Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_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: 0.08946066349744797
Inter Cos: 0.11311887949705124
Norm Quadratic Average: 23.532936096191406
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10101714730262756
Inter Cos: 0.1176196038722992
Norm Quadratic Average: 90.35570526123047
Nearest Class Center Accuracy: 0.8365

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15046364068984985
Inter Cos: 0.1400032937526703
Norm Quadratic Average: 55.26458740234375
Nearest Class Center Accuracy: 0.85925

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15134550631046295
Inter Cos: 0.12924358248710632
Norm Quadratic Average: 57.3557014465332
Nearest Class Center Accuracy: 0.876875

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17048756778240204
Inter Cos: 0.10655319690704346
Norm Quadratic Average: 35.5733642578125
Nearest Class Center Accuracy: 0.911375

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17133723199367523
Inter Cos: 0.09007672965526581
Norm Quadratic Average: 36.53148651123047
Nearest Class Center Accuracy: 0.9365

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19991619884967804
Inter Cos: 0.08295213431119919
Norm Quadratic Average: 25.22040557861328
Nearest Class Center Accuracy: 0.975125

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2837742865085602
Inter Cos: 0.08855816721916199
Norm Quadratic Average: 19.062973022460938
Nearest Class Center Accuracy: 0.996

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.88478088378906
Linear Weight Rank: 4031
Intra Cos: 0.47432947158813477
Inter Cos: 0.10463953763246536
Norm Quadratic Average: 119.07293701171875
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.780269622802734
Linear Weight Rank: 3670
Intra Cos: 0.6141899824142456
Inter Cos: 0.11894956231117249
Norm Quadratic Average: 64.69854736328125
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.298161745071411
Linear Weight Rank: 10
Intra Cos: 0.7410828471183777
Inter Cos: 0.14241236448287964
Norm Quadratic Average: 41.2901496887207
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9062900543212891
Inter Cos: 0.2345191240310669
Norm Quadratic Average: 21.78382110595703
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.10141034090518951
Accuracy: 0.9765
NC1 Within Class Collapse: 1.7115063667297363
NC2 Equinorm: Features: 0.0514197014272213, Weights: 0.01121828518807888
NC2 Equiangle: Features: 0.1804044723510742, Weights: 0.08499799834357367
NC3 Self-Duality: 0.6487562656402588
NC4 NCC Mismatch: 0.00649999999999995

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: 0.12331879884004593
Inter Cos: 0.12782816588878632
Norm Quadratic Average: 89.38365936279297
Nearest Class Center Accuracy: 0.8325

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15402741730213165
Inter Cos: 0.16003555059432983
Norm Quadratic Average: 55.01660919189453
Nearest Class Center Accuracy: 0.8555

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14749127626419067
Inter Cos: 0.14306466281414032
Norm Quadratic Average: 57.17512130737305
Nearest Class Center Accuracy: 0.869

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16100095212459564
Inter Cos: 0.11225071549415588
Norm Quadratic Average: 35.60624313354492
Nearest Class Center Accuracy: 0.907

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16133157908916473
Inter Cos: 0.10324078798294067
Norm Quadratic Average: 36.60303497314453
Nearest Class Center Accuracy: 0.93

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18981269001960754
Inter Cos: 0.08821412175893784
Norm Quadratic Average: 25.223840713500977
Nearest Class Center Accuracy: 0.953

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2554628551006317
Inter Cos: 0.09421621263027191
Norm Quadratic Average: 18.9932861328125
Nearest Class Center Accuracy: 0.967

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.88478088378906
Linear Weight Rank: 4031
Intra Cos: 0.41154584288597107
Inter Cos: 0.10801532119512558
Norm Quadratic Average: 117.09866333007812
Nearest Class Center Accuracy: 0.9765

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.780269622802734
Linear Weight Rank: 3670
Intra Cos: 0.530106782913208
Inter Cos: 0.12743918597698212
Norm Quadratic Average: 63.2033805847168
Nearest Class Center Accuracy: 0.978

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.298161745071411
Linear Weight Rank: 10
Intra Cos: 0.6486397385597229
Inter Cos: 0.14974842965602875
Norm Quadratic Average: 40.17005920410156
Nearest Class Center Accuracy: 0.9775

Output Layer:
Intra Cos: 0.80572110414505
Inter Cos: 0.22698085010051727
Norm Quadratic Average: 21.073610305786133
Nearest Class Center Accuracy: 0.976

