Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_weight_decay_0.005.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: 23.53293800354004
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1047271192073822
Inter Cos: 0.11946820467710495
Norm Quadratic Average: 68.20018005371094
Nearest Class Center Accuracy: 0.82925

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14355263113975525
Inter Cos: 0.1361231803894043
Norm Quadratic Average: 45.14231872558594
Nearest Class Center Accuracy: 0.84625

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13945695757865906
Inter Cos: 0.1286662071943283
Norm Quadratic Average: 45.46767044067383
Nearest Class Center Accuracy: 0.868375

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16354236006736755
Inter Cos: 0.11374881118535995
Norm Quadratic Average: 27.607830047607422
Nearest Class Center Accuracy: 0.91525

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17237333953380585
Inter Cos: 0.1028704047203064
Norm Quadratic Average: 28.73605728149414
Nearest Class Center Accuracy: 0.941375

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19622038304805756
Inter Cos: 0.10415295511484146
Norm Quadratic Average: 19.46904754638672
Nearest Class Center Accuracy: 0.980875

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3118637502193451
Inter Cos: 0.09889453649520874
Norm Quadratic Average: 15.230584144592285
Nearest Class Center Accuracy: 0.997875

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.75019836425781
Linear Weight Rank: 4031
Intra Cos: 0.5530261993408203
Inter Cos: 0.11933673173189163
Norm Quadratic Average: 100.85186767578125
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.22850036621094
Linear Weight Rank: 3670
Intra Cos: 0.711154580116272
Inter Cos: 0.141773521900177
Norm Quadratic Average: 49.550880432128906
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9264695644378662
Linear Weight Rank: 10
Intra Cos: 0.8150802254676819
Inter Cos: 0.16359096765518188
Norm Quadratic Average: 29.24976348876953
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9084344506263733
Inter Cos: 0.22034986317157745
Norm Quadratic Average: 14.862546920776367
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.08607412871718406
Accuracy: 0.975
NC1 Within Class Collapse: 1.5608723163604736
NC2 Equinorm: Features: 0.059418510645627975, Weights: 0.012847984209656715
NC2 Equiangle: Features: 0.19455788930257162, Weights: 0.07992615169949002
NC3 Self-Duality: 0.5217981338500977
NC4 NCC Mismatch: 0.0044999999999999485

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: 22.824302673339844
Nearest Class Center Accuracy: 0.809

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12720631062984467
Inter Cos: 0.13461849093437195
Norm Quadratic Average: 67.35307312011719
Nearest Class Center Accuracy: 0.821

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15636226534843445
Inter Cos: 0.15493431687355042
Norm Quadratic Average: 44.80721664428711
Nearest Class Center Accuracy: 0.842

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14576083421707153
Inter Cos: 0.13894549012184143
Norm Quadratic Average: 45.103553771972656
Nearest Class Center Accuracy: 0.8675

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15704111754894257
Inter Cos: 0.12372011691331863
Norm Quadratic Average: 27.517404556274414
Nearest Class Center Accuracy: 0.9075

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1637306660413742
Inter Cos: 0.1164243221282959
Norm Quadratic Average: 28.675838470458984
Nearest Class Center Accuracy: 0.9305

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19907782971858978
Inter Cos: 0.12144500762224197
Norm Quadratic Average: 19.381078720092773
Nearest Class Center Accuracy: 0.9565

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2818964123725891
Inter Cos: 0.11177655309438705
Norm Quadratic Average: 15.083185195922852
Nearest Class Center Accuracy: 0.971

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.75019836425781
Linear Weight Rank: 4031
Intra Cos: 0.4604339003562927
Inter Cos: 0.1436808705329895
Norm Quadratic Average: 98.31964874267578
Nearest Class Center Accuracy: 0.9725

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.22850036621094
Linear Weight Rank: 3670
Intra Cos: 0.5911171436309814
Inter Cos: 0.1492060422897339
Norm Quadratic Average: 47.96019744873047
Nearest Class Center Accuracy: 0.974

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9264695644378662
Linear Weight Rank: 10
Intra Cos: 0.689024031162262
Inter Cos: 0.1728232204914093
Norm Quadratic Average: 28.222145080566406
Nearest Class Center Accuracy: 0.9735

Output Layer:
Intra Cos: 0.7830563187599182
Inter Cos: 0.2592211365699768
Norm Quadratic Average: 14.290306091308594
Nearest Class Center Accuracy: 0.9725

