Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg19_rand_seed_314159_test_samples_None_train_samples_None_weight_decay_0.005.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09116753935813904
Inter Cos: 0.10967151075601578
Norm Quadratic Average: 23.567678451538086
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.05927944555878639
Inter Cos: 0.07686957716941833
Norm Quadratic Average: 2.5996811389923096
Nearest Class Center Accuracy: 0.80945

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10486714541912079
Inter Cos: 0.10001837462186813
Norm Quadratic Average: 1.4154419898986816
Nearest Class Center Accuracy: 0.8724

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10491573065519333
Inter Cos: 0.09855131059885025
Norm Quadratic Average: 1.07029128074646
Nearest Class Center Accuracy: 0.8785

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18167906999588013
Inter Cos: 0.12540476024150848
Norm Quadratic Average: 0.6672507524490356
Nearest Class Center Accuracy: 0.93225

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23825250566005707
Inter Cos: 0.14604829251766205
Norm Quadratic Average: 0.47113943099975586
Nearest Class Center Accuracy: 0.9610333333333333

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3101765513420105
Inter Cos: 0.15752162039279938
Norm Quadratic Average: 0.3774680495262146
Nearest Class Center Accuracy: 0.9714833333333334

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3508097529411316
Inter Cos: 0.15234021842479706
Norm Quadratic Average: 0.3388926386833191
Nearest Class Center Accuracy: 0.9733

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4102051556110382
Inter Cos: 0.14044496417045593
Norm Quadratic Average: 0.19516509771347046
Nearest Class Center Accuracy: 0.9923

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.613335907459259
Inter Cos: 0.1978403925895691
Norm Quadratic Average: 0.11598774045705795
Nearest Class Center Accuracy: 0.998

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.827521800994873
Inter Cos: 0.20727138221263885
Norm Quadratic Average: 0.1180952936410904
Nearest Class Center Accuracy: 0.99985

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8713590502738953
Inter Cos: 0.1251336634159088
Norm Quadratic Average: 0.14605218172073364
Nearest Class Center Accuracy: 0.9999333333333333

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9155866503715515
Inter Cos: 0.22994767129421234
Norm Quadratic Average: 0.2069181203842163
Nearest Class Center Accuracy: 0.9999666666666667

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9826335310935974
Inter Cos: 0.062058571726083755
Norm Quadratic Average: 0.25847265124320984
Nearest Class Center Accuracy: 0.9999833333333333

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9966868162155151
Inter Cos: -0.021853003650903702
Norm Quadratic Average: 0.5466500520706177
Nearest Class Center Accuracy: 0.9999833333333333

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9986746311187744
Inter Cos: -0.05751292034983635
Norm Quadratic Average: 1.1284143924713135
Nearest Class Center Accuracy: 0.9999833333333333

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.1466896533966064
Linear Weight Rank: 10
Intra Cos: 0.9992444515228271
Inter Cos: -0.019651424139738083
Norm Quadratic Average: 25.63260841369629
Nearest Class Center Accuracy: 0.9999833333333333

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.1490678787231445
Linear Weight Rank: 1430
Intra Cos: 0.9992338418960571
Inter Cos: 0.014292948879301548
Norm Quadratic Average: 17.183839797973633
Nearest Class Center Accuracy: 0.9999833333333333

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.1494498252868652
Linear Weight Rank: 9
Intra Cos: 0.9992467164993286
Inter Cos: 0.030966537073254585
Norm Quadratic Average: 11.762873649597168
Nearest Class Center Accuracy: 0.9999833333333333

Output Layer:
Intra Cos: 0.9993365406990051
Inter Cos: 0.053982190787792206
Norm Quadratic Average: 8.476125717163086
Nearest Class Center Accuracy: 0.9999833333333333

Test Set:
Average Loss: 0.018326515563204884
Accuracy: 0.9962
NC1 Within Class Collapse: 0.07700140029191971
NC2 Equinorm: Features: 0.02404084987938404, Weights: 0.005676326807588339
NC2 Equiangle: Features: 0.056343258751763235, Weights: 0.02058345079421997
NC3 Self-Duality: 0.00782005675137043
NC4 NCC Mismatch: 9.999999999998899e-05

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219582915306091
Inter Cos: 0.12048851698637009
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: 0.06769979745149612
Inter Cos: 0.0793709084391594
Norm Quadratic Average: 2.5893900394439697
Nearest Class Center Accuracy: 0.8201

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11558476090431213
Inter Cos: 0.10136430710554123
Norm Quadratic Average: 1.4058266878128052
Nearest Class Center Accuracy: 0.8839

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11500454694032669
Inter Cos: 0.10100598633289337
Norm Quadratic Average: 1.0666190385818481
Nearest Class Center Accuracy: 0.8862

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19507752358913422
Inter Cos: 0.13670401275157928
Norm Quadratic Average: 0.6646602749824524
Nearest Class Center Accuracy: 0.938

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25609639286994934
Inter Cos: 0.14275231957435608
Norm Quadratic Average: 0.4703182876110077
Nearest Class Center Accuracy: 0.9627

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.32762372493743896
Inter Cos: 0.16051998734474182
Norm Quadratic Average: 0.37694886326789856
Nearest Class Center Accuracy: 0.9717

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3669023811817169
Inter Cos: 0.1620304137468338
Norm Quadratic Average: 0.33803096413612366
Nearest Class Center Accuracy: 0.9744

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4239237904548645
Inter Cos: 0.15190434455871582
Norm Quadratic Average: 0.19487892091274261
Nearest Class Center Accuracy: 0.9891

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6234120726585388
Inter Cos: 0.21056169271469116
Norm Quadratic Average: 0.11607631295919418
Nearest Class Center Accuracy: 0.9934

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8253167271614075
Inter Cos: 0.2169305831193924
Norm Quadratic Average: 0.11844223737716675
Nearest Class Center Accuracy: 0.9944

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.870745837688446
Inter Cos: 0.13356201350688934
Norm Quadratic Average: 0.14611954987049103
Nearest Class Center Accuracy: 0.9956

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9094346761703491
Inter Cos: 0.2293524593114853
Norm Quadratic Average: 0.20665228366851807
Nearest Class Center Accuracy: 0.9956

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9727275967597961
Inter Cos: 0.06358955055475235
Norm Quadratic Average: 0.257642537355423
Nearest Class Center Accuracy: 0.9961

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9791908264160156
Inter Cos: -0.01828945241868496
Norm Quadratic Average: 0.5445736050605774
Nearest Class Center Accuracy: 0.9961

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9796375632286072
Inter Cos: -0.04861370101571083
Norm Quadratic Average: 1.1240520477294922
Nearest Class Center Accuracy: 0.9963

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.1466896533966064
Linear Weight Rank: 10
Intra Cos: 0.9809092283248901
Inter Cos: -0.018792465329170227
Norm Quadratic Average: 25.538280487060547
Nearest Class Center Accuracy: 0.9963

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.1490678787231445
Linear Weight Rank: 1430
Intra Cos: 0.9817177653312683
Inter Cos: 0.02175978757441044
Norm Quadratic Average: 17.121585845947266
Nearest Class Center Accuracy: 0.9963

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.1494498252868652
Linear Weight Rank: 9
Intra Cos: 0.9821807742118835
Inter Cos: 0.04062042757868767
Norm Quadratic Average: 11.721134185791016
Nearest Class Center Accuracy: 0.9963

Output Layer:
Intra Cos: 0.9827636480331421
Inter Cos: 0.06346350163221359
Norm Quadratic Average: 8.446151733398438
Nearest Class Center Accuracy: 0.9962

