Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_weight_decay_0.03.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: 23.532934188842773
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12365749478340149
Inter Cos: 0.15123620629310608
Norm Quadratic Average: 38.52078628540039
Nearest Class Center Accuracy: 0.803375

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15304149687290192
Inter Cos: 0.18461447954177856
Norm Quadratic Average: 46.39961624145508
Nearest Class Center Accuracy: 0.76175

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15997682511806488
Inter Cos: 0.19838298857212067
Norm Quadratic Average: 64.7169189453125
Nearest Class Center Accuracy: 0.7415

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16055317223072052
Inter Cos: 0.20267055928707123
Norm Quadratic Average: 43.493072509765625
Nearest Class Center Accuracy: 0.756125

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19014504551887512
Inter Cos: 0.24585089087486267
Norm Quadratic Average: 30.795007705688477
Nearest Class Center Accuracy: 0.821125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.286744624376297
Inter Cos: 0.29030513763427734
Norm Quadratic Average: 16.24632453918457
Nearest Class Center Accuracy: 0.885125

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.42002367973327637
Inter Cos: 0.34914979338645935
Norm Quadratic Average: 9.924314498901367
Nearest Class Center Accuracy: 0.933375

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 24.012798309326172
Linear Weight Rank: 4031
Intra Cos: 0.5533915162086487
Inter Cos: 0.34584930539131165
Norm Quadratic Average: 41.06109619140625
Nearest Class Center Accuracy: 0.963

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.8313627243042
Linear Weight Rank: 3669
Intra Cos: 0.6329156756401062
Inter Cos: 0.3434554636478424
Norm Quadratic Average: 26.794984817504883
Nearest Class Center Accuracy: 0.970625

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.7965446710586548
Linear Weight Rank: 10
Intra Cos: 0.6669746041297913
Inter Cos: 0.3287002146244049
Norm Quadratic Average: 18.565099716186523
Nearest Class Center Accuracy: 0.973

Output Layer:
Intra Cos: 0.7094775438308716
Inter Cos: 0.376386821269989
Norm Quadratic Average: 13.74963092803955
Nearest Class Center Accuracy: 0.972625

Test Set:
Average Loss: 0.12594195890426635
Accuracy: 0.9615
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.1704600751399994, Weights: 0.03574037179350853
NC2 Equiangle: Features: 0.3097492853800456, Weights: 0.19497449662950303
NC3 Self-Duality: 0.18609416484832764
NC4 NCC Mismatch: 0.02949999999999997

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133805871009827
Inter Cos: 0.11957792192697525
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: 0.14212435483932495
Inter Cos: 0.1698848307132721
Norm Quadratic Average: 37.11178970336914
Nearest Class Center Accuracy: 0.803

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15927278995513916
Inter Cos: 0.2161041498184204
Norm Quadratic Average: 44.71974182128906
Nearest Class Center Accuracy: 0.764

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.169321671128273
Inter Cos: 0.24248051643371582
Norm Quadratic Average: 62.18711853027344
Nearest Class Center Accuracy: 0.749

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14527295529842377
Inter Cos: 0.24010354280471802
Norm Quadratic Average: 41.92683792114258
Nearest Class Center Accuracy: 0.7695

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17586182057857513
Inter Cos: 0.2807483971118927
Norm Quadratic Average: 29.794979095458984
Nearest Class Center Accuracy: 0.823

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.26099225878715515
Inter Cos: 0.2771703898906708
Norm Quadratic Average: 15.641471862792969
Nearest Class Center Accuracy: 0.8825

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3741919696331024
Inter Cos: 0.32571864128112793
Norm Quadratic Average: 9.510648727416992
Nearest Class Center Accuracy: 0.915

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 24.012798309326172
Linear Weight Rank: 4031
Intra Cos: 0.48837822675704956
Inter Cos: 0.3201569616794586
Norm Quadratic Average: 39.35211181640625
Nearest Class Center Accuracy: 0.9415

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.8313627243042
Linear Weight Rank: 3669
Intra Cos: 0.5550544857978821
Inter Cos: 0.3282648026943207
Norm Quadratic Average: 25.68578338623047
Nearest Class Center Accuracy: 0.954

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.7965446710586548
Linear Weight Rank: 10
Intra Cos: 0.5805635452270508
Inter Cos: 0.3176899254322052
Norm Quadratic Average: 17.796390533447266
Nearest Class Center Accuracy: 0.95

Output Layer:
Intra Cos: 0.6080880761146545
Inter Cos: 0.3988531827926636
Norm Quadratic Average: 13.155762672424316
Nearest Class Center Accuracy: 0.949

