Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_weight_decay_0.005.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: 0.11311887204647064
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: 0.11354494839906693
Inter Cos: 0.13877087831497192
Norm Quadratic Average: 42.773651123046875
Nearest Class Center Accuracy: 0.81575

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1486835777759552
Inter Cos: 0.17414158582687378
Norm Quadratic Average: 44.8852424621582
Nearest Class Center Accuracy: 0.792

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16142454743385315
Inter Cos: 0.19442734122276306
Norm Quadratic Average: 57.512481689453125
Nearest Class Center Accuracy: 0.8

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19640687108039856
Inter Cos: 0.20248493552207947
Norm Quadratic Average: 34.448341369628906
Nearest Class Center Accuracy: 0.835125

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23217473924160004
Inter Cos: 0.22311970591545105
Norm Quadratic Average: 29.623268127441406
Nearest Class Center Accuracy: 0.876625

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2916901409626007
Inter Cos: 0.20444779098033905
Norm Quadratic Average: 15.770831108093262
Nearest Class Center Accuracy: 0.9245

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.43017691373825073
Inter Cos: 0.23955905437469482
Norm Quadratic Average: 10.972259521484375
Nearest Class Center Accuracy: 0.971375

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.7633285522461
Linear Weight Rank: 4031
Intra Cos: 0.6517025232315063
Inter Cos: 0.27417945861816406
Norm Quadratic Average: 47.889984130859375
Nearest Class Center Accuracy: 0.996

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.25822448730469
Linear Weight Rank: 3670
Intra Cos: 0.746411919593811
Inter Cos: 0.2716924548149109
Norm Quadratic Average: 32.088111877441406
Nearest Class Center Accuracy: 0.999125

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2789690494537354
Linear Weight Rank: 10
Intra Cos: 0.7789656519889832
Inter Cos: 0.26529431343078613
Norm Quadratic Average: 25.681964874267578
Nearest Class Center Accuracy: 0.999125

Output Layer:
Intra Cos: 0.8039219975471497
Inter Cos: 0.3651406764984131
Norm Quadratic Average: 19.27359962463379
Nearest Class Center Accuracy: 0.998

Test Set:
Average Loss: 0.07156112569570541
Accuracy: 0.9785
NC1 Within Class Collapse: 2.009493112564087
NC2 Equinorm: Features: 0.12841935455799103, Weights: 0.017913613468408585
NC2 Equiangle: Features: 0.2564586639404297, Weights: 0.1072790781656901
NC3 Self-Duality: 0.41990870237350464
NC4 NCC Mismatch: 0.011499999999999955

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: 0.1371198445558548
Inter Cos: 0.1548624485731125
Norm Quadratic Average: 41.61056900024414
Nearest Class Center Accuracy: 0.808

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17049339413642883
Inter Cos: 0.20476239919662476
Norm Quadratic Average: 43.71160125732422
Nearest Class Center Accuracy: 0.7905

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1834314912557602
Inter Cos: 0.23250901699066162
Norm Quadratic Average: 55.927371978759766
Nearest Class Center Accuracy: 0.7995

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17445234954357147
Inter Cos: 0.23701892793178558
Norm Quadratic Average: 33.62083053588867
Nearest Class Center Accuracy: 0.8325

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19998066127300262
Inter Cos: 0.25811538100242615
Norm Quadratic Average: 28.928251266479492
Nearest Class Center Accuracy: 0.868

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.256570965051651
Inter Cos: 0.23306870460510254
Norm Quadratic Average: 15.382721900939941
Nearest Class Center Accuracy: 0.922

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.37859269976615906
Inter Cos: 0.2738586366176605
Norm Quadratic Average: 10.672557830810547
Nearest Class Center Accuracy: 0.9535

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.7633285522461
Linear Weight Rank: 4031
Intra Cos: 0.5790611505508423
Inter Cos: 0.3124665915966034
Norm Quadratic Average: 46.42727279663086
Nearest Class Center Accuracy: 0.967

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.25822448730469
Linear Weight Rank: 3670
Intra Cos: 0.663741946220398
Inter Cos: 0.3128432333469391
Norm Quadratic Average: 31.052602767944336
Nearest Class Center Accuracy: 0.972

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2789690494537354
Linear Weight Rank: 10
Intra Cos: 0.6899733543395996
Inter Cos: 0.2959633469581604
Norm Quadratic Average: 24.88728904724121
Nearest Class Center Accuracy: 0.972

Output Layer:
Intra Cos: 0.705251157283783
Inter Cos: 0.35758477449417114
Norm Quadratic Average: 18.655879974365234
Nearest Class Center Accuracy: 0.9695

