Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_weight_decay_0.01.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946067094802856
Inter Cos: 0.11311887204647064
Norm Quadratic Average: 23.532939910888672
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1161700114607811
Inter Cos: 0.14099743962287903
Norm Quadratic Average: 41.94813919067383
Nearest Class Center Accuracy: 0.8155

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15357835590839386
Inter Cos: 0.18323734402656555
Norm Quadratic Average: 46.99225616455078
Nearest Class Center Accuracy: 0.783625

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16691824793815613
Inter Cos: 0.20376361906528473
Norm Quadratic Average: 60.729618072509766
Nearest Class Center Accuracy: 0.790375

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18774805963039398
Inter Cos: 0.20675262808799744
Norm Quadratic Average: 37.64409637451172
Nearest Class Center Accuracy: 0.82775

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21616263687610626
Inter Cos: 0.23210839927196503
Norm Quadratic Average: 29.057552337646484
Nearest Class Center Accuracy: 0.870875

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2959461808204651
Inter Cos: 0.2403714507818222
Norm Quadratic Average: 14.695757865905762
Nearest Class Center Accuracy: 0.91825

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.44408655166625977
Inter Cos: 0.29687321186065674
Norm Quadratic Average: 9.59635066986084
Nearest Class Center Accuracy: 0.965125

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.752967834472656
Linear Weight Rank: 4031
Intra Cos: 0.6318631768226624
Inter Cos: 0.3221191167831421
Norm Quadratic Average: 41.89616012573242
Nearest Class Center Accuracy: 0.990125

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.402538299560547
Linear Weight Rank: 3671
Intra Cos: 0.7232121229171753
Inter Cos: 0.29846644401550293
Norm Quadratic Average: 27.98590087890625
Nearest Class Center Accuracy: 0.99475

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.1366140842437744
Linear Weight Rank: 10
Intra Cos: 0.7515849471092224
Inter Cos: 0.3096136450767517
Norm Quadratic Average: 21.787351608276367
Nearest Class Center Accuracy: 0.995

Output Layer:
Intra Cos: 0.7869524955749512
Inter Cos: 0.39042919874191284
Norm Quadratic Average: 16.388700485229492
Nearest Class Center Accuracy: 0.994125

Test Set:
Average Loss: 0.07129395711421967
Accuracy: 0.979
NC1 Within Class Collapse: 2.7374792098999023
NC2 Equinorm: Features: 0.13248971104621887, Weights: 0.03153412789106369
NC2 Equiangle: Features: 0.2793213738335503, Weights: 0.11703205108642578
NC3 Self-Duality: 0.33127662539482117
NC4 NCC Mismatch: 0.018000000000000016

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: 22.82430076599121
Nearest Class Center Accuracy: 0.809

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13729175925254822
Inter Cos: 0.15676692128181458
Norm Quadratic Average: 40.577796936035156
Nearest Class Center Accuracy: 0.814

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1658724546432495
Inter Cos: 0.21222707629203796
Norm Quadratic Average: 45.453948974609375
Nearest Class Center Accuracy: 0.7855

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1807018220424652
Inter Cos: 0.24515047669410706
Norm Quadratic Average: 58.70079803466797
Nearest Class Center Accuracy: 0.7935

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16338162124156952
Inter Cos: 0.240401953458786
Norm Quadratic Average: 36.60683822631836
Nearest Class Center Accuracy: 0.828

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18738216161727905
Inter Cos: 0.26444491744041443
Norm Quadratic Average: 28.34556770324707
Nearest Class Center Accuracy: 0.8615

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2551315426826477
Inter Cos: 0.24010713398456573
Norm Quadratic Average: 14.293362617492676
Nearest Class Center Accuracy: 0.911

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.38511785864830017
Inter Cos: 0.2717703878879547
Norm Quadratic Average: 9.285534858703613
Nearest Class Center Accuracy: 0.9525

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.752967834472656
Linear Weight Rank: 4031
Intra Cos: 0.5553833246231079
Inter Cos: 0.2942330837249756
Norm Quadratic Average: 40.405860900878906
Nearest Class Center Accuracy: 0.963

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.402538299560547
Linear Weight Rank: 3671
Intra Cos: 0.6402699947357178
Inter Cos: 0.29468148946762085
Norm Quadratic Average: 26.92849349975586
Nearest Class Center Accuracy: 0.97

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.1366140842437744
Linear Weight Rank: 10
Intra Cos: 0.6654078960418701
Inter Cos: 0.31978824734687805
Norm Quadratic Average: 20.984106063842773
Nearest Class Center Accuracy: 0.97

Output Layer:
Intra Cos: 0.6913092136383057
Inter Cos: 0.39299169182777405
Norm Quadratic Average: 15.744488716125488
Nearest Class Center Accuracy: 0.9685

