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_0.01.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: 0.10208769142627716
Inter Cos: 0.1054530218243599
Norm Quadratic Average: 2.1806933879852295
Nearest Class Center Accuracy: 0.8555166666666667

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17849035561084747
Inter Cos: 0.13019342720508575
Norm Quadratic Average: 1.1110126972198486
Nearest Class Center Accuracy: 0.9189333333333334

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22390680015087128
Inter Cos: 0.15449067950248718
Norm Quadratic Average: 0.7162685990333557
Nearest Class Center Accuracy: 0.9524166666666667

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.30765801668167114
Inter Cos: 0.11198065429925919
Norm Quadratic Average: 0.338832288980484
Nearest Class Center Accuracy: 0.9883833333333333

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6495888233184814
Inter Cos: 0.195632204413414
Norm Quadratic Average: 0.30447307229042053
Nearest Class Center Accuracy: 0.9994666666666666

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8559002876281738
Inter Cos: 0.2280087023973465
Norm Quadratic Average: 0.45738738775253296
Nearest Class Center Accuracy: 0.9999833333333333

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9781390428543091
Inter Cos: 0.26106521487236023
Norm Quadratic Average: 0.8720184564590454
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.038097858428955
Linear Weight Rank: 8
Intra Cos: 0.9968155026435852
Inter Cos: 0.27720245718955994
Norm Quadratic Average: 23.181142807006836
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.0391685962677
Linear Weight Rank: 1379
Intra Cos: 0.9978494644165039
Inter Cos: 0.233722522854805
Norm Quadratic Average: 16.519445419311523
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.0401980876922607
Linear Weight Rank: 8
Intra Cos: 0.9982099533081055
Inter Cos: 0.19248338043689728
Norm Quadratic Average: 12.024541854858398
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.997882068157196
Inter Cos: 0.2504545748233795
Norm Quadratic Average: 9.403515815734863
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.019472257527709008
Accuracy: 0.9951
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.03583532199263573, Weights: 0.010879045352339745
NC2 Equiangle: Features: 0.16995849609375, Weights: 0.1661209848192003
NC3 Self-Duality: 0.03427434340119362
NC4 NCC Mismatch: 0.00039999999999995595

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: 0.11225384473800659
Inter Cos: 0.10572012513875961
Norm Quadratic Average: 2.172266721725464
Nearest Class Center Accuracy: 0.8683

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1899152547121048
Inter Cos: 0.12703937292099
Norm Quadratic Average: 1.1067867279052734
Nearest Class Center Accuracy: 0.9288

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23654547333717346
Inter Cos: 0.15062043070793152
Norm Quadratic Average: 0.7151557803153992
Nearest Class Center Accuracy: 0.9554

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3147551119327545
Inter Cos: 0.12222688645124435
Norm Quadratic Average: 0.338092565536499
Nearest Class Center Accuracy: 0.9854

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.647964596748352
Inter Cos: 0.20288611948490143
Norm Quadratic Average: 0.3036872148513794
Nearest Class Center Accuracy: 0.9939

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8493001461029053
Inter Cos: 0.2351292371749878
Norm Quadratic Average: 0.45603814721107483
Nearest Class Center Accuracy: 0.9953

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9646193981170654
Inter Cos: 0.2617743909358978
Norm Quadratic Average: 0.8680436611175537
Nearest Class Center Accuracy: 0.9953

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.038097858428955
Linear Weight Rank: 8
Intra Cos: 0.9770653247833252
Inter Cos: 0.27950823307037354
Norm Quadratic Average: 23.070310592651367
Nearest Class Center Accuracy: 0.9953

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.0391685962677
Linear Weight Rank: 1379
Intra Cos: 0.9792526960372925
Inter Cos: 0.23653090000152588
Norm Quadratic Average: 16.438640594482422
Nearest Class Center Accuracy: 0.9952

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.0401980876922607
Linear Weight Rank: 8
Intra Cos: 0.9804359078407288
Inter Cos: 0.19234314560890198
Norm Quadratic Average: 11.964676856994629
Nearest Class Center Accuracy: 0.9951

Output Layer:
Intra Cos: 0.9825189709663391
Inter Cos: 0.2510732114315033
Norm Quadratic Average: 9.355964660644531
Nearest Class Center Accuracy: 0.9954

