Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_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: 0.11311887204647064
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: 0.11144072562456131
Inter Cos: 0.1352735161781311
Norm Quadratic Average: 46.38246536254883
Nearest Class Center Accuracy: 0.8185

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14758001267910004
Inter Cos: 0.16859187185764313
Norm Quadratic Average: 47.11722183227539
Nearest Class Center Accuracy: 0.803125

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1608717441558838
Inter Cos: 0.18571914732456207
Norm Quadratic Average: 63.23372268676758
Nearest Class Center Accuracy: 0.81325

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19470034539699554
Inter Cos: 0.19084040820598602
Norm Quadratic Average: 40.54397964477539
Nearest Class Center Accuracy: 0.850375

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22598865628242493
Inter Cos: 0.20738637447357178
Norm Quadratic Average: 40.17015838623047
Nearest Class Center Accuracy: 0.886625

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2762119770050049
Inter Cos: 0.18178735673427582
Norm Quadratic Average: 23.808908462524414
Nearest Class Center Accuracy: 0.93275

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.39805248379707336
Inter Cos: 0.20973584055900574
Norm Quadratic Average: 18.509552001953125
Nearest Class Center Accuracy: 0.975125

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.89517974853516
Linear Weight Rank: 4031
Intra Cos: 0.6204041242599487
Inter Cos: 0.23377351462841034
Norm Quadratic Average: 81.4137954711914
Nearest Class Center Accuracy: 0.997875

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.78433609008789
Linear Weight Rank: 3670
Intra Cos: 0.723796010017395
Inter Cos: 0.2552254796028137
Norm Quadratic Average: 52.88201904296875
Nearest Class Center Accuracy: 0.9995

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.5186755657196045
Linear Weight Rank: 10
Intra Cos: 0.7785861492156982
Inter Cos: 0.2761121094226837
Norm Quadratic Average: 41.51844787597656
Nearest Class Center Accuracy: 0.99975

Output Layer:
Intra Cos: 0.8256657719612122
Inter Cos: 0.4086422920227051
Norm Quadratic Average: 30.27947425842285
Nearest Class Center Accuracy: 0.999875

Test Set:
Average Loss: 0.09263968318700791
Accuracy: 0.981
NC1 Within Class Collapse: 1.732520580291748
NC2 Equinorm: Features: 0.12086853384971619, Weights: 0.013259528204798698
NC2 Equiangle: Features: 0.23591702779134113, Weights: 0.09392280578613281
NC3 Self-Duality: 0.5541292428970337
NC4 NCC Mismatch: 0.011499999999999955

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: 0.13491052389144897
Inter Cos: 0.150302916765213
Norm Quadratic Average: 45.223323822021484
Nearest Class Center Accuracy: 0.813

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17053256928920746
Inter Cos: 0.19743581116199493
Norm Quadratic Average: 46.00071716308594
Nearest Class Center Accuracy: 0.7965

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18041136860847473
Inter Cos: 0.22178146243095398
Norm Quadratic Average: 61.64553451538086
Nearest Class Center Accuracy: 0.817

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17210529744625092
Inter Cos: 0.22429494559764862
Norm Quadratic Average: 39.63285827636719
Nearest Class Center Accuracy: 0.8495

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19410666823387146
Inter Cos: 0.2404375523328781
Norm Quadratic Average: 39.26585006713867
Nearest Class Center Accuracy: 0.881

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24248693883419037
Inter Cos: 0.2095111757516861
Norm Quadratic Average: 23.270038604736328
Nearest Class Center Accuracy: 0.9265

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3473846912384033
Inter Cos: 0.24307656288146973
Norm Quadratic Average: 18.024564743041992
Nearest Class Center Accuracy: 0.954

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.89517974853516
Linear Weight Rank: 4031
Intra Cos: 0.5486129522323608
Inter Cos: 0.2727873623371124
Norm Quadratic Average: 78.9175796508789
Nearest Class Center Accuracy: 0.9735

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.78433609008789
Linear Weight Rank: 3670
Intra Cos: 0.6426821947097778
Inter Cos: 0.2770560085773468
Norm Quadratic Average: 51.14913558959961
Nearest Class Center Accuracy: 0.977

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.5186755657196045
Linear Weight Rank: 10
Intra Cos: 0.6901547908782959
Inter Cos: 0.30994680523872375
Norm Quadratic Average: 40.2119140625
Nearest Class Center Accuracy: 0.974

Output Layer:
Intra Cos: 0.7245164513587952
Inter Cos: 0.4374501407146454
Norm Quadratic Average: 29.306676864624023
Nearest Class Center Accuracy: 0.969

