Model save path: ./New_Models/bn_True_dataset_CIFAR10_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_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: 0.021450400352478027
Inter Cos: 0.11371058970689774
Norm Quadratic Average: 27.691617965698242
Nearest Class Center Accuracy: 0.279125

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.023175885900855064
Inter Cos: 0.10070184618234634
Norm Quadratic Average: 69.84566497802734
Nearest Class Center Accuracy: 0.34975

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.025680892169475555
Inter Cos: 0.09325036406517029
Norm Quadratic Average: 51.944725036621094
Nearest Class Center Accuracy: 0.377375

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02219417691230774
Inter Cos: 0.06808143854141235
Norm Quadratic Average: 55.08042907714844
Nearest Class Center Accuracy: 0.4095

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.030228279531002045
Inter Cos: 0.0823003277182579
Norm Quadratic Average: 34.58978271484375
Nearest Class Center Accuracy: 0.438125

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.031024914234876633
Inter Cos: 0.07696621119976044
Norm Quadratic Average: 35.524513244628906
Nearest Class Center Accuracy: 0.481625

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.042948827147483826
Inter Cos: 0.08192460983991623
Norm Quadratic Average: 22.561460494995117
Nearest Class Center Accuracy: 0.5875

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0714259222149849
Inter Cos: 0.08171478658914566
Norm Quadratic Average: 15.983195304870605
Nearest Class Center Accuracy: 0.903375

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.7608642578125
Linear Weight Rank: 4031
Intra Cos: 0.2267266809940338
Inter Cos: 0.11575407534837723
Norm Quadratic Average: 89.66864776611328
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.25187683105469
Linear Weight Rank: 3670
Intra Cos: 0.5146052241325378
Inter Cos: 0.20520758628845215
Norm Quadratic Average: 43.3076171875
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.137233257293701
Linear Weight Rank: 10
Intra Cos: 0.745873749256134
Inter Cos: 0.28928616642951965
Norm Quadratic Average: 28.411046981811523
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.8966159224510193
Inter Cos: 0.45259109139442444
Norm Quadratic Average: 18.18556785583496
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 1.8517778015136719
Accuracy: 0.583
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.1998700499534607, Weights: 0.015733011066913605
NC2 Equiangle: Features: 0.4317655775282118, Weights: 0.09129343032836915
NC3 Self-Duality: 0.5790743231773376
NC4 NCC Mismatch: 0.15349999999999997

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018480457365512848
Inter Cos: 0.09352368116378784
Norm Quadratic Average: 27.530664443969727
Nearest Class Center Accuracy: 0.2895

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02270578034222126
Inter Cos: 0.08861537277698517
Norm Quadratic Average: 69.5246810913086
Nearest Class Center Accuracy: 0.3715

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02551734261214733
Inter Cos: 0.08264263719320297
Norm Quadratic Average: 51.69200134277344
Nearest Class Center Accuracy: 0.398

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02114366739988327
Inter Cos: 0.06016920134425163
Norm Quadratic Average: 54.915592193603516
Nearest Class Center Accuracy: 0.447

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.026550794020295143
Inter Cos: 0.07372282445430756
Norm Quadratic Average: 34.45923614501953
Nearest Class Center Accuracy: 0.458

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.026877081021666527
Inter Cos: 0.06886706501245499
Norm Quadratic Average: 35.41648483276367
Nearest Class Center Accuracy: 0.4935

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.031215136870741844
Inter Cos: 0.07253342866897583
Norm Quadratic Average: 22.43942642211914
Nearest Class Center Accuracy: 0.513

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.036573659628629684
Inter Cos: 0.07775671780109406
Norm Quadratic Average: 15.82862663269043
Nearest Class Center Accuracy: 0.5845

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.7608642578125
Linear Weight Rank: 4031
Intra Cos: 0.07091198861598969
Inter Cos: 0.1294403374195099
Norm Quadratic Average: 85.79155731201172
Nearest Class Center Accuracy: 0.6105

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.25187683105469
Linear Weight Rank: 3670
Intra Cos: 0.14587920904159546
Inter Cos: 0.2435642033815384
Norm Quadratic Average: 39.26737976074219
Nearest Class Center Accuracy: 0.5935

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.137233257293701
Linear Weight Rank: 10
Intra Cos: 0.21528476476669312
Inter Cos: 0.355797678232193
Norm Quadratic Average: 24.805299758911133
Nearest Class Center Accuracy: 0.584

Output Layer:
Intra Cos: 0.2853567600250244
Inter Cos: 0.488216757774353
Norm Quadratic Average: 15.554940223693848
Nearest Class Center Accuracy: 0.571

