Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg19_rand_seed_979323_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: 0.10967149585485458
Norm Quadratic Average: 23.567672729492188
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.059743575751781464
Inter Cos: 0.07797076553106308
Norm Quadratic Average: 2.4807353019714355
Nearest Class Center Accuracy: 0.8123333333333334

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10054165124893188
Inter Cos: 0.09732633829116821
Norm Quadratic Average: 1.4855509996414185
Nearest Class Center Accuracy: 0.8726666666666667

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09866742044687271
Inter Cos: 0.09539660811424255
Norm Quadratic Average: 1.1642818450927734
Nearest Class Center Accuracy: 0.8817666666666667

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17901982367038727
Inter Cos: 0.11761747300624847
Norm Quadratic Average: 0.8214924931526184
Nearest Class Center Accuracy: 0.9388

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23127637803554535
Inter Cos: 0.1391129195690155
Norm Quadratic Average: 0.6346176862716675
Nearest Class Center Accuracy: 0.9641

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.29299813508987427
Inter Cos: 0.15297004580497742
Norm Quadratic Average: 0.5258776545524597
Nearest Class Center Accuracy: 0.9758333333333333

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.336024671792984
Inter Cos: 0.17825497686862946
Norm Quadratic Average: 0.48486948013305664
Nearest Class Center Accuracy: 0.9811833333333333

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.40755969285964966
Inter Cos: 0.17728273570537567
Norm Quadratic Average: 0.3508646488189697
Nearest Class Center Accuracy: 0.9943833333333333

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6697230935096741
Inter Cos: 0.2558404803276062
Norm Quadratic Average: 0.26494988799095154
Nearest Class Center Accuracy: 0.9987

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8225283622741699
Inter Cos: 0.23547831177711487
Norm Quadratic Average: 0.22680805623531342
Nearest Class Center Accuracy: 0.9996333333333334

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8608673810958862
Inter Cos: 0.18410439789295197
Norm Quadratic Average: 0.21211066842079163
Nearest Class Center Accuracy: 0.9999833333333333

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9067897796630859
Inter Cos: 0.12306872010231018
Norm Quadratic Average: 0.2794768214225769
Nearest Class Center Accuracy: 0.9999833333333333

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9845249056816101
Inter Cos: -0.022422295063734055
Norm Quadratic Average: 0.3292253613471985
Nearest Class Center Accuracy: 0.9999833333333333

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9957137703895569
Inter Cos: -0.0330609455704689
Norm Quadratic Average: 0.5567024350166321
Nearest Class Center Accuracy: 0.9999833333333333

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9985305666923523
Inter Cos: -0.055549345910549164
Norm Quadratic Average: 1.0865042209625244
Nearest Class Center Accuracy: 0.9999833333333333

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.197824478149414
Linear Weight Rank: 144
Intra Cos: 0.9993512630462646
Inter Cos: -0.03528909012675285
Norm Quadratic Average: 25.748319625854492
Nearest Class Center Accuracy: 0.9999833333333333

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.20450758934021
Linear Weight Rank: 1352
Intra Cos: 0.9993889927864075
Inter Cos: 0.017854055389761925
Norm Quadratic Average: 17.618976593017578
Nearest Class Center Accuracy: 0.9999833333333333

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2011072635650635
Linear Weight Rank: 9
Intra Cos: 0.9994078874588013
Inter Cos: 0.04485649615526199
Norm Quadratic Average: 12.352692604064941
Nearest Class Center Accuracy: 0.9999833333333333

Output Layer:
Intra Cos: 0.9995623826980591
Inter Cos: 0.06626453995704651
Norm Quadratic Average: 9.160056114196777
Nearest Class Center Accuracy: 0.9999833333333333

