Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_314159_test_samples_None_train_samples_None_weight_decay_0.003.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09116754680871964
Inter Cos: 0.10967153310775757
Norm Quadratic Average: 23.567678451538086
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.097893625497818
Inter Cos: 0.09786469489336014
Norm Quadratic Average: 2.1511712074279785
Nearest Class Center Accuracy: 0.8612166666666666

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16890716552734375
Inter Cos: 0.12070540338754654
Norm Quadratic Average: 1.314003348350525
Nearest Class Center Accuracy: 0.9207833333333333

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20050199329853058
Inter Cos: 0.13151361048221588
Norm Quadratic Average: 0.9976551532745361
Nearest Class Center Accuracy: 0.9559666666666666

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2861829996109009
Inter Cos: 0.1273013800382614
Norm Quadratic Average: 0.6783669590950012
Nearest Class Center Accuracy: 0.9909666666666667

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5648790597915649
Inter Cos: 0.1469022035598755
Norm Quadratic Average: 0.5539510250091553
Nearest Class Center Accuracy: 0.999

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7889502048492432
Inter Cos: 0.14690862596035004
Norm Quadratic Average: 0.6144713759422302
Nearest Class Center Accuracy: 1.0

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9776343107223511
Inter Cos: 0.027560239657759666
Norm Quadratic Average: 0.9754420518875122
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.2058820724487305
Linear Weight Rank: 183
Intra Cos: 0.9966753125190735
Inter Cos: 0.023866131901741028
Norm Quadratic Average: 25.100034713745117
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.211156129837036
Linear Weight Rank: 1430
Intra Cos: 0.997518002986908
Inter Cos: 0.07003147900104523
Norm Quadratic Average: 17.420398712158203
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2077231407165527
Linear Weight Rank: 9
Intra Cos: 0.9978386163711548
Inter Cos: 0.068564772605896
Norm Quadratic Average: 12.315144538879395
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9980071187019348
Inter Cos: 0.07624645531177521
Norm Quadratic Average: 9.247696876525879
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.01575924698142335
Accuracy: 0.9958
NC1 Within Class Collapse: 0.11657653748989105
NC2 Equinorm: Features: 0.017553599551320076, Weights: 0.007318513467907906
NC2 Equiangle: Features: 0.08497297498914931, Weights: 0.04274509747823079
NC3 Self-Duality: 0.013937941752374172
NC4 NCC Mismatch: 0.00019999999999997797

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219582915306091
Inter Cos: 0.12048852443695068
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: 0.1072177141904831
Inter Cos: 0.09899906814098358
Norm Quadratic Average: 2.138725757598877
Nearest Class Center Accuracy: 0.8744

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18008998036384583
Inter Cos: 0.1193246990442276
Norm Quadratic Average: 1.3063746690750122
Nearest Class Center Accuracy: 0.9292

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21374912559986115
Inter Cos: 0.12928903102874756
Norm Quadratic Average: 0.9935513734817505
Nearest Class Center Accuracy: 0.9578

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2967394292354584
Inter Cos: 0.13680145144462585
Norm Quadratic Average: 0.675533652305603
Nearest Class Center Accuracy: 0.9876

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5734413266181946
Inter Cos: 0.15752346813678741
Norm Quadratic Average: 0.5525026917457581
Nearest Class Center Accuracy: 0.9941

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7854702472686768
Inter Cos: 0.1591310203075409
Norm Quadratic Average: 0.6128533482551575
Nearest Class Center Accuracy: 0.9956

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9670127630233765
Inter Cos: 0.041358716785907745
Norm Quadratic Average: 0.9712307453155518
Nearest Class Center Accuracy: 0.9957

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.2058820724487305
Linear Weight Rank: 183
Intra Cos: 0.9776440262794495
Inter Cos: 0.0295743178576231
Norm Quadratic Average: 24.98520278930664
Nearest Class Center Accuracy: 0.9956

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.211156129837036
Linear Weight Rank: 1430
Intra Cos: 0.9785983562469482
Inter Cos: 0.07463777810335159
Norm Quadratic Average: 17.341022491455078
Nearest Class Center Accuracy: 0.9957

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2077231407165527
Linear Weight Rank: 9
Intra Cos: 0.978951096534729
Inter Cos: 0.0729953721165657
Norm Quadratic Average: 12.25911808013916
Nearest Class Center Accuracy: 0.9958

Output Layer:
Intra Cos: 0.979593813419342
Inter Cos: 0.08194181323051453
Norm Quadratic Average: 9.205536842346191
Nearest Class Center Accuracy: 0.9958

