Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_weight_decay_0.0001.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: 0.11311887949705124
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: 0.09934301674365997
Inter Cos: 0.12072869390249252
Norm Quadratic Average: 87.81538391113281
Nearest Class Center Accuracy: 0.83025

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13967980444431305
Inter Cos: 0.12974295020103455
Norm Quadratic Average: 57.535221099853516
Nearest Class Center Accuracy: 0.84475

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1361335963010788
Inter Cos: 0.11906016618013382
Norm Quadratic Average: 55.87055969238281
Nearest Class Center Accuracy: 0.864625

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1630406379699707
Inter Cos: 0.10029414296150208
Norm Quadratic Average: 34.40492248535156
Nearest Class Center Accuracy: 0.908125

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17573852837085724
Inter Cos: 0.08255855739116669
Norm Quadratic Average: 35.754127502441406
Nearest Class Center Accuracy: 0.932

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18434061110019684
Inter Cos: 0.10254162549972534
Norm Quadratic Average: 24.5591983795166
Nearest Class Center Accuracy: 0.973

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2671273946762085
Inter Cos: 0.09883007407188416
Norm Quadratic Average: 19.080289840698242
Nearest Class Center Accuracy: 0.996

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.8961410522461
Linear Weight Rank: 4031
Intra Cos: 0.46497809886932373
Inter Cos: 0.13470248878002167
Norm Quadratic Average: 119.75186157226562
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.78998565673828
Linear Weight Rank: 3671
Intra Cos: 0.622167706489563
Inter Cos: 0.17607766389846802
Norm Quadratic Average: 65.46674346923828
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2883036136627197
Linear Weight Rank: 10
Intra Cos: 0.7554782032966614
Inter Cos: 0.20223554968833923
Norm Quadratic Average: 42.256324768066406
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.90791916847229
Inter Cos: 0.2647877633571625
Norm Quadratic Average: 23.219707489013672
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.10657871270179749
Accuracy: 0.9765
NC1 Within Class Collapse: 1.644472599029541
NC2 Equinorm: Features: 0.06465711444616318, Weights: 0.012955645099282265
NC2 Equiangle: Features: 0.21383283403184677, Weights: 0.08851650026109484
NC3 Self-Duality: 0.6498749852180481
NC4 NCC Mismatch: 0.005499999999999949

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133805871009827
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: 0.12469207495450974
Inter Cos: 0.1320573091506958
Norm Quadratic Average: 86.73626708984375
Nearest Class Center Accuracy: 0.8245

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15431350469589233
Inter Cos: 0.15305660665035248
Norm Quadratic Average: 57.13991165161133
Nearest Class Center Accuracy: 0.8385

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15496055781841278
Inter Cos: 0.14056938886642456
Norm Quadratic Average: 55.4838752746582
Nearest Class Center Accuracy: 0.858

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17124103009700775
Inter Cos: 0.11309945583343506
Norm Quadratic Average: 34.29994583129883
Nearest Class Center Accuracy: 0.8995

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17428945004940033
Inter Cos: 0.10007532685995102
Norm Quadratic Average: 35.80794143676758
Nearest Class Center Accuracy: 0.9245

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.188712939620018
Inter Cos: 0.10587989538908005
Norm Quadratic Average: 24.59962272644043
Nearest Class Center Accuracy: 0.9475

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.26168569922447205
Inter Cos: 0.10738836228847504
Norm Quadratic Average: 19.02815818786621
Nearest Class Center Accuracy: 0.9665

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.8961410522461
Linear Weight Rank: 4031
Intra Cos: 0.4074578583240509
Inter Cos: 0.14654648303985596
Norm Quadratic Average: 117.6884536743164
Nearest Class Center Accuracy: 0.9745

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.78998565673828
Linear Weight Rank: 3671
Intra Cos: 0.5246527791023254
Inter Cos: 0.18974275887012482
Norm Quadratic Average: 63.98146057128906
Nearest Class Center Accuracy: 0.975

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2883036136627197
Linear Weight Rank: 10
Intra Cos: 0.6364627480506897
Inter Cos: 0.22100397944450378
Norm Quadratic Average: 41.107303619384766
Nearest Class Center Accuracy: 0.9745

Output Layer:
Intra Cos: 0.7868694067001343
Inter Cos: 0.28675660490989685
Norm Quadratic Average: 22.45903205871582
Nearest Class Center Accuracy: 0.9725

