Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_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: 23.53293800354004
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11440431326627731
Inter Cos: 0.13455310463905334
Norm Quadratic Average: 48.80192184448242
Nearest Class Center Accuracy: 0.821625

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15306636691093445
Inter Cos: 0.1695227026939392
Norm Quadratic Average: 47.5401725769043
Nearest Class Center Accuracy: 0.801625

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16651996970176697
Inter Cos: 0.18167950212955475
Norm Quadratic Average: 62.709476470947266
Nearest Class Center Accuracy: 0.809375

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1818130761384964
Inter Cos: 0.17967821657657623
Norm Quadratic Average: 41.01493453979492
Nearest Class Center Accuracy: 0.852625

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20125694572925568
Inter Cos: 0.2062593698501587
Norm Quadratic Average: 40.54256057739258
Nearest Class Center Accuracy: 0.8935

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.262401282787323
Inter Cos: 0.19257371127605438
Norm Quadratic Average: 24.048948287963867
Nearest Class Center Accuracy: 0.936375

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.37903931736946106
Inter Cos: 0.2188650369644165
Norm Quadratic Average: 19.026805877685547
Nearest Class Center Accuracy: 0.974625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.93406677246094
Linear Weight Rank: 4031
Intra Cos: 0.6035841107368469
Inter Cos: 0.2390449196100235
Norm Quadratic Average: 84.23665618896484
Nearest Class Center Accuracy: 0.997375

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.38948059082031
Linear Weight Rank: 3670
Intra Cos: 0.715968668460846
Inter Cos: 0.2381058931350708
Norm Quadratic Average: 54.224491119384766
Nearest Class Center Accuracy: 0.999625

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.4876255989074707
Linear Weight Rank: 10
Intra Cos: 0.77225661277771
Inter Cos: 0.25873157382011414
Norm Quadratic Average: 41.919944763183594
Nearest Class Center Accuracy: 0.999875

Output Layer:
Intra Cos: 0.8265080451965332
Inter Cos: 0.35695797204971313
Norm Quadratic Average: 30.032989501953125
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.08680173288285732
Accuracy: 0.9795
NC1 Within Class Collapse: 1.8365609645843506
NC2 Equinorm: Features: 0.10179838538169861, Weights: 0.013156539760529995
NC2 Equiangle: Features: 0.24378704494900175, Weights: 0.09770076539781358
NC3 Self-Duality: 0.5535824298858643
NC4 NCC Mismatch: 0.009499999999999953

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133808106184006
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: 0.13504716753959656
Inter Cos: 0.15120801329612732
Norm Quadratic Average: 47.45901107788086
Nearest Class Center Accuracy: 0.814

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17065489292144775
Inter Cos: 0.2004469633102417
Norm Quadratic Average: 46.21828842163086
Nearest Class Center Accuracy: 0.802

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18004195392131805
Inter Cos: 0.22194726765155792
Norm Quadratic Average: 60.82061767578125
Nearest Class Center Accuracy: 0.813

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16279281675815582
Inter Cos: 0.21677803993225098
Norm Quadratic Average: 39.96530532836914
Nearest Class Center Accuracy: 0.8455

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17925409972667694
Inter Cos: 0.23946240544319153
Norm Quadratic Average: 39.57768630981445
Nearest Class Center Accuracy: 0.887

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23277901113033295
Inter Cos: 0.21763890981674194
Norm Quadratic Average: 23.471586227416992
Nearest Class Center Accuracy: 0.928

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3327237069606781
Inter Cos: 0.2486959993839264
Norm Quadratic Average: 18.449127197265625
Nearest Class Center Accuracy: 0.954

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.93406677246094
Linear Weight Rank: 4031
Intra Cos: 0.5266641974449158
Inter Cos: 0.2640130817890167
Norm Quadratic Average: 80.88890075683594
Nearest Class Center Accuracy: 0.9705

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.38948059082031
Linear Weight Rank: 3670
Intra Cos: 0.6287133097648621
Inter Cos: 0.254145085811615
Norm Quadratic Average: 51.96320724487305
Nearest Class Center Accuracy: 0.975

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.4876255989074707
Linear Weight Rank: 10
Intra Cos: 0.6792324781417847
Inter Cos: 0.23734143376350403
Norm Quadratic Average: 40.19703674316406
Nearest Class Center Accuracy: 0.976

Output Layer:
Intra Cos: 0.7207975387573242
Inter Cos: 0.33248621225357056
Norm Quadratic Average: 28.759666442871094
Nearest Class Center Accuracy: 0.9725

