Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_weight_decay_0.001.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: 0.11456328630447388
Inter Cos: 0.13479964435100555
Norm Quadratic Average: 47.80103302001953
Nearest Class Center Accuracy: 0.821125

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15332438051700592
Inter Cos: 0.16992664337158203
Norm Quadratic Average: 46.444393157958984
Nearest Class Center Accuracy: 0.80125

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16651099920272827
Inter Cos: 0.18129141628742218
Norm Quadratic Average: 60.41758346557617
Nearest Class Center Accuracy: 0.806875

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18330490589141846
Inter Cos: 0.18124409019947052
Norm Quadratic Average: 38.821109771728516
Nearest Class Center Accuracy: 0.851875

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2020864188671112
Inter Cos: 0.20940126478672028
Norm Quadratic Average: 37.62727737426758
Nearest Class Center Accuracy: 0.891375

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.26904407143592834
Inter Cos: 0.1943252682685852
Norm Quadratic Average: 21.933008193969727
Nearest Class Center Accuracy: 0.93725

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3877353370189667
Inter Cos: 0.21860024333000183
Norm Quadratic Average: 17.10200309753418
Nearest Class Center Accuracy: 0.9745

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.63551330566406
Linear Weight Rank: 4031
Intra Cos: 0.6101170778274536
Inter Cos: 0.23549632728099823
Norm Quadratic Average: 74.83538055419922
Nearest Class Center Accuracy: 0.99725

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.058135986328125
Linear Weight Rank: 3670
Intra Cos: 0.7221322059631348
Inter Cos: 0.23563599586486816
Norm Quadratic Average: 48.090728759765625
Nearest Class Center Accuracy: 0.9995

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.439854860305786
Linear Weight Rank: 10
Intra Cos: 0.7754745483398438
Inter Cos: 0.25467559695243835
Norm Quadratic Average: 37.13566970825195
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.8249112963676453
Inter Cos: 0.360261470079422
Norm Quadratic Average: 26.574703216552734
Nearest Class Center Accuracy: 0.999875

Test Set:
Average Loss: 0.0784774709045887
Accuracy: 0.98
NC1 Within Class Collapse: 1.8817646503448486
NC2 Equinorm: Features: 0.10391919314861298, Weights: 0.01302820723503828
NC2 Equiangle: Features: 0.24527367485894097, Weights: 0.09853519863552518
NC3 Self-Duality: 0.5338676571846008
NC4 NCC Mismatch: 0.011499999999999955

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: 0.13525809347629547
Inter Cos: 0.15155382454395294
Norm Quadratic Average: 46.48146438598633
Nearest Class Center Accuracy: 0.814

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17110711336135864
Inter Cos: 0.20148326456546783
Norm Quadratic Average: 45.148582458496094
Nearest Class Center Accuracy: 0.8

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18083824217319489
Inter Cos: 0.2229306995868683
Norm Quadratic Average: 58.592891693115234
Nearest Class Center Accuracy: 0.8115

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16427311301231384
Inter Cos: 0.2192634791135788
Norm Quadratic Average: 37.826229095458984
Nearest Class Center Accuracy: 0.8445

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18060080707073212
Inter Cos: 0.24427519738674164
Norm Quadratic Average: 36.73343276977539
Nearest Class Center Accuracy: 0.8865

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24026966094970703
Inter Cos: 0.22154730558395386
Norm Quadratic Average: 21.405780792236328
Nearest Class Center Accuracy: 0.927

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3418042063713074
Inter Cos: 0.2505861818790436
Norm Quadratic Average: 16.583532333374023
Nearest Class Center Accuracy: 0.953

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.63551330566406
Linear Weight Rank: 4031
Intra Cos: 0.5335478782653809
Inter Cos: 0.26781895756721497
Norm Quadratic Average: 71.87777709960938
Nearest Class Center Accuracy: 0.971

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.058135986328125
Linear Weight Rank: 3670
Intra Cos: 0.634998619556427
Inter Cos: 0.26245367527008057
Norm Quadratic Average: 46.10633087158203
Nearest Class Center Accuracy: 0.9735

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.439854860305786
Linear Weight Rank: 10
Intra Cos: 0.683256208896637
Inter Cos: 0.23645150661468506
Norm Quadratic Average: 35.620662689208984
Nearest Class Center Accuracy: 0.9755

Output Layer:
Intra Cos: 0.7198475003242493
Inter Cos: 0.33464759588241577
Norm Quadratic Average: 25.458467483520508
Nearest Class Center Accuracy: 0.9735

