Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_265358_test_samples_None_train_samples_None_weight_decay_0.02.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: 23.567670822143555
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10476595163345337
Inter Cos: 0.10992099344730377
Norm Quadratic Average: 2.127671957015991
Nearest Class Center Accuracy: 0.8525833333333334

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1776096522808075
Inter Cos: 0.14376361668109894
Norm Quadratic Average: 1.0940980911254883
Nearest Class Center Accuracy: 0.9085

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23075778782367706
Inter Cos: 0.16729842126369476
Norm Quadratic Average: 0.6336688995361328
Nearest Class Center Accuracy: 0.9475833333333333

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.32318395376205444
Inter Cos: 0.13862964510917664
Norm Quadratic Average: 0.23234397172927856
Nearest Class Center Accuracy: 0.9874833333333334

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7030636072158813
Inter Cos: 0.18390566110610962
Norm Quadratic Average: 0.18116821348667145
Nearest Class Center Accuracy: 0.9994666666666666

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8893832564353943
Inter Cos: 0.3517625033855438
Norm Quadratic Average: 0.2773153781890869
Nearest Class Center Accuracy: 0.9999666666666667

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.983418881893158
Inter Cos: 0.33939459919929504
Norm Quadratic Average: 0.6749705672264099
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.9608869552612305
Linear Weight Rank: 8
Intra Cos: 0.9963092803955078
Inter Cos: 0.3694084584712982
Norm Quadratic Average: 23.15619659423828
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.9617862701416016
Linear Weight Rank: 1339
Intra Cos: 0.9975513815879822
Inter Cos: 0.3242820203304291
Norm Quadratic Average: 15.990985870361328
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9630695581436157
Linear Weight Rank: 8
Intra Cos: 0.9983078837394714
Inter Cos: 0.26499518752098083
Norm Quadratic Average: 11.215864181518555
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9982256293296814
Inter Cos: 0.27175822854042053
Norm Quadratic Average: 8.409817695617676
Nearest Class Center Accuracy: 0.9999833333333333

Test Set:
Average Loss: 0.02352041540145874
Accuracy: 0.9957
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.03226085007190704, Weights: 0.010164876468479633
NC2 Equiangle: Features: 0.16272194120619032, Weights: 0.15819424523247613
NC3 Self-Duality: 0.04335835576057434
NC4 NCC Mismatch: 0.00039999999999995595

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219583660364151
Inter Cos: 0.12048852443695068
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: 0.11500882357358932
Inter Cos: 0.10954685509204865
Norm Quadratic Average: 2.120469093322754
Nearest Class Center Accuracy: 0.8649

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18981505930423737
Inter Cos: 0.14103305339813232
Norm Quadratic Average: 1.0902374982833862
Nearest Class Center Accuracy: 0.9187

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24594414234161377
Inter Cos: 0.1633835881948471
Norm Quadratic Average: 0.6329828500747681
Nearest Class Center Accuracy: 0.9527

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3357069492340088
Inter Cos: 0.1488519310951233
Norm Quadratic Average: 0.2320997565984726
Nearest Class Center Accuracy: 0.985

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7051944136619568
Inter Cos: 0.19982750713825226
Norm Quadratic Average: 0.1813351958990097
Nearest Class Center Accuracy: 0.9941

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8814991116523743
Inter Cos: 0.36044228076934814
Norm Quadratic Average: 0.27715015411376953
Nearest Class Center Accuracy: 0.9957

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9715158343315125
Inter Cos: 0.3345292806625366
Norm Quadratic Average: 0.6722286939620972
Nearest Class Center Accuracy: 0.9955

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.9608869552612305
Linear Weight Rank: 8
Intra Cos: 0.9814896583557129
Inter Cos: 0.36445334553718567
Norm Quadratic Average: 23.051950454711914
Nearest Class Center Accuracy: 0.9955

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.9617862701416016
Linear Weight Rank: 1339
Intra Cos: 0.9830394983291626
Inter Cos: 0.31990689039230347
Norm Quadratic Average: 15.917244911193848
Nearest Class Center Accuracy: 0.9956

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9630695581436157
Linear Weight Rank: 8
Intra Cos: 0.9838881492614746
Inter Cos: 0.26146987080574036
Norm Quadratic Average: 11.162952423095703
Nearest Class Center Accuracy: 0.9957

Output Layer:
Intra Cos: 0.9854066967964172
Inter Cos: 0.2692694067955017
Norm Quadratic Average: 8.370616912841797
Nearest Class Center Accuracy: 0.9958

