Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_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: 23.532934188842773
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11812461167573929
Inter Cos: 0.13738805055618286
Norm Quadratic Average: 47.40460205078125
Nearest Class Center Accuracy: 0.817375

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16357682645320892
Inter Cos: 0.16932231187820435
Norm Quadratic Average: 46.18656921386719
Nearest Class Center Accuracy: 0.803125

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17797820270061493
Inter Cos: 0.18320757150650024
Norm Quadratic Average: 60.57658386230469
Nearest Class Center Accuracy: 0.815875

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18819668889045715
Inter Cos: 0.17703044414520264
Norm Quadratic Average: 39.411136627197266
Nearest Class Center Accuracy: 0.856625

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2130899876356125
Inter Cos: 0.18989291787147522
Norm Quadratic Average: 37.835411071777344
Nearest Class Center Accuracy: 0.8965

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2921871542930603
Inter Cos: 0.17653021216392517
Norm Quadratic Average: 21.914867401123047
Nearest Class Center Accuracy: 0.93925

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.41240665316581726
Inter Cos: 0.20299765467643738
Norm Quadratic Average: 17.203922271728516
Nearest Class Center Accuracy: 0.97375

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.03260040283203
Linear Weight Rank: 4031
Intra Cos: 0.6453639268875122
Inter Cos: 0.23151344060897827
Norm Quadratic Average: 75.4396743774414
Nearest Class Center Accuracy: 0.998

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.632389068603516
Linear Weight Rank: 3671
Intra Cos: 0.7521616816520691
Inter Cos: 0.2556697726249695
Norm Quadratic Average: 48.795440673828125
Nearest Class Center Accuracy: 0.999875

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.4720349311828613
Linear Weight Rank: 10
Intra Cos: 0.8014659285545349
Inter Cos: 0.2670876681804657
Norm Quadratic Average: 38.08012390136719
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.8496109247207642
Inter Cos: 0.378826767206192
Norm Quadratic Average: 27.386056900024414
Nearest Class Center Accuracy: 0.99975

Test Set:
Average Loss: 0.08155916161835193
Accuracy: 0.9795
NC1 Within Class Collapse: 1.7633004188537598
NC2 Equinorm: Features: 0.09249703586101532, Weights: 0.009688688442111015
NC2 Equiangle: Features: 0.24134606255425348, Weights: 0.09598526424831814
NC3 Self-Duality: 0.532140851020813
NC4 NCC Mismatch: 0.013000000000000012

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: 0.132956400513649
Inter Cos: 0.14879925549030304
Norm Quadratic Average: 46.04895782470703
Nearest Class Center Accuracy: 0.8105

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1674775332212448
Inter Cos: 0.19422008097171783
Norm Quadratic Average: 44.93821716308594
Nearest Class Center Accuracy: 0.798

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17406399548053741
Inter Cos: 0.21670332551002502
Norm Quadratic Average: 58.836265563964844
Nearest Class Center Accuracy: 0.8125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17038221657276154
Inter Cos: 0.2102283090353012
Norm Quadratic Average: 38.38386917114258
Nearest Class Center Accuracy: 0.845

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19238881766796112
Inter Cos: 0.22513921558856964
Norm Quadratic Average: 36.91106414794922
Nearest Class Center Accuracy: 0.882

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25747814774513245
Inter Cos: 0.20643854141235352
Norm Quadratic Average: 21.30876922607422
Nearest Class Center Accuracy: 0.93

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.36337676644325256
Inter Cos: 0.22247348725795746
Norm Quadratic Average: 16.622770309448242
Nearest Class Center Accuracy: 0.9545

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.03260040283203
Linear Weight Rank: 4031
Intra Cos: 0.5749362111091614
Inter Cos: 0.2443581074476242
Norm Quadratic Average: 72.374755859375
Nearest Class Center Accuracy: 0.9695

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.632389068603516
Linear Weight Rank: 3671
Intra Cos: 0.6813740134239197
Inter Cos: 0.2537476420402527
Norm Quadratic Average: 46.700435638427734
Nearest Class Center Accuracy: 0.977

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.4720349311828613
Linear Weight Rank: 10
Intra Cos: 0.7287904024124146
Inter Cos: 0.27116069197654724
Norm Quadratic Average: 36.44548416137695
Nearest Class Center Accuracy: 0.977

Output Layer:
Intra Cos: 0.7719041109085083
Inter Cos: 0.35572317242622375
Norm Quadratic Average: 26.191259384155273
Nearest Class Center Accuracy: 0.9765

