Model save path: ./New_Models/bn_True_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: 0.11311888694763184
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: 0.10203775018453598
Inter Cos: 0.12098703533411026
Norm Quadratic Average: 59.21718978881836
Nearest Class Center Accuracy: 0.838625

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1505925953388214
Inter Cos: 0.14201338589191437
Norm Quadratic Average: 42.00273895263672
Nearest Class Center Accuracy: 0.859125

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14805732667446136
Inter Cos: 0.1322893649339676
Norm Quadratic Average: 41.98345947265625
Nearest Class Center Accuracy: 0.874375

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17657552659511566
Inter Cos: 0.11310280859470367
Norm Quadratic Average: 25.24376678466797
Nearest Class Center Accuracy: 0.916

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19246071577072144
Inter Cos: 0.1019134595990181
Norm Quadratic Average: 25.76399803161621
Nearest Class Center Accuracy: 0.94625

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2313574105501175
Inter Cos: 0.13187411427497864
Norm Quadratic Average: 17.53877067565918
Nearest Class Center Accuracy: 0.983625

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3410780429840088
Inter Cos: 0.10308177024126053
Norm Quadratic Average: 13.674437522888184
Nearest Class Center Accuracy: 0.99875

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 72.46099853515625
Linear Weight Rank: 4031
Intra Cos: 0.5974785685539246
Inter Cos: 0.13912291824817657
Norm Quadratic Average: 95.128173828125
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 29.292049407958984
Linear Weight Rank: 3670
Intra Cos: 0.7625356912612915
Inter Cos: 0.1609683483839035
Norm Quadratic Average: 45.78913879394531
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.8251047134399414
Linear Weight Rank: 10
Intra Cos: 0.8569735884666443
Inter Cos: 0.1595558524131775
Norm Quadratic Average: 26.71289825439453
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9270640015602112
Inter Cos: 0.19880551099777222
Norm Quadratic Average: 13.652610778808594
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.06428644466400146
Accuracy: 0.982
NC1 Within Class Collapse: 1.4306492805480957
NC2 Equinorm: Features: 0.04881145805120468, Weights: 0.013897127471864223
NC2 Equiangle: Features: 0.20130123562282987, Weights: 0.08038260142008463
NC3 Self-Duality: 0.45759308338165283
NC4 NCC Mismatch: 0.0034999999999999476

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
Inter Cos: 0.11957792937755585
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: 0.12079320102930069
Inter Cos: 0.12544797360897064
Norm Quadratic Average: 58.56262969970703
Nearest Class Center Accuracy: 0.8325

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1486683338880539
Inter Cos: 0.14833219349384308
Norm Quadratic Average: 41.749778747558594
Nearest Class Center Accuracy: 0.847

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14957323670387268
Inter Cos: 0.1356067657470703
Norm Quadratic Average: 41.7296142578125
Nearest Class Center Accuracy: 0.867

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16577114164829254
Inter Cos: 0.11756881326436996
Norm Quadratic Average: 25.166872024536133
Nearest Class Center Accuracy: 0.9075

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1802370399236679
Inter Cos: 0.10828176885843277
Norm Quadratic Average: 25.71902084350586
Nearest Class Center Accuracy: 0.9355

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21914470195770264
Inter Cos: 0.132898211479187
Norm Quadratic Average: 17.49628448486328
Nearest Class Center Accuracy: 0.9605

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.31061851978302
Inter Cos: 0.10088889300823212
Norm Quadratic Average: 13.559305191040039
Nearest Class Center Accuracy: 0.978

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 72.46099853515625
Linear Weight Rank: 4031
Intra Cos: 0.512240469455719
Inter Cos: 0.14384865760803223
Norm Quadratic Average: 92.74874877929688
Nearest Class Center Accuracy: 0.981

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 29.292049407958984
Linear Weight Rank: 3670
Intra Cos: 0.654915988445282
Inter Cos: 0.17255201935768127
Norm Quadratic Average: 44.36000061035156
Nearest Class Center Accuracy: 0.981

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.8251047134399414
Linear Weight Rank: 10
Intra Cos: 0.7480767369270325
Inter Cos: 0.1770818680524826
Norm Quadratic Average: 25.824979782104492
Nearest Class Center Accuracy: 0.98

Output Layer:
Intra Cos: 0.8241850137710571
Inter Cos: 0.2067023068666458
Norm Quadratic Average: 13.165989875793457
Nearest Class Center Accuracy: 0.979

