Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_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: 0.11311887204647064
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: 0.11452362686395645
Inter Cos: 0.14035050570964813
Norm Quadratic Average: 42.22096633911133
Nearest Class Center Accuracy: 0.81425

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14910054206848145
Inter Cos: 0.1759592890739441
Norm Quadratic Average: 45.532867431640625
Nearest Class Center Accuracy: 0.789

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16160576045513153
Inter Cos: 0.19685153663158417
Norm Quadratic Average: 58.036441802978516
Nearest Class Center Accuracy: 0.7965

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1952015608549118
Inter Cos: 0.205962672829628
Norm Quadratic Average: 34.42881393432617
Nearest Class Center Accuracy: 0.831

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23204749822616577
Inter Cos: 0.228331059217453
Norm Quadratic Average: 28.15847396850586
Nearest Class Center Accuracy: 0.87275

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.298315167427063
Inter Cos: 0.2128385305404663
Norm Quadratic Average: 14.597977638244629
Nearest Class Center Accuracy: 0.923125

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.44429150223731995
Inter Cos: 0.25047001242637634
Norm Quadratic Average: 9.855467796325684
Nearest Class Center Accuracy: 0.9695

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 72.46479797363281
Linear Weight Rank: 4031
Intra Cos: 0.65635085105896
Inter Cos: 0.28412896394729614
Norm Quadratic Average: 43.48476791381836
Nearest Class Center Accuracy: 0.995375

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 29.31586265563965
Linear Weight Rank: 3670
Intra Cos: 0.7442196011543274
Inter Cos: 0.27286064624786377
Norm Quadratic Average: 29.47378921508789
Nearest Class Center Accuracy: 0.998625

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2229034900665283
Linear Weight Rank: 10
Intra Cos: 0.7710937857627869
Inter Cos: 0.2732810974121094
Norm Quadratic Average: 23.625770568847656
Nearest Class Center Accuracy: 0.99825

Output Layer:
Intra Cos: 0.7941223978996277
Inter Cos: 0.3638615012168884
Norm Quadratic Average: 17.989009857177734
Nearest Class Center Accuracy: 0.996875

Test Set:
Average Loss: 0.07250024402141571
Accuracy: 0.9765
NC1 Within Class Collapse: 2.1726725101470947
NC2 Equinorm: Features: 0.13066551089286804, Weights: 0.02139299362897873
NC2 Equiangle: Features: 0.2629703097873264, Weights: 0.11419109768337674
NC3 Self-Duality: 0.37528324127197266
NC4 NCC Mismatch: 0.013499999999999956

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: 0.13805562257766724
Inter Cos: 0.15700985491275787
Norm Quadratic Average: 41.029571533203125
Nearest Class Center Accuracy: 0.8075

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16962110996246338
Inter Cos: 0.20684197545051575
Norm Quadratic Average: 44.30429458618164
Nearest Class Center Accuracy: 0.786

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18303753435611725
Inter Cos: 0.2353477030992508
Norm Quadratic Average: 56.39533996582031
Nearest Class Center Accuracy: 0.7915

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17336313426494598
Inter Cos: 0.24121800065040588
Norm Quadratic Average: 33.56167221069336
Nearest Class Center Accuracy: 0.828

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20051166415214539
Inter Cos: 0.26325488090515137
Norm Quadratic Average: 27.475557327270508
Nearest Class Center Accuracy: 0.866

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2616444528102875
Inter Cos: 0.2404233068227768
Norm Quadratic Average: 14.226686477661133
Nearest Class Center Accuracy: 0.9205

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3906543552875519
Inter Cos: 0.2830088138580322
Norm Quadratic Average: 9.579627990722656
Nearest Class Center Accuracy: 0.9515

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 72.46479797363281
Linear Weight Rank: 4031
Intra Cos: 0.5838022232055664
Inter Cos: 0.32290127873420715
Norm Quadratic Average: 42.182472229003906
Nearest Class Center Accuracy: 0.967

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 29.31586265563965
Linear Weight Rank: 3670
Intra Cos: 0.6627603769302368
Inter Cos: 0.3178335428237915
Norm Quadratic Average: 28.55304718017578
Nearest Class Center Accuracy: 0.974

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2229034900665283
Linear Weight Rank: 10
Intra Cos: 0.6836808919906616
Inter Cos: 0.30135324597358704
Norm Quadratic Average: 22.9222354888916
Nearest Class Center Accuracy: 0.9705

Output Layer:
Intra Cos: 0.697143018245697
Inter Cos: 0.3552853465080261
Norm Quadratic Average: 17.43317222595215
Nearest Class Center Accuracy: 0.968

