Model save path: ./New_Models/bn_False_dataset_CIFAR10_epochs_200_lr_0.01_model_type_vgg11_rand_seed_979323_test_samples_None_train_samples_None_weight_decay_0.01.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0198909230530262
Inter Cos: 0.10477276891469955
Norm Quadratic Average: 27.59718894958496
Nearest Class Center Accuracy: 0.26968

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.023183520883321762
Inter Cos: 0.10448596626520157
Norm Quadratic Average: 24.548179626464844
Nearest Class Center Accuracy: 0.34164

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.030483944341540337
Inter Cos: 0.10818948596715927
Norm Quadratic Average: 17.523296356201172
Nearest Class Center Accuracy: 0.42568

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.032563481479883194
Inter Cos: 0.08750331401824951
Norm Quadratic Average: 9.646439552307129
Nearest Class Center Accuracy: 0.53604

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.05569755658507347
Inter Cos: 0.10450701415538788
Norm Quadratic Average: 1.8299355506896973
Nearest Class Center Accuracy: 0.6426

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.284796804189682
Inter Cos: 0.43893155455589294
Norm Quadratic Average: 0.6967818737030029
Nearest Class Center Accuracy: 0.73986

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5072782635688782
Inter Cos: 0.5235982537269592
Norm Quadratic Average: 0.6199326515197754
Nearest Class Center Accuracy: 0.92152

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6698185205459595
Inter Cos: 0.5169193744659424
Norm Quadratic Average: 1.000502347946167
Nearest Class Center Accuracy: 0.98508

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.984708547592163
Linear Weight Rank: 6
Intra Cos: 0.7293193340301514
Inter Cos: 0.4295193552970886
Norm Quadratic Average: 8.552295684814453
Nearest Class Center Accuracy: 0.99662

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.9845001697540283
Linear Weight Rank: 2744
Intra Cos: 0.7527297139167786
Inter Cos: 0.4086288809776306
Norm Quadratic Average: 10.580436706542969
Nearest Class Center Accuracy: 0.99866

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.9828248023986816
Linear Weight Rank: 9
Intra Cos: 0.7860102653503418
Inter Cos: 0.3773707449436188
Norm Quadratic Average: 12.12065601348877
Nearest Class Center Accuracy: 0.99952

Output Layer:
Intra Cos: 0.7850368618965149
Inter Cos: 0.4022102952003479
Norm Quadratic Average: 15.906940460205078
Nearest Class Center Accuracy: 0.9997

Test Set:
Average Loss: 0.9091401558876038
Accuracy: 0.7653
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.253309428691864, Weights: 0.05480283126235008
NC2 Equiangle: Features: 0.3740116967095269, Weights: 0.24708682166205512
NC3 Self-Duality: 0.20890110731124878
NC4 NCC Mismatch: 0.0676

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018526077270507812
Inter Cos: 0.1042705774307251
Norm Quadratic Average: 27.550140380859375
Nearest Class Center Accuracy: 0.284

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.023786429315805435
Inter Cos: 0.1052539274096489
Norm Quadratic Average: 24.510425567626953
Nearest Class Center Accuracy: 0.3582

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.029502371326088905
Inter Cos: 0.10943180322647095
Norm Quadratic Average: 17.534000396728516
Nearest Class Center Accuracy: 0.4379

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03081825003027916
Inter Cos: 0.08774513751268387
Norm Quadratic Average: 9.662014961242676
Nearest Class Center Accuracy: 0.5427

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.049872104078531265
Inter Cos: 0.1055065169930458
Norm Quadratic Average: 1.8323218822479248
Nearest Class Center Accuracy: 0.6342

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25565531849861145
Inter Cos: 0.4356008768081665
Norm Quadratic Average: 0.6956467628479004
Nearest Class Center Accuracy: 0.6621

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3632148504257202
Inter Cos: 0.522863507270813
Norm Quadratic Average: 0.6144582629203796
Nearest Class Center Accuracy: 0.7262

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4387018084526062
Inter Cos: 0.5348260998725891
Norm Quadratic Average: 0.9844597578048706
Nearest Class Center Accuracy: 0.7566

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.984708547592163
Linear Weight Rank: 6
Intra Cos: 0.43228036165237427
Inter Cos: 0.4704468250274658
Norm Quadratic Average: 8.373917579650879
Nearest Class Center Accuracy: 0.7607

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.9845001697540283
Linear Weight Rank: 2744
Intra Cos: 0.41258883476257324
Inter Cos: 0.42866775393486023
Norm Quadratic Average: 10.313504219055176
Nearest Class Center Accuracy: 0.7593

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.9828248023986816
Linear Weight Rank: 9
Intra Cos: 0.40828201174736023
Inter Cos: 0.39187711477279663
Norm Quadratic Average: 11.76401138305664
Nearest Class Center Accuracy: 0.7555

Output Layer:
Intra Cos: 0.38776275515556335
Inter Cos: 0.37882348895072937
Norm Quadratic Average: 15.388359069824219
Nearest Class Center Accuracy: 0.7501

