Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_979323_test_samples_None_train_samples_None_weight_decay_0.0003.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: 0.09625956416130066
Inter Cos: 0.11002562940120697
Norm Quadratic Average: 26.977975845336914
Nearest Class Center Accuracy: 0.8449833333333333

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1641569882631302
Inter Cos: 0.12752670049667358
Norm Quadratic Average: 18.373153686523438
Nearest Class Center Accuracy: 0.9033

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2005244791507721
Inter Cos: 0.13192972540855408
Norm Quadratic Average: 18.89984130859375
Nearest Class Center Accuracy: 0.9330833333333334

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2550910711288452
Inter Cos: 0.10663249343633652
Norm Quadratic Average: 12.527017593383789
Nearest Class Center Accuracy: 0.9793

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.34732934832572937
Inter Cos: 0.1065034493803978
Norm Quadratic Average: 13.824806213378906
Nearest Class Center Accuracy: 0.9933333333333333

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.49238285422325134
Inter Cos: 0.10979510843753815
Norm Quadratic Average: 10.557427406311035
Nearest Class Center Accuracy: 0.99955

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7748885154724121
Inter Cos: 0.08668939024209976
Norm Quadratic Average: 8.147843360900879
Nearest Class Center Accuracy: 0.9999833333333333

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 31.688976287841797
Linear Weight Rank: 4031
Intra Cos: 0.9498845338821411
Inter Cos: 0.00420403853058815
Norm Quadratic Average: 68.86353302001953
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 12.971035957336426
Linear Weight Rank: 3670
Intra Cos: 0.9857810139656067
Inter Cos: 0.004474850837141275
Norm Quadratic Average: 40.50867462158203
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9564284086227417
Linear Weight Rank: 10
Intra Cos: 0.9887599945068359
Inter Cos: 0.03920953720808029
Norm Quadratic Average: 23.314260482788086
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9962656497955322
Inter Cos: 0.08241264522075653
Norm Quadratic Average: 14.302513122558594
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.016824091541068627
Accuracy: 0.9955
NC1 Within Class Collapse: 0.20477408170700073
NC2 Equinorm: Features: 0.03255932405591011, Weights: 0.03411988541483879
NC2 Equiangle: Features: 0.08228416442871093, Weights: 0.048058774736192494
NC3 Self-Duality: 0.1607763022184372
NC4 NCC Mismatch: 0.0004999999999999449

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: 0.1056819036602974
Inter Cos: 0.11056607216596603
Norm Quadratic Average: 26.809722900390625
Nearest Class Center Accuracy: 0.8569

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17516811192035675
Inter Cos: 0.12640899419784546
Norm Quadratic Average: 18.246150970458984
Nearest Class Center Accuracy: 0.914

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21569417417049408
Inter Cos: 0.129770427942276
Norm Quadratic Average: 18.78767204284668
Nearest Class Center Accuracy: 0.9382

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2637542486190796
Inter Cos: 0.10693836957216263
Norm Quadratic Average: 12.477462768554688
Nearest Class Center Accuracy: 0.9773

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3626113831996918
Inter Cos: 0.1097450852394104
Norm Quadratic Average: 13.791747093200684
Nearest Class Center Accuracy: 0.9888

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5005773901939392
Inter Cos: 0.11825965344905853
Norm Quadratic Average: 10.544108390808105
Nearest Class Center Accuracy: 0.9939

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7726198434829712
Inter Cos: 0.08720594644546509
Norm Quadratic Average: 8.137145042419434
Nearest Class Center Accuracy: 0.9952

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 31.688976287841797
Linear Weight Rank: 4031
Intra Cos: 0.940311849117279
Inter Cos: 0.0033830138854682446
Norm Quadratic Average: 68.71520233154297
Nearest Class Center Accuracy: 0.9952

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 12.971035957336426
Linear Weight Rank: 3670
Intra Cos: 0.967614471912384
Inter Cos: 0.005768955685198307
Norm Quadratic Average: 40.3974723815918
Nearest Class Center Accuracy: 0.9957

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9564284086227417
Linear Weight Rank: 10
Intra Cos: 0.968108057975769
Inter Cos: 0.04019833728671074
Norm Quadratic Average: 23.25383758544922
Nearest Class Center Accuracy: 0.9956

Output Layer:
Intra Cos: 0.9817047715187073
Inter Cos: 0.09204889088869095
Norm Quadratic Average: 14.259111404418945
Nearest Class Center Accuracy: 0.9956