Test Set:
Average Loss: 0.018192839918658138
Accuracy: 0.9964
NC1 Within Class Collapse: 0.08108234405517578
NC2 Equinorm: Features: 0.02081412263214588, Weights: 0.005492422729730606
NC2 Equiangle: Features: 0.0687048594156901, Weights: 0.029422023561265734
NC3 Self-Duality: 0.009474712423980236
NC4 NCC Mismatch: 9.999999999998899e-05

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219583660364151
Inter Cos: 0.12048852443695068
Norm Quadratic Average: 23.595197677612305
Nearest Class Center Accuracy: 0.8229

Layer 1: Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06734760105609894
Inter Cos: 0.08038617670536041
Norm Quadratic Average: 2.4715700149536133
Nearest Class Center Accuracy: 0.8261

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1099533885717392
Inter Cos: 0.09905915707349777
Norm Quadratic Average: 1.4748941659927368
Nearest Class Center Accuracy: 0.8829

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10815703868865967
Inter Cos: 0.0964406207203865
Norm Quadratic Average: 1.1602057218551636
Nearest Class Center Accuracy: 0.8907

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1902933269739151
Inter Cos: 0.12872573733329773
Norm Quadratic Average: 0.8184349536895752
Nearest Class Center Accuracy: 0.9455

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2449052333831787
Inter Cos: 0.150906503200531
Norm Quadratic Average: 0.6329983472824097
Nearest Class Center Accuracy: 0.966

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.30655303597450256
Inter Cos: 0.1669750064611435
Norm Quadratic Average: 0.5251097679138184
Nearest Class Center Accuracy: 0.9751

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3487660586833954
Inter Cos: 0.19256453216075897
Norm Quadratic Average: 0.4839014708995819
Nearest Class Center Accuracy: 0.9802

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.41539087891578674
Inter Cos: 0.18816712498664856
Norm Quadratic Average: 0.350206196308136
Nearest Class Center Accuracy: 0.9907

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6766278743743896
Inter Cos: 0.26616156101226807
Norm Quadratic Average: 0.2648591995239258
Nearest Class Center Accuracy: 0.9946

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8241212964057922
Inter Cos: 0.24557769298553467
Norm Quadratic Average: 0.2267432063817978
Nearest Class Center Accuracy: 0.9952

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8603620529174805
Inter Cos: 0.1954578012228012
Norm Quadratic Average: 0.21180592477321625
Nearest Class Center Accuracy: 0.996

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9033479690551758
Inter Cos: 0.12308891862630844
Norm Quadratic Average: 0.2786904275417328
Nearest Class Center Accuracy: 0.9959

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9719223976135254
Inter Cos: -0.024538211524486542
Norm Quadratic Average: 0.32815390825271606
Nearest Class Center Accuracy: 0.9965

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9774551391601562
Inter Cos: -0.030762702226638794
Norm Quadratic Average: 0.5548858046531677
Nearest Class Center Accuracy: 0.9964

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9793820977210999
Inter Cos: -0.05329615995287895
Norm Quadratic Average: 1.0829414129257202
Nearest Class Center Accuracy: 0.9964

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.197824478149414
Linear Weight Rank: 144
Intra Cos: 0.9808048605918884
Inter Cos: -0.025563428178429604
Norm Quadratic Average: 25.660457611083984
Nearest Class Center Accuracy: 0.9964

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.20450758934021
Linear Weight Rank: 1352
Intra Cos: 0.9815912246704102
Inter Cos: 0.02529638633131981
Norm Quadratic Average: 17.559593200683594
Nearest Class Center Accuracy: 0.9965

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2011072635650635
Linear Weight Rank: 9
Intra Cos: 0.9820014834403992
Inter Cos: 0.053752969950437546
Norm Quadratic Average: 12.311710357666016
Nearest Class Center Accuracy: 0.9965

Output Layer:
Intra Cos: 0.982732892036438
Inter Cos: 0.07460438460111618
Norm Quadratic Average: 9.129220008850098
Nearest Class Center Accuracy: 0.9964

