Model save path: ./New_Models/bn_False_dataset_CIFAR10_epochs_200_lr_0.01_model_type_vgg11_rand_seed_979323_test_samples_None_train_samples_None_weight_decay_0.02.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0198909230530262
Inter Cos: 0.10477276891469955
Norm Quadratic Average: 27.59718894958496
Nearest Class Center Accuracy: 0.26968

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.024551445618271828
Inter Cos: 0.09343601018190384
Norm Quadratic Average: 19.999038696289062
Nearest Class Center Accuracy: 0.358

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03254072368144989
Inter Cos: 0.10058574378490448
Norm Quadratic Average: 10.218244552612305
Nearest Class Center Accuracy: 0.45886

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03747163712978363
Inter Cos: 0.09544390439987183
Norm Quadratic Average: 4.332376003265381
Nearest Class Center Accuracy: 0.56682

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0909654051065445
Inter Cos: 0.16741882264614105
Norm Quadratic Average: 0.8556356430053711
Nearest Class Center Accuracy: 0.63002

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3293766677379608
Inter Cos: 0.4866182208061218
Norm Quadratic Average: 0.44191649556159973
Nearest Class Center Accuracy: 0.79288

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6148391962051392
Inter Cos: 0.6516163349151611
Norm Quadratic Average: 0.6417948603630066
Nearest Class Center Accuracy: 0.8958

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6916038990020752
Inter Cos: 0.669520914554596
Norm Quadratic Average: 1.236899733543396
Nearest Class Center Accuracy: 0.9381

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.6634504795074463
Linear Weight Rank: 5
Intra Cos: 0.6606414914131165
Inter Cos: 0.5884211659431458
Norm Quadratic Average: 10.538127899169922
Nearest Class Center Accuracy: 0.96662

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.6659255027770996
Linear Weight Rank: 2747
Intra Cos: 0.63609778881073
Inter Cos: 0.5403792858123779
Norm Quadratic Average: 12.85043716430664
Nearest Class Center Accuracy: 0.97736

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.663220167160034
Linear Weight Rank: 9
Intra Cos: 0.6602867841720581
Inter Cos: 0.5098080039024353
Norm Quadratic Average: 14.305625915527344
Nearest Class Center Accuracy: 0.98226

Output Layer:
Intra Cos: 0.6328951716423035
Inter Cos: 0.5964764356613159
Norm Quadratic Average: 17.861448287963867
Nearest Class Center Accuracy: 0.98376

Test Set:
Average Loss: 0.8853177183151245
Accuracy: 0.7515
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.3373182415962219, Weights: 0.08294615894556046
NC2 Equiangle: Features: 0.4195093790690104, Weights: 0.27048640780978733
NC3 Self-Duality: 0.286763995885849
NC4 NCC Mismatch: 0.0827

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018526077270507812
Inter Cos: 0.1042705774307251
Norm Quadratic Average: 27.550140380859375
Nearest Class Center Accuracy: 0.284

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.022040551528334618
Inter Cos: 0.09400767832994461
Norm Quadratic Average: 19.995346069335938
Nearest Class Center Accuracy: 0.3726

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03104645013809204
Inter Cos: 0.10207761824131012
Norm Quadratic Average: 10.227725982666016
Nearest Class Center Accuracy: 0.4635

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03516184166073799
Inter Cos: 0.09609685093164444
Norm Quadratic Average: 4.340823173522949
Nearest Class Center Accuracy: 0.5637

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08755069226026535
Inter Cos: 0.16647954285144806
Norm Quadratic Average: 0.8563807606697083
Nearest Class Center Accuracy: 0.6137

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25705254077911377
Inter Cos: 0.478581964969635
Norm Quadratic Average: 0.4400906264781952
Nearest Class Center Accuracy: 0.6838

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.44790858030319214
Inter Cos: 0.587890088558197
Norm Quadratic Average: 0.636590838432312
Nearest Class Center Accuracy: 0.7175

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5251980423927307
Inter Cos: 0.5984069108963013
Norm Quadratic Average: 1.223301649093628
Nearest Class Center Accuracy: 0.7343

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.6634504795074463
Linear Weight Rank: 5
Intra Cos: 0.4844432473182678
Inter Cos: 0.5388770699501038
Norm Quadratic Average: 10.382569313049316
Nearest Class Center Accuracy: 0.7439

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.6659255027770996
Linear Weight Rank: 2747
Intra Cos: 0.43292003870010376
Inter Cos: 0.48718756437301636
Norm Quadratic Average: 12.610825538635254
Nearest Class Center Accuracy: 0.7402

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.663220167160034
Linear Weight Rank: 9
Intra Cos: 0.40660369396209717
Inter Cos: 0.4322082996368408
Norm Quadratic Average: 14.009468078613281
Nearest Class Center Accuracy: 0.737

Output Layer:
Intra Cos: 0.34415847063064575
Inter Cos: 0.4510648250579834
Norm Quadratic Average: 17.425411224365234
Nearest Class Center Accuracy: 0.7258

