Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_weight_decay_0.0003.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: 0.10171040147542953
Inter Cos: 0.12586481869220734
Norm Quadratic Average: 89.3249282836914
Nearest Class Center Accuracy: 0.83125

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1419590413570404
Inter Cos: 0.1332779973745346
Norm Quadratic Average: 55.839195251464844
Nearest Class Center Accuracy: 0.847875

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14024503529071808
Inter Cos: 0.12424648553133011
Norm Quadratic Average: 56.155426025390625
Nearest Class Center Accuracy: 0.8685

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17325809597969055
Inter Cos: 0.10222221910953522
Norm Quadratic Average: 34.56233215332031
Nearest Class Center Accuracy: 0.90425

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17700685560703278
Inter Cos: 0.09206721931695938
Norm Quadratic Average: 35.67921447753906
Nearest Class Center Accuracy: 0.93075

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20852366089820862
Inter Cos: 0.08967295289039612
Norm Quadratic Average: 24.379831314086914
Nearest Class Center Accuracy: 0.972625

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2905576527118683
Inter Cos: 0.10291459411382675
Norm Quadratic Average: 19.025842666625977
Nearest Class Center Accuracy: 0.995875

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.91657257080078
Linear Weight Rank: 4031
Intra Cos: 0.48819416761398315
Inter Cos: 0.1389937698841095
Norm Quadratic Average: 118.60687255859375
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.39731216430664
Linear Weight Rank: 3671
Intra Cos: 0.6348905563354492
Inter Cos: 0.1583297699689865
Norm Quadratic Average: 64.03765869140625
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2718307971954346
Linear Weight Rank: 10
Intra Cos: 0.7517692446708679
Inter Cos: 0.16355067491531372
Norm Quadratic Average: 40.84989547729492
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9056472182273865
Inter Cos: 0.26544174551963806
Norm Quadratic Average: 22.08831787109375
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.0992530229985714
Accuracy: 0.976
NC1 Within Class Collapse: 1.6453323364257812
NC2 Equinorm: Features: 0.06661276519298553, Weights: 0.012244081124663353
NC2 Equiangle: Features: 0.20550301869710286, Weights: 0.08653225898742675
NC3 Self-Duality: 0.6352279186248779
NC4 NCC Mismatch: 0.005499999999999949

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: 0.12988737225532532
Inter Cos: 0.1339970976114273
Norm Quadratic Average: 87.6878890991211
Nearest Class Center Accuracy: 0.825

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15483364462852478
Inter Cos: 0.15719261765480042
Norm Quadratic Average: 55.30624771118164
Nearest Class Center Accuracy: 0.842

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1477283388376236
Inter Cos: 0.14042969048023224
Norm Quadratic Average: 55.701568603515625
Nearest Class Center Accuracy: 0.86

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16131435334682465
Inter Cos: 0.11990230530500412
Norm Quadratic Average: 34.425479888916016
Nearest Class Center Accuracy: 0.9

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16334667801856995
Inter Cos: 0.11201509833335876
Norm Quadratic Average: 35.59265899658203
Nearest Class Center Accuracy: 0.92

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1893647313117981
Inter Cos: 0.08896759897470474
Norm Quadratic Average: 24.279075622558594
Nearest Class Center Accuracy: 0.948

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25706934928894043
Inter Cos: 0.09964422136545181
Norm Quadratic Average: 18.880216598510742
Nearest Class Center Accuracy: 0.967

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.91657257080078
Linear Weight Rank: 4031
Intra Cos: 0.4055529236793518
Inter Cos: 0.12061121314764023
Norm Quadratic Average: 116.20518493652344
Nearest Class Center Accuracy: 0.973

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.39731216430664
Linear Weight Rank: 3671
Intra Cos: 0.5290732979774475
Inter Cos: 0.13702711462974548
Norm Quadratic Average: 62.4015998840332
Nearest Class Center Accuracy: 0.975

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2718307971954346
Linear Weight Rank: 10
Intra Cos: 0.6396350860595703
Inter Cos: 0.14581745862960815
Norm Quadratic Average: 39.68400192260742
Nearest Class Center Accuracy: 0.9745

Output Layer:
Intra Cos: 0.7998120784759521
Inter Cos: 0.25769710540771484
Norm Quadratic Average: 21.371929168701172
Nearest Class Center Accuracy: 0.9735

