Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_weight_decay_0.0005.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: 0.11806503683328629
Inter Cos: 0.13733823597431183
Norm Quadratic Average: 47.68703079223633
Nearest Class Center Accuracy: 0.817625

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1636488139629364
Inter Cos: 0.16928939521312714
Norm Quadratic Average: 46.58249282836914
Nearest Class Center Accuracy: 0.804

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17814643681049347
Inter Cos: 0.18329282104969025
Norm Quadratic Average: 61.46078872680664
Nearest Class Center Accuracy: 0.81675

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18799670040607452
Inter Cos: 0.17491267621517181
Norm Quadratic Average: 40.135292053222656
Nearest Class Center Accuracy: 0.85675

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21271584928035736
Inter Cos: 0.18671366572380066
Norm Quadratic Average: 38.625003814697266
Nearest Class Center Accuracy: 0.897875

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2912118434906006
Inter Cos: 0.1749970018863678
Norm Quadratic Average: 22.470483779907227
Nearest Class Center Accuracy: 0.940125

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.413234680891037
Inter Cos: 0.206438347697258
Norm Quadratic Average: 17.724740982055664
Nearest Class Center Accuracy: 0.975625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.97734832763672
Linear Weight Rank: 4031
Intra Cos: 0.6438082456588745
Inter Cos: 0.23631852865219116
Norm Quadratic Average: 77.91207122802734
Nearest Class Center Accuracy: 0.997625

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.01382064819336
Linear Weight Rank: 3671
Intra Cos: 0.7503952980041504
Inter Cos: 0.2583155930042267
Norm Quadratic Average: 50.450714111328125
Nearest Class Center Accuracy: 0.999875

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.4859695434570312
Linear Weight Rank: 10
Intra Cos: 0.8001351356506348
Inter Cos: 0.2701355218887329
Norm Quadratic Average: 39.33326721191406
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.8498387932777405
Inter Cos: 0.37987610697746277
Norm Quadratic Average: 28.289888381958008
Nearest Class Center Accuracy: 0.99975

Test Set:
Average Loss: 0.08067828749120236
Accuracy: 0.9795
NC1 Within Class Collapse: 1.7470393180847168
NC2 Equinorm: Features: 0.09204789251089096, Weights: 0.009921587072312832
NC2 Equiangle: Features: 0.24171691470676, Weights: 0.09579481548733182
NC3 Self-Duality: 0.5380378365516663
NC4 NCC Mismatch: 0.01200000000000001

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: 0.13289837539196014
Inter Cos: 0.1486809402704239
Norm Quadratic Average: 46.32417678833008
Nearest Class Center Accuracy: 0.811

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16732139885425568
Inter Cos: 0.1938297152519226
Norm Quadratic Average: 45.3210563659668
Nearest Class Center Accuracy: 0.7985

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17358431220054626
Inter Cos: 0.21553246676921844
Norm Quadratic Average: 59.68227767944336
Nearest Class Center Accuracy: 0.814

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1699623018503189
Inter Cos: 0.20741812884807587
Norm Quadratic Average: 39.09339904785156
Nearest Class Center Accuracy: 0.847

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19207368791103363
Inter Cos: 0.22132015228271484
Norm Quadratic Average: 37.67961883544922
Nearest Class Center Accuracy: 0.8835

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2562885880470276
Inter Cos: 0.1989240050315857
Norm Quadratic Average: 21.84048080444336
Nearest Class Center Accuracy: 0.929

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3642941415309906
Inter Cos: 0.21406111121177673
Norm Quadratic Average: 17.116039276123047
Nearest Class Center Accuracy: 0.956

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.97734832763672
Linear Weight Rank: 4031
Intra Cos: 0.5746341943740845
Inter Cos: 0.2464403361082077
Norm Quadratic Average: 74.6138916015625
Nearest Class Center Accuracy: 0.968

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.01382064819336
Linear Weight Rank: 3671
Intra Cos: 0.680704653263092
Inter Cos: 0.2551827132701874
Norm Quadratic Average: 48.2015495300293
Nearest Class Center Accuracy: 0.975

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.4859695434570312
Linear Weight Rank: 10
Intra Cos: 0.7285640239715576
Inter Cos: 0.2733733355998993
Norm Quadratic Average: 37.58263397216797
Nearest Class Center Accuracy: 0.977

Output Layer:
Intra Cos: 0.7734028100967407
Inter Cos: 0.3546459376811981
Norm Quadratic Average: 27.01202392578125
Nearest Class Center Accuracy: 0.977

