Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_314159_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: 0.09116754680871964
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: 0.12446559965610504
Inter Cos: 0.1549122929573059
Norm Quadratic Average: 39.00387191772461
Nearest Class Center Accuracy: 0.8016

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1636224389076233
Inter Cos: 0.18488606810569763
Norm Quadratic Average: 41.920562744140625
Nearest Class Center Accuracy: 0.7929166666666667

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20026825368404388
Inter Cos: 0.20820026099681854
Norm Quadratic Average: 43.714393615722656
Nearest Class Center Accuracy: 0.8281

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17349421977996826
Inter Cos: 0.24472373723983765
Norm Quadratic Average: 23.4309024810791
Nearest Class Center Accuracy: 0.88135

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23899982869625092
Inter Cos: 0.2994507849216461
Norm Quadratic Average: 13.976489067077637
Nearest Class Center Accuracy: 0.9194166666666667

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.45788437128067017
Inter Cos: 0.3436030447483063
Norm Quadratic Average: 8.053932189941406
Nearest Class Center Accuracy: 0.96745

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6352120637893677
Inter Cos: 0.42694032192230225
Norm Quadratic Average: 8.334394454956055
Nearest Class Center Accuracy: 0.9813166666666666

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.815110445022583
Linear Weight Rank: 11
Intra Cos: 0.748760461807251
Inter Cos: 0.40428662300109863
Norm Quadratic Average: 39.92215347290039
Nearest Class Center Accuracy: 0.9876333333333334

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.8160380125045776
Linear Weight Rank: 2682
Intra Cos: 0.8345302939414978
Inter Cos: 0.36133840680122375
Norm Quadratic Average: 28.909116744995117
Nearest Class Center Accuracy: 0.9904

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.8103564977645874
Linear Weight Rank: 9
Intra Cos: 0.8705822825431824
Inter Cos: 0.3522229492664337
Norm Quadratic Average: 20.31099510192871
Nearest Class Center Accuracy: 0.9911166666666666

Output Layer:
Intra Cos: 0.8973421454429626
Inter Cos: 0.41015979647636414
Norm Quadratic Average: 16.160432815551758
Nearest Class Center Accuracy: 0.99135

Test Set:
Average Loss: 0.035144495592266324
Accuracy: 0.9884
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.11660853028297424, Weights: 0.048373736441135406
NC2 Equiangle: Features: 0.269711176554362, Weights: 0.241649776034885
NC3 Self-Duality: 0.06439325213432312
NC4 NCC Mismatch: 0.006299999999999972

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: 0.13797564804553986
Inter Cos: 0.16965077817440033
Norm Quadratic Average: 39.08279037475586
Nearest Class Center Accuracy: 0.8178

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1796063631772995
Inter Cos: 0.20328515768051147
Norm Quadratic Average: 41.89646911621094
Nearest Class Center Accuracy: 0.8098

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2133556306362152
Inter Cos: 0.2281099408864975
Norm Quadratic Average: 43.693477630615234
Nearest Class Center Accuracy: 0.8457

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18455862998962402
Inter Cos: 0.2476428896188736
Norm Quadratic Average: 23.382272720336914
Nearest Class Center Accuracy: 0.9007

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25335875153541565
Inter Cos: 0.32170766592025757
Norm Quadratic Average: 13.970669746398926
Nearest Class Center Accuracy: 0.9272

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4736388325691223
Inter Cos: 0.3410837948322296
Norm Quadratic Average: 8.080755233764648
Nearest Class Center Accuracy: 0.9679

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6420461535453796
Inter Cos: 0.44544681906700134
Norm Quadratic Average: 8.399893760681152
Nearest Class Center Accuracy: 0.9784

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.815110445022583
Linear Weight Rank: 11
Intra Cos: 0.750602126121521
Inter Cos: 0.4193532466888428
Norm Quadratic Average: 40.35927200317383
Nearest Class Center Accuracy: 0.9845

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.8160380125045776
Linear Weight Rank: 2682
Intra Cos: 0.8303173184394836
Inter Cos: 0.3800307512283325
Norm Quadratic Average: 29.26498031616211
Nearest Class Center Accuracy: 0.9868

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.8103564977645874
Linear Weight Rank: 9
Intra Cos: 0.8645426034927368
Inter Cos: 0.3688051402568817
Norm Quadratic Average: 20.564807891845703
Nearest Class Center Accuracy: 0.9872

Output Layer:
Intra Cos: 0.8881860971450806
Inter Cos: 0.4256748557090759
Norm Quadratic Average: 16.37104034423828
Nearest Class Center Accuracy: 0.9883

