Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_weight_decay_0.003.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: 23.532934188842773
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1125975176692009
Inter Cos: 0.13719899952411652
Norm Quadratic Average: 43.741058349609375
Nearest Class Center Accuracy: 0.8165

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14826877415180206
Inter Cos: 0.17178761959075928
Norm Quadratic Average: 44.74070739746094
Nearest Class Center Accuracy: 0.796

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16098883748054504
Inter Cos: 0.190787211060524
Norm Quadratic Average: 57.68292999267578
Nearest Class Center Accuracy: 0.80475

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1958712935447693
Inter Cos: 0.19805526733398438
Norm Quadratic Average: 35.36551284790039
Nearest Class Center Accuracy: 0.839

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22854234278202057
Inter Cos: 0.2173936367034912
Norm Quadratic Average: 32.1193962097168
Nearest Class Center Accuracy: 0.87875

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2823021411895752
Inter Cos: 0.1974249631166458
Norm Quadratic Average: 17.755857467651367
Nearest Class Center Accuracy: 0.924375

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4143015742301941
Inter Cos: 0.23350703716278076
Norm Quadratic Average: 12.867938995361328
Nearest Class Center Accuracy: 0.971125

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.79495239257812
Linear Weight Rank: 4031
Intra Cos: 0.6450891494750977
Inter Cos: 0.25846049189567566
Norm Quadratic Average: 55.89842987060547
Nearest Class Center Accuracy: 0.99675

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.497314453125
Linear Weight Rank: 3670
Intra Cos: 0.745718777179718
Inter Cos: 0.2638697922229767
Norm Quadratic Average: 36.8049201965332
Nearest Class Center Accuracy: 0.9995

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.3495168685913086
Linear Weight Rank: 10
Intra Cos: 0.7856035828590393
Inter Cos: 0.26044777035713196
Norm Quadratic Average: 29.17585563659668
Nearest Class Center Accuracy: 0.9995

Output Layer:
Intra Cos: 0.8150807619094849
Inter Cos: 0.3619615137577057
Norm Quadratic Average: 21.514751434326172
Nearest Class Center Accuracy: 0.99925

Test Set:
Average Loss: 0.07377632933855056
Accuracy: 0.978
NC1 Within Class Collapse: 1.8827440738677979
NC2 Equinorm: Features: 0.1235433965921402, Weights: 0.014445210807025433
NC2 Equiangle: Features: 0.24799715677897136, Weights: 0.10122516420152453
NC3 Self-Duality: 0.47106942534446716
NC4 NCC Mismatch: 0.010499999999999954

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: 0.13617616891860962
Inter Cos: 0.1528661698102951
Norm Quadratic Average: 42.5932731628418
Nearest Class Center Accuracy: 0.81

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17078901827335358
Inter Cos: 0.20189788937568665
Norm Quadratic Average: 43.61748123168945
Nearest Class Center Accuracy: 0.794

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1827104687690735
Inter Cos: 0.22814571857452393
Norm Quadratic Average: 56.15514373779297
Nearest Class Center Accuracy: 0.805

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.174844890832901
Inter Cos: 0.23245403170585632
Norm Quadratic Average: 34.54299545288086
Nearest Class Center Accuracy: 0.838

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1975477933883667
Inter Cos: 0.25176262855529785
Norm Quadratic Average: 31.380826950073242
Nearest Class Center Accuracy: 0.868

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24870850145816803
Inter Cos: 0.22572696208953857
Norm Quadratic Average: 17.33894157409668
Nearest Class Center Accuracy: 0.9205

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3643728792667389
Inter Cos: 0.2682989835739136
Norm Quadratic Average: 12.530714988708496
Nearest Class Center Accuracy: 0.954

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.79495239257812
Linear Weight Rank: 4031
Intra Cos: 0.5734291076660156
Inter Cos: 0.300995409488678
Norm Quadratic Average: 54.23644256591797
Nearest Class Center Accuracy: 0.9705

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.497314453125
Linear Weight Rank: 3670
Intra Cos: 0.6640030145645142
Inter Cos: 0.29897794127464294
Norm Quadratic Average: 35.62334060668945
Nearest Class Center Accuracy: 0.975

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.3495168685913086
Linear Weight Rank: 10
Intra Cos: 0.6979015469551086
Inter Cos: 0.29091668128967285
Norm Quadratic Average: 28.279544830322266
Nearest Class Center Accuracy: 0.974

Output Layer:
Intra Cos: 0.7173189520835876
Inter Cos: 0.3867533802986145
Norm Quadratic Average: 20.833385467529297
Nearest Class Center Accuracy: 0.969

