Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_weight_decay_0.02.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: 23.532934188842773
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1191297173500061
Inter Cos: 0.14817850291728973
Norm Quadratic Average: 40.2607421875
Nearest Class Center Accuracy: 0.805625

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14781774580478668
Inter Cos: 0.18165487051010132
Norm Quadratic Average: 48.551273345947266
Nearest Class Center Accuracy: 0.7715

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1573508083820343
Inter Cos: 0.20238257944583893
Norm Quadratic Average: 64.9109878540039
Nearest Class Center Accuracy: 0.76925

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1790151745080948
Inter Cos: 0.21659938991069794
Norm Quadratic Average: 39.82671356201172
Nearest Class Center Accuracy: 0.79825

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2167009711265564
Inter Cos: 0.25506895780563354
Norm Quadratic Average: 28.074247360229492
Nearest Class Center Accuracy: 0.8525

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3017347753047943
Inter Cos: 0.2788907289505005
Norm Quadratic Average: 14.110860824584961
Nearest Class Center Accuracy: 0.90825

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.44111549854278564
Inter Cos: 0.31932908296585083
Norm Quadratic Average: 8.725090980529785
Nearest Class Center Accuracy: 0.954625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.817169189453125
Linear Weight Rank: 4031
Intra Cos: 0.590697705745697
Inter Cos: 0.31969723105430603
Norm Quadratic Average: 38.25547790527344
Nearest Class Center Accuracy: 0.976125

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 15.767196655273438
Linear Weight Rank: 3669
Intra Cos: 0.6722924113273621
Inter Cos: 0.31286412477493286
Norm Quadratic Average: 25.961458206176758
Nearest Class Center Accuracy: 0.98075

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9487522840499878
Linear Weight Rank: 10
Intra Cos: 0.7003920674324036
Inter Cos: 0.29460591077804565
Norm Quadratic Average: 19.374372482299805
Nearest Class Center Accuracy: 0.9805

Output Layer:
Intra Cos: 0.7379592061042786
Inter Cos: 0.3390367925167084
Norm Quadratic Average: 14.820277214050293
Nearest Class Center Accuracy: 0.980875

Test Set:
Average Loss: 0.10343385982513428
Accuracy: 0.9665
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.15681909024715424, Weights: 0.03307129442691803
NC2 Equiangle: Features: 0.2966480678982205, Weights: 0.16837402979532878
NC3 Self-Duality: 0.23933987319469452
NC4 NCC Mismatch: 0.027000000000000024

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: 0.1421370655298233
Inter Cos: 0.16765683889389038
Norm Quadratic Average: 38.92526626586914
Nearest Class Center Accuracy: 0.804

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1633661687374115
Inter Cos: 0.21483860909938812
Norm Quadratic Average: 47.021575927734375
Nearest Class Center Accuracy: 0.7755

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1758287400007248
Inter Cos: 0.24202068150043488
Norm Quadratic Average: 62.78178787231445
Nearest Class Center Accuracy: 0.7655

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15946237742900848
Inter Cos: 0.2513105273246765
Norm Quadratic Average: 38.602821350097656
Nearest Class Center Accuracy: 0.805

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1903335303068161
Inter Cos: 0.290004700422287
Norm Quadratic Average: 27.243099212646484
Nearest Class Center Accuracy: 0.8475

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.26817455887794495
Inter Cos: 0.2581595182418823
Norm Quadratic Average: 13.627723693847656
Nearest Class Center Accuracy: 0.9

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3916413486003876
Inter Cos: 0.3061935603618622
Norm Quadratic Average: 8.414859771728516
Nearest Class Center Accuracy: 0.9365

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.817169189453125
Linear Weight Rank: 4031
Intra Cos: 0.5232378840446472
Inter Cos: 0.34914618730545044
Norm Quadratic Average: 36.89850997924805
Nearest Class Center Accuracy: 0.949

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 15.767196655273438
Linear Weight Rank: 3669
Intra Cos: 0.5908975601196289
Inter Cos: 0.3535052239894867
Norm Quadratic Average: 25.034650802612305
Nearest Class Center Accuracy: 0.9575

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9487522840499878
Linear Weight Rank: 10
Intra Cos: 0.6106047034263611
Inter Cos: 0.33757925033569336
Norm Quadratic Average: 18.69224739074707
Nearest Class Center Accuracy: 0.9585

Output Layer:
Intra Cos: 0.6355240345001221
Inter Cos: 0.36620599031448364
Norm Quadratic Average: 14.268620491027832
Nearest Class Center Accuracy: 0.958

