Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_979323_test_samples_None_train_samples_None_weight_decay_0.01.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09116753935813904
Inter Cos: 0.10967151820659637
Norm Quadratic Average: 23.567676544189453
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12445078790187836
Inter Cos: 0.1537400782108307
Norm Quadratic Average: 39.04570388793945
Nearest Class Center Accuracy: 0.8018666666666666

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16507954895496368
Inter Cos: 0.18184372782707214
Norm Quadratic Average: 41.21855926513672
Nearest Class Center Accuracy: 0.7962333333333333

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20109188556671143
Inter Cos: 0.2106853723526001
Norm Quadratic Average: 44.45293426513672
Nearest Class Center Accuracy: 0.8273333333333334

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.171281635761261
Inter Cos: 0.24117344617843628
Norm Quadratic Average: 25.47628402709961
Nearest Class Center Accuracy: 0.8728166666666667

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2341720163822174
Inter Cos: 0.316943496465683
Norm Quadratic Average: 15.64323902130127
Nearest Class Center Accuracy: 0.9199833333333334

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.46874555945396423
Inter Cos: 0.3226418197154999
Norm Quadratic Average: 8.324067115783691
Nearest Class Center Accuracy: 0.9620333333333333

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6596729755401611
Inter Cos: 0.3991507887840271
Norm Quadratic Average: 8.055047035217285
Nearest Class Center Accuracy: 0.9815

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.824029564857483
Linear Weight Rank: 13
Intra Cos: 0.7639729976654053
Inter Cos: 0.40964779257774353
Norm Quadratic Average: 38.14061737060547
Nearest Class Center Accuracy: 0.9877166666666667

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.8244004249572754
Linear Weight Rank: 2801
Intra Cos: 0.84027099609375
Inter Cos: 0.3830794095993042
Norm Quadratic Average: 27.7878360748291
Nearest Class Center Accuracy: 0.9901666666666666

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.8187392950057983
Linear Weight Rank: 9
Intra Cos: 0.8712288737297058
Inter Cos: 0.3600495159626007
Norm Quadratic Average: 19.78351402282715
Nearest Class Center Accuracy: 0.9913

Output Layer:
Intra Cos: 0.8959181308746338
Inter Cos: 0.41290971636772156
Norm Quadratic Average: 15.882646560668945
Nearest Class Center Accuracy: 0.9915166666666667

Test Set:
Average Loss: 0.03521305623613298
Accuracy: 0.9888
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.10585730522871017, Weights: 0.04804501309990883
NC2 Equiangle: Features: 0.2747339460584852, Weights: 0.2474302503797743
NC3 Self-Duality: 0.054004546254873276
NC4 NCC Mismatch: 0.005499999999999949

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219582170248032
Inter Cos: 0.12048851698637009
Norm Quadratic Average: 23.595197677612305
Nearest Class Center Accuracy: 0.8229

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13793611526489258
Inter Cos: 0.1683269441127777
Norm Quadratic Average: 39.116722106933594
Nearest Class Center Accuracy: 0.818

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18105828762054443
Inter Cos: 0.19970184564590454
Norm Quadratic Average: 41.18526840209961
Nearest Class Center Accuracy: 0.8129

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2149999439716339
Inter Cos: 0.23063835501670837
Norm Quadratic Average: 44.422096252441406
Nearest Class Center Accuracy: 0.8452

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1791527420282364
Inter Cos: 0.2387377768754959
Norm Quadratic Average: 25.422298431396484
Nearest Class Center Accuracy: 0.8905

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2419585883617401
Inter Cos: 0.3095659911632538
Norm Quadratic Average: 15.630773544311523
Nearest Class Center Accuracy: 0.9288

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4783393442630768
Inter Cos: 0.31669217348098755
Norm Quadratic Average: 8.34339427947998
Nearest Class Center Accuracy: 0.962

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6602126359939575
Inter Cos: 0.4237631559371948
Norm Quadratic Average: 8.117883682250977
Nearest Class Center Accuracy: 0.9794

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.824029564857483
Linear Weight Rank: 13
Intra Cos: 0.7624143362045288
Inter Cos: 0.42508184909820557
Norm Quadratic Average: 38.554351806640625
Nearest Class Center Accuracy: 0.9853

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.8244004249572754
Linear Weight Rank: 2801
Intra Cos: 0.8338770866394043
Inter Cos: 0.40428176522254944
Norm Quadratic Average: 28.123971939086914
Nearest Class Center Accuracy: 0.9882

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.8187392950057983
Linear Weight Rank: 9
Intra Cos: 0.8635001182556152
Inter Cos: 0.380492627620697
Norm Quadratic Average: 20.027875900268555
Nearest Class Center Accuracy: 0.9884

Output Layer:
Intra Cos: 0.8870548009872437
Inter Cos: 0.432367742061615
Norm Quadratic Average: 16.087583541870117
Nearest Class Center Accuracy: 0.989

