Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_weight_decay_0.0005.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946066349744797
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: 0.10461493581533432
Inter Cos: 0.11924475431442261
Norm Quadratic Average: 84.68014526367188
Nearest Class Center Accuracy: 0.829375

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14318493008613586
Inter Cos: 0.13513122498989105
Norm Quadratic Average: 56.238155364990234
Nearest Class Center Accuracy: 0.84525

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13808244466781616
Inter Cos: 0.12536334991455078
Norm Quadratic Average: 56.56326675415039
Nearest Class Center Accuracy: 0.868125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16015422344207764
Inter Cos: 0.11131982505321503
Norm Quadratic Average: 34.265342712402344
Nearest Class Center Accuracy: 0.91125

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16629400849342346
Inter Cos: 0.10206962376832962
Norm Quadratic Average: 35.80323028564453
Nearest Class Center Accuracy: 0.934625

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18343670666217804
Inter Cos: 0.10959972441196442
Norm Quadratic Average: 24.338783264160156
Nearest Class Center Accuracy: 0.972375

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27798521518707275
Inter Cos: 0.09703114628791809
Norm Quadratic Average: 18.77945327758789
Nearest Class Center Accuracy: 0.9965

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.96794891357422
Linear Weight Rank: 4031
Intra Cos: 0.48060813546180725
Inter Cos: 0.11206735670566559
Norm Quadratic Average: 117.38291931152344
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.987892150878906
Linear Weight Rank: 3670
Intra Cos: 0.6229913234710693
Inter Cos: 0.13411559164524078
Norm Quadratic Average: 63.129852294921875
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2494454383850098
Linear Weight Rank: 10
Intra Cos: 0.7412239909172058
Inter Cos: 0.16235993802547455
Norm Quadratic Average: 39.96876525878906
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.893504798412323
Inter Cos: 0.23819047212600708
Norm Quadratic Average: 21.18792152404785
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.10301710380613804
Accuracy: 0.972
NC1 Within Class Collapse: 1.715545654296875
NC2 Equinorm: Features: 0.059306129813194275, Weights: 0.011078393086791039
NC2 Equiangle: Features: 0.1976265377468533, Weights: 0.08575088183085124
NC3 Self-Duality: 0.6405695080757141
NC4 NCC Mismatch: 0.00649999999999995

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
Inter Cos: 0.11957792937755585
Norm Quadratic Average: 22.824302673339844
Nearest Class Center Accuracy: 0.809

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1270424872636795
Inter Cos: 0.1345827281475067
Norm Quadratic Average: 83.62037658691406
Nearest Class Center Accuracy: 0.8215

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15626950562000275
Inter Cos: 0.15608054399490356
Norm Quadratic Average: 55.822811126708984
Nearest Class Center Accuracy: 0.8415

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14465127885341644
Inter Cos: 0.13837093114852905
Norm Quadratic Average: 56.14383316040039
Nearest Class Center Accuracy: 0.866

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15536335110664368
Inter Cos: 0.12332555651664734
Norm Quadratic Average: 34.15586853027344
Nearest Class Center Accuracy: 0.902

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1611822098493576
Inter Cos: 0.11490415036678314
Norm Quadratic Average: 35.71569061279297
Nearest Class Center Accuracy: 0.9255

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18795675039291382
Inter Cos: 0.12845957279205322
Norm Quadratic Average: 24.22323989868164
Nearest Class Center Accuracy: 0.9475

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2541567087173462
Inter Cos: 0.09738178551197052
Norm Quadratic Average: 18.61591911315918
Nearest Class Center Accuracy: 0.9645

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.96794891357422
Linear Weight Rank: 4031
Intra Cos: 0.3991509974002838
Inter Cos: 0.12014413625001907
Norm Quadratic Average: 114.90511322021484
Nearest Class Center Accuracy: 0.9675

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.987892150878906
Linear Weight Rank: 3670
Intra Cos: 0.5124337673187256
Inter Cos: 0.13949349522590637
Norm Quadratic Average: 61.417518615722656
Nearest Class Center Accuracy: 0.97

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2494454383850098
Linear Weight Rank: 10
Intra Cos: 0.6188413500785828
Inter Cos: 0.168103888630867
Norm Quadratic Average: 38.72150421142578
Nearest Class Center Accuracy: 0.9695

Output Layer:
Intra Cos: 0.7662232518196106
Inter Cos: 0.2842824161052704
Norm Quadratic Average: 20.41100311279297
Nearest Class Center Accuracy: 0.9685

