697432518005
Norm Quadratic Average: 24.31157112121582
Nearest Class Center Accuracy: 0.9435

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24959464371204376
Inter Cos: 0.11015568673610687
Norm Quadratic Average: 18.562686920166016
Nearest Class Center Accuracy: 0.9655

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.87727355957031
Linear Weight Rank: 4031
Intra Cos: 0.38596367835998535
Inter Cos: 0.11367557942867279
Norm Quadratic Average: 116.03964233398438
Nearest Class Center Accuracy: 0.9745

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.782100677490234
Linear Weight Rank: 3670
Intra Cos: 0.5078547596931458
Inter Cos: 0.1348627507686615
Norm Quadratic Average: 62.57663345336914
Nearest Class Center Accuracy: 0.976

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.297445058822632
Linear Weight Rank: 10
Intra Cos: 0.6173787713050842
Inter Cos: 0.16753356158733368
Norm Quadratic Average: 39.745182037353516
Nearest Class Center Accuracy: 0.976

Output Layer:
Intra Cos: 0.7739509344100952
Inter Cos: 0.26342934370040894
Norm Quadratic Average: 21.23242950439453
Nearest Class Center Accuracy: 0.9735

