Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg19_rand_seed_846264_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: 0.10967151820659637
Norm Quadratic Average: 23.567686080932617
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.060931988060474396
Inter Cos: 0.07983797788619995
Norm Quadratic Average: 2.242387533187866
Nearest Class Center Accuracy: 0.8116166666666667

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1029190719127655
Inter Cos: 0.10044176131486893
Norm Quadratic Average: 1.3533822298049927
Nearest Class Center Accuracy: 0.8706833333333334

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09951189905405045
Inter Cos: 0.0974639430642128
Norm Quadratic Average: 1.082086205482483
Nearest Class Center Accuracy: 0.8774166666666666

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17972329258918762
Inter Cos: 0.11758077144622803
Norm Quadratic Average: 0.680293619632721
Nearest Class Center Accuracy: 0.9372333333333334

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23208169639110565
Inter Cos: 0.1327190399169922
Norm Quadratic Average: 0.4918064475059509
Nearest Class Center Accuracy: 0.9634833333333334

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3127785325050354
Inter Cos: 0.14975345134735107
Norm Quadratic Average: 0.4109373688697815
Nearest Class Center Accuracy: 0.9738

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3502393662929535
Inter Cos: 0.15887729823589325
Norm Quadratic Average: 0.37199681997299194
Nearest Class Center Accuracy: 0.9770333333333333

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.41560497879981995
Inter Cos: 0.14773453772068024
Norm Quadratic Average: 0.22956614196300507
Nearest Class Center Accuracy: 0.9917833333333334

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6438090801239014
Inter Cos: 0.24050410091876984
Norm Quadratic Average: 0.15085113048553467
Nearest Class Center Accuracy: 0.9982833333333333

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8187421560287476
Inter Cos: 0.2946489751338959
Norm Quadratic Average: 0.13314859569072723
Nearest Class Center Accuracy: 0.9995166666666667

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8582523465156555
Inter Cos: 0.14784769713878632
Norm Quadratic Average: 0.15782254934310913
Nearest Class Center Accuracy: 0.9999333333333333

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9231403470039368
Inter Cos: 0.17331337928771973
Norm Quadratic Average: 0.14494509994983673
Nearest Class Center Accuracy: 0.99995

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9841131567955017
Inter Cos: 0.18396644294261932
Norm Quadratic Average: 0.16723591089248657
Nearest Class Center Accuracy: 0.99995

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9968364834785461
Inter Cos: 0.14020805060863495
Norm Quadratic Average: 0.42613691091537476
Nearest Class Center Accuracy: 0.99995

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9983590245246887
Inter Cos: 0.1742735356092453
Norm Quadratic Average: 1.0119538307189941
Nearest Class Center Accuracy: 0.99995

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.055035352706909
Linear Weight Rank: 9
Intra Cos: 0.999020516872406
Inter Cos: 0.21029505133628845
Norm Quadratic Average: 24.352766036987305
Nearest Class Center Accuracy: 0.99995

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.0564019680023193
Linear Weight Rank: 1565
Intra Cos: 0.999060332775116
Inter Cos: 0.19711069762706757
Norm Quadratic Average: 16.55744743347168
Nearest Class Center Accuracy: 0.99995

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.0574471950531006
Linear Weight Rank: 9
Intra Cos: 0.9990770220756531
Inter Cos: 0.17979168891906738
Norm Quadratic Average: 11.45042896270752
Nearest Class Center Accuracy: 0.99995

Output Layer:
Intra Cos: 0.9991244673728943
Inter Cos: 0.12754161655902863
Norm Quadratic Average: 8.325474739074707
Nearest Class Center Accuracy: 0.99995

Test Set:
Average Loss: 0.01974301270656288
Accuracy: 0.9953
NC1 Within Class Collapse: 0.09388984739780426
NC2 Equinorm: Features: 0.014807956293225288, Weights: 0.006978793069720268
NC2 Equiangle: Features: 0.12137302822536893, Weights: 0.09013291464911567
NC3 Self-Duality: 0.027774233371019363
NC4 NCC Mismatch: 0.00029999999999996696

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219582170248032
Inter Cos: 0.12048851698637009
Norm Quadratic Average: 23.59519386291504
Nearest Class Center Accuracy: 0.8229

Layer 1: Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06935285031795502
Inter Cos: 0.08213916420936584
Norm Quadratic Average: 2.2344868183135986
Nearest Class Center Accuracy: 0.822

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11309593915939331
Inter Cos: 0.10258392244577408
Norm Quadratic Average: 1.3450865745544434
Nearest Class Center Accuracy: 0.8815

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10917025059461594
Inter Cos: 0.10021038353443146
Norm Quadratic Average: 1.079346776008606
Nearest Class Center Accuracy: 0.8849

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19306665658950806
Inter Cos: 0.12820091843605042
Norm Quadratic Average: 0.6774826645851135
Nearest Class Center Accuracy: 0.9452

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24904640018939972
Inter Cos: 0.1310061812400818
Norm Quadratic Average: 0.49089953303337097
Nearest Class Center Accuracy: 0.9653

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.33076998591423035
Inter Cos: 0.1572721302509308
Norm Quadratic Average: 0.41069158911705017
Nearest Class Center Accuracy: 0.9734

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3674171268939972
Inter Cos: 0.17120203375816345
Norm Quadratic Average: 0.37154605984687805
Nearest Class Center Accuracy: 0.9764

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.43195101618766785
Inter Cos: 0.16430267691612244
Norm Quadratic Average: 0.22914673388004303
Nearest Class Center Accuracy: 0.9875

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.660227358341217
Inter Cos: 0.2581717371940613
Norm Quadratic Average: 0.15087950229644775
Nearest Class Center Accuracy: 0.993

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8106116056442261
Inter Cos: 0.3095781207084656
Norm Quadratic Average: 0.13344532251358032
Nearest Class Center Accuracy: 0.9943

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8586841225624084
Inter Cos: 0.16005218029022217
Norm Quadratic Average: 0.15785010159015656
Nearest Class Center Accuracy: 0.9954

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9184945821762085
Inter Cos: 0.16657733917236328
Norm Quadratic Average: 0.14469186961650848
Nearest Class Center Accuracy: 0.9951

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9739407896995544
Inter Cos: 0.1780860424041748
Norm Quadratic Average: 0.16662053763866425
Nearest Class Center Accuracy: 0.9949

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9783980846405029
Inter Cos: 0.1477850079536438
Norm Quadratic Average: 0.424782395362854
Nearest Class Center Accuracy: 0.995

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9799448251724243
Inter Cos: 0.17263680696487427
Norm Quadratic Average: 1.0086073875427246
Nearest Class Center Accuracy: 0.9951

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.055035352706909
Linear Weight Rank: 9
Intra Cos: 0.981580376625061
Inter Cos: 0.21370606124401093
Norm Quadratic Average: 24.27399253845215
Nearest Class Center Accuracy: 0.9953

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.0564019680023193
Linear Weight Rank: 1565
Intra Cos: 0.9826564192771912
Inter Cos: 0.20080238580703735
Norm Quadratic Average: 16.502817153930664
Nearest Class Center Accuracy: 0.9954

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.0574471950531006
Linear Weight Rank: 9
Intra Cos: 0.9834032654762268
Inter Cos: 0.18376226723194122
Norm Quadratic Average: 11.412042617797852
Nearest Class Center Accuracy: 0.9954

Output Layer:
Intra Cos: 0.9845724701881409
Inter Cos: 0.13394099473953247
Norm Quadratic Average: 8.295729637145996
Nearest Class Center Accuracy: 0.9954

