Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_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: 0.08946067094802856
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: 0.10211402177810669
Inter Cos: 0.12399016320705414
Norm Quadratic Average: 69.47256469726562
Nearest Class Center Accuracy: 0.830875

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13938115537166595
Inter Cos: 0.13690219819545746
Norm Quadratic Average: 43.61506652832031
Nearest Class Center Accuracy: 0.848875

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14113055169582367
Inter Cos: 0.1279539167881012
Norm Quadratic Average: 44.24372482299805
Nearest Class Center Accuracy: 0.870125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17409659922122955
Inter Cos: 0.09787039458751678
Norm Quadratic Average: 27.539974212646484
Nearest Class Center Accuracy: 0.912625

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18245916068553925
Inter Cos: 0.09148622304201126
Norm Quadratic Average: 28.416912078857422
Nearest Class Center Accuracy: 0.93725

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21384069323539734
Inter Cos: 0.08262184262275696
Norm Quadratic Average: 19.37641143798828
Nearest Class Center Accuracy: 0.9815

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3099878430366516
Inter Cos: 0.09134623408317566
Norm Quadratic Average: 15.235546112060547
Nearest Class Center Accuracy: 0.99825

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.75428771972656
Linear Weight Rank: 4031
Intra Cos: 0.5433689951896667
Inter Cos: 0.10839495807886124
Norm Quadratic Average: 100.1797103881836
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.236942291259766
Linear Weight Rank: 3671
Intra Cos: 0.707394003868103
Inter Cos: 0.14317652583122253
Norm Quadratic Average: 49.355079650878906
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9331074953079224
Linear Weight Rank: 10
Intra Cos: 0.8200969099998474
Inter Cos: 0.15538935363292694
Norm Quadratic Average: 29.116525650024414
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9130826592445374
Inter Cos: 0.252078652381897
Norm Quadratic Average: 14.862030029296875
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.08287735891342163
Accuracy: 0.977
NC1 Within Class Collapse: 1.5577161312103271
NC2 Equinorm: Features: 0.06011282280087471, Weights: 0.011930428445339203
NC2 Equiangle: Features: 0.19442418416341145, Weights: 0.08053385946485732
NC3 Self-Duality: 0.5177090167999268
NC4 NCC Mismatch: 0.005499999999999949

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: 0.12832877039909363
Inter Cos: 0.13292981684207916
Norm Quadratic Average: 68.21975708007812
Nearest Class Center Accuracy: 0.8265

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1557323932647705
Inter Cos: 0.15344959497451782
Norm Quadratic Average: 43.133480072021484
Nearest Class Center Accuracy: 0.845

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1524657905101776
Inter Cos: 0.13611829280853271
Norm Quadratic Average: 43.812313079833984
Nearest Class Center Accuracy: 0.8645

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16066844761371613
Inter Cos: 0.1215452179312706
Norm Quadratic Average: 27.391950607299805
Nearest Class Center Accuracy: 0.9055

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16678458452224731
Inter Cos: 0.11577779054641724
Norm Quadratic Average: 28.32892417907715
Nearest Class Center Accuracy: 0.923

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20387905836105347
Inter Cos: 0.09281385689973831
Norm Quadratic Average: 19.323566436767578
Nearest Class Center Accuracy: 0.958

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27240806818008423
Inter Cos: 0.0948135182261467
Norm Quadratic Average: 15.083623886108398
Nearest Class Center Accuracy: 0.974

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.75428771972656
Linear Weight Rank: 4031
Intra Cos: 0.45646730065345764
Inter Cos: 0.12496128678321838
Norm Quadratic Average: 97.4721450805664
Nearest Class Center Accuracy: 0.9755

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.236942291259766
Linear Weight Rank: 3671
Intra Cos: 0.5878813862800598
Inter Cos: 0.14604811370372772
Norm Quadratic Average: 47.70138931274414
Nearest Class Center Accuracy: 0.976

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9331074953079224
Linear Weight Rank: 10
Intra Cos: 0.691353976726532
Inter Cos: 0.19630727171897888
Norm Quadratic Average: 28.04706573486328
Nearest Class Center Accuracy: 0.977

Output Layer:
Intra Cos: 0.7845717072486877
Inter Cos: 0.2894291281700134
Norm Quadratic Average: 14.264575004577637
Nearest Class Center Accuracy: 0.9755

