Model save path: ./New_Models/bn_False_dataset_CIFAR10_epochs_200_lr_0.01_model_type_vgg11_rand_seed_265358_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: 27.59717559814453
Nearest Class Center Accuracy: 0.26968

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.024076832458376884
Inter Cos: 0.1031133309006691
Norm Quadratic Average: 27.998918533325195
Nearest Class Center Accuracy: 0.33794

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.030412355437874794
Inter Cos: 0.1112360954284668
Norm Quadratic Average: 25.507186889648438
Nearest Class Center Accuracy: 0.40712

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0320400670170784
Inter Cos: 0.09113464504480362
Norm Quadratic Average: 21.018465042114258
Nearest Class Center Accuracy: 0.49572

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.038175150752067566
Inter Cos: 0.08317524194717407
Norm Quadratic Average: 5.993685245513916
Nearest Class Center Accuracy: 0.59938

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11130242794752121
Inter Cos: 0.17847563326358795
Norm Quadratic Average: 2.003997802734375
Nearest Class Center Accuracy: 0.67352

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3211649954319
Inter Cos: 0.45892077684402466
Norm Quadratic Average: 0.8488469123840332
Nearest Class Center Accuracy: 0.77882

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5385875105857849
Inter Cos: 0.579447865486145
Norm Quadratic Average: 1.035068392753601
Nearest Class Center Accuracy: 0.93592

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 3.418088912963867
Linear Weight Rank: 78
Intra Cos: 0.6979166269302368
Inter Cos: 0.5167719125747681
Norm Quadratic Average: 7.9554829597473145
Nearest Class Center Accuracy: 0.98696

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 3.423711061477661
Linear Weight Rank: 2856
Intra Cos: 0.7499235272407532
Inter Cos: 0.41830384731292725
Norm Quadratic Average: 9.910052299499512
Nearest Class Center Accuracy: 0.99766

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 3.4166452884674072
Linear Weight Rank: 9
Intra Cos: 0.7807821035385132
Inter Cos: 0.30052027106285095
Norm Quadratic Average: 11.835904121398926
Nearest Class Center Accuracy: 0.99926

Output Layer:
Intra Cos: 0.7748653888702393
Inter Cos: 0.3102807402610779
Norm Quadratic Average: 16.26461410522461
Nearest Class Center Accuracy: 0.99976

Test Set:
Average Loss: 1.0412625968933105
Accuracy: 0.7566
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.22634707391262054, Weights: 0.06820780038833618
NC2 Equiangle: Features: 0.35944476657443575, Weights: 0.19727753533257378
NC3 Self-Duality: 0.23239392042160034
NC4 NCC Mismatch: 0.0696

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: 27.550134658813477
Nearest Class Center Accuracy: 0.284

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02357586659491062
Inter Cos: 0.103814497590065
Norm Quadratic Average: 27.95545196533203
Nearest Class Center Accuracy: 0.3565

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.029591277241706848
Inter Cos: 0.11274494230747223
Norm Quadratic Average: 25.51142692565918
Nearest Class Center Accuracy: 0.4164

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.030523430556058884
Inter Cos: 0.09144344925880432
Norm Quadratic Average: 21.04493522644043
Nearest Class Center Accuracy: 0.5031

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03429670259356499
Inter Cos: 0.08386573940515518
Norm Quadratic Average: 6.003879547119141
Nearest Class Center Accuracy: 0.5935

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0978127270936966
Inter Cos: 0.17820240557193756
Norm Quadratic Average: 2.006765127182007
Nearest Class Center Accuracy: 0.6414

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2893109619617462
Inter Cos: 0.4444320499897003
Norm Quadratic Average: 0.8488561511039734
Nearest Class Center Accuracy: 0.6667

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4340399205684662
Inter Cos: 0.5638752579689026
Norm Quadratic Average: 1.0272897481918335
Nearest Class Center Accuracy: 0.728

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 3.418088912963867
Linear Weight Rank: 78
Intra Cos: 0.44782593846321106
Inter Cos: 0.5220585465431213
Norm Quadratic Average: 7.840956687927246
Nearest Class Center Accuracy: 0.7527

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 3.423711061477661
Linear Weight Rank: 2856
Intra Cos: 0.4319281578063965
Inter Cos: 0.4524271488189697
Norm Quadratic Average: 9.71115779876709
Nearest Class Center Accuracy: 0.7552

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 3.4166452884674072
Linear Weight Rank: 9
Intra Cos: 0.4101882576942444
Inter Cos: 0.36989715695381165
Norm Quadratic Average: 11.549474716186523
Nearest Class Center Accuracy: 0.7544

Output Layer:
Intra Cos: 0.39227771759033203
Inter Cos: 0.35075247287750244
Norm Quadratic Average: 15.809420585632324
Nearest Class Center Accuracy: 0.7461

