Model save path: ./New_Models/bn_False_dataset_CIFAR10_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(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01989092119038105
Inter Cos: 0.10477277636528015
Norm Quadratic Average: 27.597183227539062
Nearest Class Center Accuracy: 0.26968

Layer 1: Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.019895952194929123
Inter Cos: 0.09141529351472855
Norm Quadratic Average: 30.631328582763672
Nearest Class Center Accuracy: 0.33166

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.024285219609737396
Inter Cos: 0.10409320145845413
Norm Quadratic Average: 25.667980194091797
Nearest Class Center Accuracy: 0.4245

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.029243802651762962
Inter Cos: 0.08929359912872314
Norm Quadratic Average: 27.01589584350586
Nearest Class Center Accuracy: 0.50516

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02208295278251171
Inter Cos: 0.0652536004781723
Norm Quadratic Average: 11.389735221862793
Nearest Class Center Accuracy: 0.59374

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.026124941185116768
Inter Cos: 0.05173318460583687
Norm Quadratic Average: 3.9242029190063477
Nearest Class Center Accuracy: 0.647

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06628388911485672
Inter Cos: 0.09537720680236816
Norm Quadratic Average: 0.8959581255912781
Nearest Class Center Accuracy: 0.73764

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25739291310310364
Inter Cos: 0.2651771306991577
Norm Quadratic Average: 0.3846641778945923
Nearest Class Center Accuracy: 0.84882

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4202687740325928
Inter Cos: 0.4067644476890564
Norm Quadratic Average: 0.2593632638454437
Nearest Class Center Accuracy: 0.87822

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5656439661979675
Inter Cos: 0.5581721067428589
Norm Quadratic Average: 0.2679999768733978
Nearest Class Center Accuracy: 0.94252

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.602294385433197
Inter Cos: 0.5831226110458374
Norm Quadratic Average: 0.4175679385662079
Nearest Class Center Accuracy: 0.95732

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6282075643539429
Inter Cos: 0.6072850227355957
Norm Quadratic Average: 0.7168952226638794
Nearest Class Center Accuracy: 0.95568

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6705494523048401
Inter Cos: 0.6630297899246216
Norm Quadratic Average: 0.8544437289237976
Nearest Class Center Accuracy: 0.95748

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8030515909194946
Inter Cos: 0.7800636887550354
Norm Quadratic Average: 1.3301777839660645
Nearest Class Center Accuracy: 0.96796

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8302669525146484
Inter Cos: 0.7764082551002502
Norm Quadratic Average: 2.4346039295196533
Nearest Class Center Accuracy: 0.9819

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8324263095855713
Inter Cos: 0.7341414093971252
Norm Quadratic Average: 4.465884208679199
Nearest Class Center Accuracy: 0.98988

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.15193247795105
Linear Weight Rank: 95
Intra Cos: 0.8742291927337646
Inter Cos: 0.5223430395126343
Norm Quadratic Average: 28.27130699157715
Nearest Class Center Accuracy: 0.99348

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.1801846027374268
Linear Weight Rank: 2770
Intra Cos: 0.8835991024971008
Inter Cos: 0.47688940167427063
Norm Quadratic Average: 25.869901657104492
Nearest Class Center Accuracy: 0.99826

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.153419017791748
Linear Weight Rank: 9
Intra Cos: 0.8794654011726379
Inter Cos: 0.4155283570289612
Norm Quadratic Average: 20.554798126220703
Nearest Class Center Accuracy: 0.99974

Output Layer:
Intra Cos: 0.9067614674568176
Inter Cos: 0.4356587529182434
Norm Quadratic Average: 17.714641571044922
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.8077010919570923
Accuracy: 0.8156
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.21764114499092102, Weights: 0.07039929181337357
NC2 Equiangle: Features: 0.37349026997884116, Weights: 0.17743599149915906
NC3 Self-Duality: 0.2636374235153198
NC4 NCC Mismatch: 0.037900000000000045

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018526075407862663
Inter Cos: 0.1042705774307251
Norm Quadratic Average: 27.550134658813477
Nearest Class Center Accuracy: 0.284

Layer 1: Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.017342861741781235
Inter Cos: 0.09185086190700531
Norm Quadratic Average: 30.59542465209961
Nearest Class Center Accuracy: 0.3458

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.023593435063958168
Inter Cos: 0.10469553619623184
Norm Quadratic Average: 25.660856246948242
Nearest Class Center Accuracy: 0.4385

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.027293452993035316
Inter Cos: 0.08987225592136383
Norm Quadratic Average: 27.025104522705078
Nearest Class Center Accuracy: 0.5163

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.020355049520730972
Inter Cos: 0.066096231341362
Norm Quadratic Average: 11.404102325439453
Nearest Class Center Accuracy: 0.5981

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.024079561233520508
Inter Cos: 0.051680926233530045
Norm Quadratic Average: 3.9308199882507324
Nearest Class Center Accuracy: 0.6414

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06056538224220276
Inter Cos: 0.09743023663759232
Norm Quadratic Average: 0.8960597515106201
Nearest Class Center Accuracy: 0.7085

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2274990975856781
Inter Cos: 0.26693907380104065
Norm Quadratic Average: 0.3831392824649811
Nearest Class Center Accuracy: 0.7785

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3583744466304779
Inter Cos: 0.3774615228176117
Norm Quadratic Average: 0.25739267468452454
Nearest Class Center Accuracy: 0.7785

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.44003310799598694
Inter Cos: 0.4916456639766693
Norm Quadratic Average: 0.264909029006958
Nearest Class Center Accuracy: 0.8026

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.44511744379997253
Inter Cos: 0.5015550851821899
Norm Quadratic Average: 0.41190603375434875
Nearest Class Center Accuracy: 0.8001

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.45556387305259705
Inter Cos: 0.5160547494888306
Norm Quadratic Average: 0.7065819501876831
Nearest Class Center Accuracy: 0.7944

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.44187402725219727
Inter Cos: 0.6044350862503052
Norm Quadratic Average: 0.840620219707489
Nearest Class Center Accuracy: 0.7868

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.49298402667045593
Inter Cos: 0.6436377167701721
Norm Quadratic Average: 1.3062403202056885
Nearest Class Center Accuracy: 0.7892

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5239166021347046
Inter Cos: 0.6232228875160217
Norm Quadratic Average: 2.389815092086792
Nearest Class Center Accuracy: 0.7978

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.525044858455658
Inter Cos: 0.613553524017334
Norm Quadratic Average: 4.378224849700928
Nearest Class Center Accuracy: 0.8023

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.15193247795105
Linear Weight Rank: 95
Intra Cos: 0.6213977336883545
Inter Cos: 0.521414041519165
Norm Quadratic Average: 27.707748413085938
Nearest Class Center Accuracy: 0.8042

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.1801846027374268
Linear Weight Rank: 2770
Intra Cos: 0.5746252536773682
Inter Cos: 0.47976458072662354
Norm Quadratic Average: 25.251922607421875
Nearest Class Center Accuracy: 0.8075

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.153419017791748
Linear Weight Rank: 9
Intra Cos: 0.5356766581535339
Inter Cos: 0.4277538061141968
Norm Quadratic Average: 20.034465789794922
Nearest Class Center Accuracy: 0.8113

Output Layer:
Intra Cos: 0.5120611786842346
Inter Cos: 0.4238129258155823
Norm Quadratic Average: 17.20928192138672
Nearest Class Center Accuracy: 0.8128

