Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_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: 0.11311887204647064
Norm Quadratic Average: 23.53293800354004
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10135114938020706
Inter Cos: 0.11971321702003479
Norm Quadratic Average: 87.43818664550781
Nearest Class Center Accuracy: 0.83075

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14511418342590332
Inter Cos: 0.13393037021160126
Norm Quadratic Average: 54.626808166503906
Nearest Class Center Accuracy: 0.85725

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1469598263502121
Inter Cos: 0.12160700559616089
Norm Quadratic Average: 56.7680778503418
Nearest Class Center Accuracy: 0.879625

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1712692826986313
Inter Cos: 0.102786585688591
Norm Quadratic Average: 34.879093170166016
Nearest Class Center Accuracy: 0.9115

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18142952024936676
Inter Cos: 0.09167297184467316
Norm Quadratic Average: 36.1189079284668
Nearest Class Center Accuracy: 0.935875

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19631773233413696
Inter Cos: 0.11877144873142242
Norm Quadratic Average: 24.937152862548828
Nearest Class Center Accuracy: 0.971875

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.28426969051361084
Inter Cos: 0.09514924138784409
Norm Quadratic Average: 18.711835861206055
Nearest Class Center Accuracy: 0.99675

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.97356414794922
Linear Weight Rank: 4031
Intra Cos: 0.4878821074962616
Inter Cos: 0.12474416196346283
Norm Quadratic Average: 118.17095184326172
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.00032043457031
Linear Weight Rank: 3671
Intra Cos: 0.6306785345077515
Inter Cos: 0.14467254281044006
Norm Quadratic Average: 64.00576782226562
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.25646710395813
Linear Weight Rank: 10
Intra Cos: 0.7533830404281616
Inter Cos: 0.15642887353897095
Norm Quadratic Average: 40.69387435913086
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9101307988166809
Inter Cos: 0.24302738904953003
Norm Quadratic Average: 22.226821899414062
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.1101721739768982
Accuracy: 0.9735
NC1 Within Class Collapse: 1.724461555480957
NC2 Equinorm: Features: 0.05541691556572914, Weights: 0.012379787862300873
NC2 Equiangle: Features: 0.2079349093967014, Weights: 0.0889762454562717
NC3 Self-Duality: 0.6349128484725952
NC4 NCC Mismatch: 0.008000000000000007

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
Inter Cos: 0.11957791447639465
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: 0.12393523007631302
Inter Cos: 0.12811064720153809
Norm Quadratic Average: 86.28128051757812
Nearest Class Center Accuracy: 0.823

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.155509352684021
Inter Cos: 0.15158921480178833
Norm Quadratic Average: 54.09748840332031
Nearest Class Center Accuracy: 0.8495

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1490509808063507
Inter Cos: 0.13460861146450043
Norm Quadratic Average: 56.32797622680664
Nearest Class Center Accuracy: 0.8725

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16253221035003662
Inter Cos: 0.11828459054231644
Norm Quadratic Average: 34.823177337646484
Nearest Class Center Accuracy: 0.907

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1736048012971878
Inter Cos: 0.10981927812099457
Norm Quadratic Average: 36.09033203125
Nearest Class Center Accuracy: 0.9215

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19893231987953186
Inter Cos: 0.13299886882305145
Norm Quadratic Average: 24.90715789794922
Nearest Class Center Accuracy: 0.943

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2526718080043793
Inter Cos: 0.0902053639292717
Norm Quadratic Average: 18.558935165405273
Nearest Class Center Accuracy: 0.964

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.97356414794922
Linear Weight Rank: 4031
Intra Cos: 0.39879515767097473
Inter Cos: 0.1204615905880928
Norm Quadratic Average: 115.67520904541016
Nearest Class Center Accuracy: 0.971

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.00032043457031
Linear Weight Rank: 3671
Intra Cos: 0.5234476923942566
Inter Cos: 0.13976401090621948
Norm Quadratic Average: 62.27097702026367
Nearest Class Center Accuracy: 0.9715

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.25646710395813
Linear Weight Rank: 10
Intra Cos: 0.6377466917037964
Inter Cos: 0.15316340327262878
Norm Quadratic Average: 39.464725494384766
Nearest Class Center Accuracy: 0.9725

Output Layer:
Intra Cos: 0.8039209842681885
Inter Cos: 0.2363038808107376
Norm Quadratic Average: 21.441259384155273
Nearest Class Center Accuracy: 0.97

