Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_weight_decay_0.007.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: 0.12012407183647156
Inter Cos: 0.1413591057062149
Norm Quadratic Average: 43.12346649169922
Nearest Class Center Accuracy: 0.81325

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1633693426847458
Inter Cos: 0.17588315904140472
Norm Quadratic Average: 45.32959747314453
Nearest Class Center Accuracy: 0.790125

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17726297676563263
Inter Cos: 0.19129803776741028
Norm Quadratic Average: 57.21016311645508
Nearest Class Center Accuracy: 0.793125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1845782846212387
Inter Cos: 0.1916363686323166
Norm Quadratic Average: 34.72951889038086
Nearest Class Center Accuracy: 0.832

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21438664197921753
Inter Cos: 0.2152014523744583
Norm Quadratic Average: 28.058216094970703
Nearest Class Center Accuracy: 0.88125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.30809423327445984
Inter Cos: 0.20706650614738464
Norm Quadratic Average: 14.31518268585205
Nearest Class Center Accuracy: 0.9325

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4554053246974945
Inter Cos: 0.24616758525371552
Norm Quadratic Average: 9.925054550170898
Nearest Class Center Accuracy: 0.970375

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 72.46403503417969
Linear Weight Rank: 4031
Intra Cos: 0.6722011566162109
Inter Cos: 0.27606791257858276
Norm Quadratic Average: 43.7921257019043
Nearest Class Center Accuracy: 0.994875

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 29.318294525146484
Linear Weight Rank: 3670
Intra Cos: 0.7643841505050659
Inter Cos: 0.27902257442474365
Norm Quadratic Average: 29.482013702392578
Nearest Class Center Accuracy: 0.998625

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.220276355743408
Linear Weight Rank: 10
Intra Cos: 0.7950618863105774
Inter Cos: 0.26305100321769714
Norm Quadratic Average: 23.498275756835938
Nearest Class Center Accuracy: 0.998625

Output Layer:
Intra Cos: 0.8268115520477295
Inter Cos: 0.32821571826934814
Norm Quadratic Average: 17.678850173950195
Nearest Class Center Accuracy: 0.997875

Test Set:
Average Loss: 0.06664155507087707
Accuracy: 0.9785
NC1 Within Class Collapse: 2.2770800590515137
NC2 Equinorm: Features: 0.1003996953368187, Weights: 0.022306527942419052
NC2 Equiangle: Features: 0.2648888481987847, Weights: 0.11393841637505425
NC3 Self-Duality: 0.36302560567855835
NC4 NCC Mismatch: 0.01100000000000001

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: 0.13600614666938782
Inter Cos: 0.15480321645736694
Norm Quadratic Average: 41.797122955322266
Nearest Class Center Accuracy: 0.8075

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16752195358276367
Inter Cos: 0.20405083894729614
Norm Quadratic Average: 43.97975158691406
Nearest Class Center Accuracy: 0.789

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1774110645055771
Inter Cos: 0.23177823424339294
Norm Quadratic Average: 55.39370346069336
Nearest Class Center Accuracy: 0.794

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1661585420370102
Inter Cos: 0.23114250600337982
Norm Quadratic Average: 33.70520782470703
Nearest Class Center Accuracy: 0.826

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19318577647209167
Inter Cos: 0.25219544768333435
Norm Quadratic Average: 27.287538528442383
Nearest Class Center Accuracy: 0.8715

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2736585736274719
Inter Cos: 0.24435842037200928
Norm Quadratic Average: 13.874894142150879
Nearest Class Center Accuracy: 0.9295

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4039354622364044
Inter Cos: 0.2793678939342499
Norm Quadratic Average: 9.56788158416748
Nearest Class Center Accuracy: 0.9525

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 72.46403503417969
Linear Weight Rank: 4031
Intra Cos: 0.6039732694625854
Inter Cos: 0.3134428858757019
Norm Quadratic Average: 41.99954605102539
Nearest Class Center Accuracy: 0.9655

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 29.318294525146484
Linear Weight Rank: 3670
Intra Cos: 0.6959850192070007
Inter Cos: 0.3028278052806854
Norm Quadratic Average: 28.24261474609375
Nearest Class Center Accuracy: 0.975

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.220276355743408
Linear Weight Rank: 10
Intra Cos: 0.725344717502594
Inter Cos: 0.27414748072624207
Norm Quadratic Average: 22.512765884399414
Nearest Class Center Accuracy: 0.976

Output Layer:
Intra Cos: 0.752184271812439
Inter Cos: 0.2946408689022064
Norm Quadratic Average: 16.911035537719727
Nearest Class Center Accuracy: 0.974

