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_0.0005.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: 0.09679147601127625
Inter Cos: 0.10151614248752594
Norm Quadratic Average: 11.255352020263672
Nearest Class Center Accuracy: 0.8576833333333334

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16326621174812317
Inter Cos: 0.12273797392845154
Norm Quadratic Average: 7.9146904945373535
Nearest Class Center Accuracy: 0.9126166666666666

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20188741385936737
Inter Cos: 0.13435563445091248
Norm Quadratic Average: 8.144891738891602
Nearest Class Center Accuracy: 0.9418833333333333

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.26877909898757935
Inter Cos: 0.11348847299814224
Norm Quadratic Average: 5.978989601135254
Nearest Class Center Accuracy: 0.9849333333333333

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.40952691435813904
Inter Cos: 0.136419415473938
Norm Quadratic Average: 6.743448734283447
Nearest Class Center Accuracy: 0.9968

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5797635912895203
Inter Cos: 0.12616729736328125
Norm Quadratic Average: 5.550267219543457
Nearest Class Center Accuracy: 0.9999166666666667

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8908525109291077
Inter Cos: 0.057670801877975464
Norm Quadratic Average: 4.1251139640808105
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 14.696840286254883
Linear Weight Rank: 4031
Intra Cos: 0.9802333116531372
Inter Cos: -0.026838034391403198
Norm Quadratic Average: 41.76533508300781
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 6.300727844238281
Linear Weight Rank: 3667
Intra Cos: 0.9913185834884644
Inter Cos: 0.007446670904755592
Norm Quadratic Average: 27.15933609008789
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.1295406818389893
Linear Weight Rank: 10
Intra Cos: 0.9922837018966675
Inter Cos: 0.022593658417463303
Norm Quadratic Average: 18.04706573486328
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9976422190666199
Inter Cos: 0.1201302707195282
Norm Quadratic Average: 12.842700004577637
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.017557854771002895
Accuracy: 0.9958
NC1 Within Class Collapse: 0.184654101729393
NC2 Equinorm: Features: 0.026762979105114937, Weights: 0.010463966056704521
NC2 Equiangle: Features: 0.08323370615641276, Weights: 0.05464446809556749
NC3 Self-Duality: 0.05717180669307709
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: 0.10674452781677246
Inter Cos: 0.10266421735286713
Norm Quadratic Average: 11.175637245178223
Nearest Class Center Accuracy: 0.8701

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1740403026342392
Inter Cos: 0.12089749425649643
Norm Quadratic Average: 7.8588786125183105
Nearest Class Center Accuracy: 0.9206

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21444784104824066
Inter Cos: 0.1315145492553711
Norm Quadratic Average: 8.102130889892578
Nearest Class Center Accuracy: 0.9473

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.28132566809654236
Inter Cos: 0.11314978450536728
Norm Quadratic Average: 5.9574875831604
Nearest Class Center Accuracy: 0.9832

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.42198508977890015
Inter Cos: 0.13812632858753204
Norm Quadratic Average: 6.730650901794434
Nearest Class Center Accuracy: 0.9915

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5811884999275208
Inter Cos: 0.12337825447320938
Norm Quadratic Average: 5.546721458435059
Nearest Class Center Accuracy: 0.9944

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8813753128051758
Inter Cos: 0.06092146411538124
Norm Quadratic Average: 4.1193318367004395
Nearest Class Center Accuracy: 0.9953

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 14.696840286254883
Linear Weight Rank: 4031
Intra Cos: 0.964313805103302
Inter Cos: -0.030065374448895454
Norm Quadratic Average: 41.6829833984375
Nearest Class Center Accuracy: 0.9958

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 6.300727844238281
Linear Weight Rank: 3667
Intra Cos: 0.9720391631126404
Inter Cos: 0.001031758263707161
Norm Quadratic Average: 27.10010528564453
Nearest Class Center Accuracy: 0.9959

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.1295406818389893
Linear Weight Rank: 10
Intra Cos: 0.9711263179779053
Inter Cos: 0.03430861607193947
Norm Quadratic Average: 18.010278701782227
Nearest Class Center Accuracy: 0.996

Output Layer:
Intra Cos: 0.9826311469078064
Inter Cos: 0.1280040740966797
Norm Quadratic Average: 12.811716079711914
Nearest Class Center Accuracy: 0.9959

