Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg19_rand_seed_265358_test_samples_None_train_samples_None_weight_decay_0.007.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09116753190755844
Inter Cos: 0.10967151820659637
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: 0.05775611102581024
Inter Cos: 0.07806931436061859
Norm Quadratic Average: 2.4913573265075684
Nearest Class Center Accuracy: 0.8050833333333334

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10425610095262527
Inter Cos: 0.09908182173967361
Norm Quadratic Average: 1.5257325172424316
Nearest Class Center Accuracy: 0.8741

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09917934238910675
Inter Cos: 0.09467120468616486
Norm Quadratic Average: 1.2192697525024414
Nearest Class Center Accuracy: 0.8796333333333334

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1734103411436081
Inter Cos: 0.11760911345481873
Norm Quadratic Average: 0.8042680621147156
Nearest Class Center Accuracy: 0.9370666666666667

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22362646460533142
Inter Cos: 0.12896133959293365
Norm Quadratic Average: 0.6025998592376709
Nearest Class Center Accuracy: 0.9607

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2958016097545624
Inter Cos: 0.1458238810300827
Norm Quadratic Average: 0.509731113910675
Nearest Class Center Accuracy: 0.9724833333333334

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.33829259872436523
Inter Cos: 0.14590832591056824
Norm Quadratic Average: 0.43647971749305725
Nearest Class Center Accuracy: 0.9772833333333333

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.41719913482666016
Inter Cos: 0.12676934897899628
Norm Quadratic Average: 0.286023885011673
Nearest Class Center Accuracy: 0.9932833333333333

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6355515122413635
Inter Cos: 0.18526805937290192
Norm Quadratic Average: 0.1908353865146637
Nearest Class Center Accuracy: 0.9984666666666666

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7994197010993958
Inter Cos: 0.21510252356529236
Norm Quadratic Average: 0.1728433221578598
Nearest Class Center Accuracy: 0.9996

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8579229116439819
Inter Cos: 0.10460277646780014
Norm Quadratic Average: 0.18115003407001495
Nearest Class Center Accuracy: 0.9999333333333333

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9143564105033875
Inter Cos: 0.15373265743255615
Norm Quadratic Average: 0.16325344145298004
Nearest Class Center Accuracy: 0.9999666666666667

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9845129251480103
Inter Cos: 0.11555743217468262
Norm Quadratic Average: 0.20433610677719116
Nearest Class Center Accuracy: 0.9999666666666667

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9972966909408569
Inter Cos: 0.16219495236873627
Norm Quadratic Average: 0.48705971240997314
Nearest Class Center Accuracy: 0.9999666666666667

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9986361265182495
Inter Cos: 0.18918918073177338
Norm Quadratic Average: 1.0704954862594604
Nearest Class Center Accuracy: 0.9999666666666667

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.09580397605896
Linear Weight Rank: 9
Intra Cos: 0.999265193939209
Inter Cos: 0.24200284481048584
Norm Quadratic Average: 24.576194763183594
Nearest Class Center Accuracy: 0.9999666666666667

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.0974338054656982
Linear Weight Rank: 1461
Intra Cos: 0.9994230270385742
Inter Cos: 0.23704536259174347
Norm Quadratic Average: 16.97814178466797
Nearest Class Center Accuracy: 0.9999666666666667

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.098256826400757
Linear Weight Rank: 9
Intra Cos: 0.9994823932647705
Inter Cos: 0.21513444185256958
Norm Quadratic Average: 11.968395233154297
Nearest Class Center Accuracy: 0.9999666666666667

Output Layer:
Intra Cos: 0.9996193051338196
Inter Cos: 0.12378323078155518
Norm Quadratic Average: 8.867290496826172
Nearest Class Center Accuracy: 0.9999666666666667

Test Set:
Average Loss: 0.020148180808499457
Accuracy: 0.9956
NC1 Within Class Collapse: 0.08957983553409576
NC2 Equinorm: Features: 0.023666823282837868, Weights: 0.0060427626594901085
NC2 Equiangle: Features: 0.11702360577053494, Weights: 0.08373099433051215
NC3 Self-Duality: 0.0398353710770607
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: 0.12048853933811188
Norm Quadratic Average: 23.595195770263672
Nearest Class Center Accuracy: 0.8229

Layer 1: Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06586890667676926
Inter Cos: 0.08098646253347397
Norm Quadratic Average: 2.479980707168579
Nearest Class Center Accuracy: 0.8154

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11449276655912399
Inter Cos: 0.10101442784070969
Norm Quadratic Average: 1.514510154724121
Nearest Class Center Accuracy: 0.8859

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10865281522274017
Inter Cos: 0.09676750004291534
Norm Quadratic Average: 1.2149871587753296
Nearest Class Center Accuracy: 0.8875

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18572916090488434
Inter Cos: 0.1282830387353897
Norm Quadratic Average: 0.8014646768569946
Nearest Class Center Accuracy: 0.9429

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2400771528482437
Inter Cos: 0.13973993062973022
Norm Quadratic Average: 0.6019231677055359
Nearest Class Center Accuracy: 0.9621

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3139701187610626
Inter Cos: 0.15762223303318024
Norm Quadratic Average: 0.5096244215965271
Nearest Class Center Accuracy: 0.971

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3565249741077423
Inter Cos: 0.15720638632774353
Norm Quadratic Average: 0.4359438121318817
Nearest Class Center Accuracy: 0.9753

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4323759078979492
Inter Cos: 0.13093936443328857
Norm Quadratic Average: 0.28583797812461853
Nearest Class Center Accuracy: 0.989

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6473572254180908
Inter Cos: 0.19776687026023865
Norm Quadratic Average: 0.19116351008415222
Nearest Class Center Accuracy: 0.9927

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7952495217323303
Inter Cos: 0.22739216685295105
Norm Quadratic Average: 0.1733652651309967
Nearest Class Center Accuracy: 0.9942

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8627164959907532
Inter Cos: 0.11614928394556046
Norm Quadratic Average: 0.18124735355377197
Nearest Class Center Accuracy: 0.9953

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9121339917182922
Inter Cos: 0.16256269812583923
Norm Quadratic Average: 0.1628808081150055
Nearest Class Center Accuracy: 0.9949

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9701474905014038
Inter Cos: 0.1152397096157074
Norm Quadratic Average: 0.2035188227891922
Nearest Class Center Accuracy: 0.9958

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9755603075027466
Inter Cos: 0.1652868390083313
Norm Quadratic Average: 0.48529481887817383
Nearest Class Center Accuracy: 0.9956

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9762234091758728
Inter Cos: 0.18738001585006714
Norm Quadratic Average: 1.066888689994812
Nearest Class Center Accuracy: 0.9956

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.09580397605896
Linear Weight Rank: 9
Intra Cos: 0.9772805571556091
Inter Cos: 0.2432338446378708
Norm Quadratic Average: 24.49648094177246
Nearest Class Center Accuracy: 0.9956

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.0974338054656982
Linear Weight Rank: 1461
Intra Cos: 0.9781718850135803
Inter Cos: 0.23813654482364655
Norm Quadratic Average: 16.918928146362305
Nearest Class Center Accuracy: 0.9955

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.098256826400757
Linear Weight Rank: 9
Intra Cos: 0.9785926938056946
Inter Cos: 0.21405135095119476
Norm Quadratic Average: 11.92418098449707
Nearest Class Center Accuracy: 0.9954

Output Layer:
Intra Cos: 0.9792589545249939
Inter Cos: 0.12044163048267365
Norm Quadratic Average: 8.830265998840332
Nearest Class Center Accuracy: 0.9954

