Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_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: 0.11311887949705124
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: 0.11796526610851288
Inter Cos: 0.13717719912528992
Norm Quadratic Average: 48.28604507446289
Nearest Class Center Accuracy: 0.817625

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16336357593536377
Inter Cos: 0.16892492771148682
Norm Quadratic Average: 47.19731521606445
Nearest Class Center Accuracy: 0.80475

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1779002994298935
Inter Cos: 0.18307705223560333
Norm Quadratic Average: 62.444522857666016
Nearest Class Center Accuracy: 0.819125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18735899031162262
Inter Cos: 0.1782619208097458
Norm Quadratic Average: 40.869667053222656
Nearest Class Center Accuracy: 0.859875

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2125457227230072
Inter Cos: 0.18628071248531342
Norm Quadratic Average: 40.02233123779297
Nearest Class Center Accuracy: 0.900125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.29069510102272034
Inter Cos: 0.17053119838237762
Norm Quadratic Average: 23.580612182617188
Nearest Class Center Accuracy: 0.94175

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.41199833154678345
Inter Cos: 0.20797191560268402
Norm Quadratic Average: 18.76764488220215
Nearest Class Center Accuracy: 0.9755

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.89423370361328
Linear Weight Rank: 4031
Intra Cos: 0.6420126557350159
Inter Cos: 0.24169562757015228
Norm Quadratic Average: 82.91063690185547
Nearest Class Center Accuracy: 0.998125

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.787933349609375
Linear Weight Rank: 3671
Intra Cos: 0.7475032806396484
Inter Cos: 0.26022836565971375
Norm Quadratic Average: 53.378841400146484
Nearest Class Center Accuracy: 0.999875

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.518226385116577
Linear Weight Rank: 10
Intra Cos: 0.7998008131980896
Inter Cos: 0.25337210297584534
Norm Quadratic Average: 41.59181213378906
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.8519313931465149
Inter Cos: 0.360315203666687
Norm Quadratic Average: 29.948238372802734
Nearest Class Center Accuracy: 0.999875

Test Set:
Average Loss: 0.08354560924321414
Accuracy: 0.9815
NC1 Within Class Collapse: 1.7221012115478516
NC2 Equinorm: Features: 0.0936344638466835, Weights: 0.009440645575523376
NC2 Equiangle: Features: 0.23906440734863282, Weights: 0.09406052695380317
NC3 Self-Duality: 0.5490010380744934
NC4 NCC Mismatch: 0.010499999999999954

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: 0.13276639580726624
Inter Cos: 0.1484682410955429
Norm Quadratic Average: 46.9093017578125
Nearest Class Center Accuracy: 0.8105

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1674753576517105
Inter Cos: 0.1929333359003067
Norm Quadratic Average: 45.9255485534668
Nearest Class Center Accuracy: 0.7995

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1733734905719757
Inter Cos: 0.21506904065608978
Norm Quadratic Average: 60.64596176147461
Nearest Class Center Accuracy: 0.817

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1689816117286682
Inter Cos: 0.20680521428585052
Norm Quadratic Average: 39.81162643432617
Nearest Class Center Accuracy: 0.852

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1899249106645584
Inter Cos: 0.2206912636756897
Norm Quadratic Average: 39.030906677246094
Nearest Class Center Accuracy: 0.8855

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25440216064453125
Inter Cos: 0.19961325824260712
Norm Quadratic Average: 22.9010066986084
Nearest Class Center Accuracy: 0.933

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3617710471153259
Inter Cos: 0.21268261969089508
Norm Quadratic Average: 18.10173988342285
Nearest Class Center Accuracy: 0.956

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.89423370361328
Linear Weight Rank: 4031
Intra Cos: 0.5711760520935059
Inter Cos: 0.24778100848197937
Norm Quadratic Average: 79.3494644165039
Nearest Class Center Accuracy: 0.9685

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.787933349609375
Linear Weight Rank: 3671
Intra Cos: 0.6751831769943237
Inter Cos: 0.2588317096233368
Norm Quadratic Average: 50.999874114990234
Nearest Class Center Accuracy: 0.9755

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.518226385116577
Linear Weight Rank: 10
Intra Cos: 0.7254296541213989
Inter Cos: 0.2838926911354065
Norm Quadratic Average: 39.74614334106445
Nearest Class Center Accuracy: 0.977

Output Layer:
Intra Cos: 0.7727329134941101
Inter Cos: 0.36994847655296326
Norm Quadratic Average: 28.603614807128906
Nearest Class Center Accuracy: 0.976

