Model save path: ./New_Models/bn_True_dataset_CIFAR10_epochs_200_lr_0.01_model_type_vgg11_rand_seed_314159_test_samples_None_train_samples_None_weight_decay_0.03.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01989092119038105
Inter Cos: 0.10477276146411896
Norm Quadratic Average: 27.59718132019043
Nearest Class Center Accuracy: 0.26968

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02218010649085045
Inter Cos: 0.08613824844360352
Norm Quadratic Average: 2.627408504486084
Nearest Class Center Accuracy: 0.4058

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.022438939660787582
Inter Cos: 0.058763790875673294
Norm Quadratic Average: 1.3222097158432007
Nearest Class Center Accuracy: 0.52552

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.020412860438227654
Inter Cos: 0.055628784000873566
Norm Quadratic Average: 0.9880579710006714
Nearest Class Center Accuracy: 0.61674

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03091082163155079
Inter Cos: 0.06017468124628067
Norm Quadratic Average: 0.6981716156005859
Nearest Class Center Accuracy: 0.7339

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.05188431963324547
Inter Cos: 0.06818684935569763
Norm Quadratic Average: 0.6075230240821838
Nearest Class Center Accuracy: 0.8406

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21458815038204193
Inter Cos: 0.2199016511440277
Norm Quadratic Average: 0.3856956362724304
Nearest Class Center Accuracy: 0.95872

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8106045722961426
Inter Cos: 0.27949902415275574
Norm Quadratic Average: 0.4541398584842682
Nearest Class Center Accuracy: 0.9999

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.000941753387451
Linear Weight Rank: 9
Intra Cos: 0.979983389377594
Inter Cos: 0.23922917246818542
Norm Quadratic Average: 22.50994873046875
Nearest Class Center Accuracy: 0.99994

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.0034310817718506
Linear Weight Rank: 1502
Intra Cos: 0.9857235550880432
Inter Cos: 0.2368568629026413
Norm Quadratic Average: 14.915889739990234
Nearest Class Center Accuracy: 0.99994

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.0033860206604004
Linear Weight Rank: 9
Intra Cos: 0.9881612062454224
Inter Cos: 0.21624760329723358
Norm Quadratic Average: 10.096061706542969
Nearest Class Center Accuracy: 0.99994

Output Layer:
Intra Cos: 0.990620493888855
Inter Cos: 0.17923854291439056
Norm Quadratic Average: 7.314876556396484
Nearest Class Center Accuracy: 0.99996

Test Set:
Average Loss: 0.5080599918365478
Accuracy: 0.8447
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.1203605979681015, Weights: 0.008262098766863346
NC2 Equiangle: Features: 0.16199154324001735, Weights: 0.11021628909640842
NC3 Self-Duality: 0.05956335365772247
NC4 NCC Mismatch: 0.01849999999999996

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018526073545217514
Inter Cos: 0.1042705774307251
Norm Quadratic Average: 27.550134658813477
Nearest Class Center Accuracy: 0.284

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02048044465482235
Inter Cos: 0.08691377192735672
Norm Quadratic Average: 2.626178741455078
Nearest Class Center Accuracy: 0.4224

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.021145382896065712
Inter Cos: 0.05958576127886772
Norm Quadratic Average: 1.322779893875122
Nearest Class Center Accuracy: 0.5367

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.019168145954608917
Inter Cos: 0.056040920317173004
Norm Quadratic Average: 0.9894562363624573
Nearest Class Center Accuracy: 0.618

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02695293352007866
Inter Cos: 0.061001408845186234
Norm Quadratic Average: 0.6984608769416809
Nearest Class Center Accuracy: 0.7079

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.042030882090330124
Inter Cos: 0.0706208273768425
Norm Quadratic Average: 0.6053999662399292
Nearest Class Center Accuracy: 0.7616

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16070330142974854
Inter Cos: 0.21900111436843872
Norm Quadratic Average: 0.38052141666412354
Nearest Class Center Accuracy: 0.8074

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.44478827714920044
Inter Cos: 0.3231556713581085
Norm Quadratic Average: 0.42058461904525757
Nearest Class Center Accuracy: 0.8422

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.000941753387451
Linear Weight Rank: 9
Intra Cos: 0.5567159056663513
Inter Cos: 0.36230355501174927
Norm Quadratic Average: 20.10861587524414
Nearest Class Center Accuracy: 0.8452

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.0034310817718506
Linear Weight Rank: 1502
Intra Cos: 0.5653791427612305
Inter Cos: 0.36849918961524963
Norm Quadratic Average: 13.3336181640625
Nearest Class Center Accuracy: 0.8452

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.0033860206604004
Linear Weight Rank: 9
Intra Cos: 0.5705844163894653
Inter Cos: 0.3650868535041809
Norm Quadratic Average: 9.021440505981445
Nearest Class Center Accuracy: 0.8439

Output Layer:
Intra Cos: 0.5912986397743225
Inter Cos: 0.35612741112709045
Norm Quadratic Average: 6.544677734375
Nearest Class Center Accuracy: 0.8443

