Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_979323_test_samples_None_train_samples_None_weight_decay_0.03.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: 0.10967151820659637
Norm Quadratic Average: 23.567676544189453
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10773785412311554
Inter Cos: 0.11395382136106491
Norm Quadratic Average: 1.8202308416366577
Nearest Class Center Accuracy: 0.8548166666666667

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1812419593334198
Inter Cos: 0.14927838742733002
Norm Quadratic Average: 0.9543263912200928
Nearest Class Center Accuracy: 0.9116

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2343093901872635
Inter Cos: 0.15964274108409882
Norm Quadratic Average: 0.6186414957046509
Nearest Class Center Accuracy: 0.9491166666666667

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3314555287361145
Inter Cos: 0.13765405118465424
Norm Quadratic Average: 0.24183572828769684
Nearest Class Center Accuracy: 0.9873166666666666

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7023182511329651
Inter Cos: 0.17606797814369202
Norm Quadratic Average: 0.1733914464712143
Nearest Class Center Accuracy: 0.9987833333333334

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8843517899513245
Inter Cos: 0.3940836191177368
Norm Quadratic Average: 0.21400326490402222
Nearest Class Center Accuracy: 0.99995

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9874982237815857
Inter Cos: 0.46323302388191223
Norm Quadratic Average: 0.5196099281311035
Nearest Class Center Accuracy: 0.99995

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.8654627799987793
Linear Weight Rank: 6
Intra Cos: 0.9972707629203796
Inter Cos: 0.3944563865661621
Norm Quadratic Average: 19.866554260253906
Nearest Class Center Accuracy: 0.9999666666666667

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.8662605285644531
Linear Weight Rank: 1229
Intra Cos: 0.997803270816803
Inter Cos: 0.3243252635002136
Norm Quadratic Average: 14.949881553649902
Nearest Class Center Accuracy: 0.9999666666666667

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.867220163345337
Linear Weight Rank: 6
Intra Cos: 0.9978905320167542
Inter Cos: 0.23306775093078613
Norm Quadratic Average: 11.426105499267578
Nearest Class Center Accuracy: 0.9999666666666667

Output Layer:
Intra Cos: 0.9979326128959656
Inter Cos: 0.3290281295776367
Norm Quadratic Average: 9.700783729553223
Nearest Class Center Accuracy: 0.9999666666666667

Test Set:
Average Loss: 0.03045626632720232
Accuracy: 0.9952
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.03177991136908531, Weights: 0.031395748257637024
NC2 Equiangle: Features: 0.2787504620022244, Weights: 0.2793475892808702
NC3 Self-Duality: 0.00314080948010087
NC4 NCC Mismatch: 0.00019999999999997797

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219582170248032
Inter Cos: 0.12048851698637009
Norm Quadratic Average: 23.595197677612305
Nearest Class Center Accuracy: 0.8229

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11797604709863663
Inter Cos: 0.11418335139751434
Norm Quadratic Average: 1.813170075416565
Nearest Class Center Accuracy: 0.8678

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19369424879550934
Inter Cos: 0.14643266797065735
Norm Quadratic Average: 0.9510684609413147
Nearest Class Center Accuracy: 0.9205

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24638257920742035
Inter Cos: 0.1562461405992508
Norm Quadratic Average: 0.6180185675621033
Nearest Class Center Accuracy: 0.9523

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.34494203329086304
Inter Cos: 0.14671848714351654
Norm Quadratic Average: 0.24154046177864075
Nearest Class Center Accuracy: 0.9859

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7057541012763977
Inter Cos: 0.18827928602695465
Norm Quadratic Average: 0.17385178804397583
Nearest Class Center Accuracy: 0.994

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8750628232955933
Inter Cos: 0.3968355655670166
Norm Quadratic Average: 0.21420921385288239
Nearest Class Center Accuracy: 0.9942

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9750009775161743
Inter Cos: 0.4518667459487915
Norm Quadratic Average: 0.5176649689674377
Nearest Class Center Accuracy: 0.9954

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.8654627799987793
Linear Weight Rank: 6
Intra Cos: 0.9830856323242188
Inter Cos: 0.3980129063129425
Norm Quadratic Average: 19.782888412475586
Nearest Class Center Accuracy: 0.9954

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.8662605285644531
Linear Weight Rank: 1229
Intra Cos: 0.9832753539085388
Inter Cos: 0.3287917673587799
Norm Quadratic Average: 14.886106491088867
Nearest Class Center Accuracy: 0.9954

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.867220163345337
Linear Weight Rank: 6
Intra Cos: 0.9833022952079773
Inter Cos: 0.23867858946323395
Norm Quadratic Average: 11.376405715942383
Nearest Class Center Accuracy: 0.9953

Output Layer:
Intra Cos: 0.9834059476852417
Inter Cos: 0.3236040472984314
Norm Quadratic Average: 9.656594276428223
Nearest Class Center Accuracy: 0.9951

