Model save path: ./New_Models/bn_False_dataset_CIFAR100_epochs_200_lr_0.01_model_type_vgg11_rand_seed_314159_test_samples_None_train_samples_None_weight_decay_0.005.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.022893192246556282
Inter Cos: 0.07011394202709198
Norm Quadratic Average: 29.326322555541992
Nearest Class Center Accuracy: 0.03258

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.04102490097284317
Inter Cos: 0.06892601400613785
Norm Quadratic Average: 36.78016662597656
Nearest Class Center Accuracy: 0.04216

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.04249297082424164
Inter Cos: 0.05288560315966606
Norm Quadratic Average: 41.43804931640625
Nearest Class Center Accuracy: 0.0509

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03942646086215973
Inter Cos: 0.04320772364735603
Norm Quadratic Average: 50.54997634887695
Nearest Class Center Accuracy: 0.05988

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03864791989326477
Inter Cos: 0.03710739687085152
Norm Quadratic Average: 16.227792739868164
Nearest Class Center Accuracy: 0.06984

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.05704332888126373
Inter Cos: 0.047071054577827454
Norm Quadratic Average: 3.3688414096832275
Nearest Class Center Accuracy: 0.07374

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.36692410707473755
Inter Cos: 0.3282654583454132
Norm Quadratic Average: 0.9901747703552246
Nearest Class Center Accuracy: 0.0857

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6812227964401245
Inter Cos: 0.5160176753997803
Norm Quadratic Average: 1.6945226192474365
Nearest Class Center Accuracy: 0.09758

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 4.88031005859375
Linear Weight Rank: 161
Intra Cos: 0.8278884887695312
Inter Cos: 0.6157465577125549
Norm Quadratic Average: 20.448896408081055
Nearest Class Center Accuracy: 0.09936

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 4.966185092926025
Linear Weight Rank: 2873
Intra Cos: 0.8725181818008423
Inter Cos: 0.6532433032989502
Norm Quadratic Average: 36.02557373046875
Nearest Class Center Accuracy: 0.09988

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 5.051718235015869
Linear Weight Rank: 96
Intra Cos: 0.8588336110115051
Inter Cos: 0.6137744188308716
Norm Quadratic Average: 49.13248062133789
Nearest Class Center Accuracy: 0.1

Output Layer:
Intra Cos: 0.8968625664710999
Inter Cos: 0.6770074367523193
Norm Quadratic Average: 67.77481842041016
Nearest Class Center Accuracy: 0.1

Test Set:
Average Loss: 3.7659545692443848
Accuracy: 0.3984
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.2901354730129242, Weights: 0.0584598034620285
NC2 Equiangle: Features: 0.3134315321180556, Weights: 0.17779594036063762
NC3 Self-Duality: 0.4553588628768921
NC4 NCC Mismatch: 0.3307

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.006621268577873707
Inter Cos: 0.4067547917366028
Norm Quadratic Average: 29.42218780517578
Nearest Class Center Accuracy: 0.1136

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.013943801634013653
Inter Cos: 0.29779475927352905
Norm Quadratic Average: 36.953853607177734
Nearest Class Center Accuracy: 0.1926

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02071119099855423
Inter Cos: 0.340145468711853
Norm Quadratic Average: 41.65993118286133
Nearest Class Center Accuracy: 0.2564

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.022420573979616165
Inter Cos: 0.33048108220100403
Norm Quadratic Average: 50.872100830078125
Nearest Class Center Accuracy: 0.3265

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02609846368432045
Inter Cos: 0.2801785469055176
Norm Quadratic Average: 16.36324691772461
Nearest Class Center Accuracy: 0.454

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.026753336191177368
Inter Cos: 0.357509046792984
Norm Quadratic Average: 3.387800931930542
Nearest Class Center Accuracy: 0.475

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0698358565568924
Inter Cos: 0.6942586898803711
Norm Quadratic Average: 0.977443277835846
Nearest Class Center Accuracy: 0.3257

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0782662183046341
Inter Cos: 0.6880103945732117
Norm Quadratic Average: 1.6266268491744995
Nearest Class Center Accuracy: 0.3408

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 4.88031005859375
Linear Weight Rank: 161
Intra Cos: 0.0905168354511261
Inter Cos: 0.729033350944519
Norm Quadratic Average: 19.37884521484375
Nearest Class Center Accuracy: 0.3728

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 4.966185092926025
Linear Weight Rank: 2873
Intra Cos: 0.08921367675065994
Inter Cos: 0.7269715070724487
Norm Quadratic Average: 33.96570587158203
Nearest Class Center Accuracy: 0.3809

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 5.051718235015869
Linear Weight Rank: 96
Intra Cos: 0.11262969672679901
Inter Cos: 0.6884844303131104
Norm Quadratic Average: 46.699283599853516
Nearest Class Center Accuracy: 0.3845

Output Layer:
Intra Cos: 0.09229423105716705
Inter Cos: 0.7201895117759705
Norm Quadratic Average: 64.00326538085938
Nearest Class Center Accuracy: 0.3877

