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_0.0003.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: 0.09395346790552139
Inter Cos: 0.10255936533212662
Norm Quadratic Average: 25.726987838745117
Nearest Class Center Accuracy: 0.8495833333333334

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16326837241649628
Inter Cos: 0.12883353233337402
Norm Quadratic Average: 18.525253295898438
Nearest Class Center Accuracy: 0.9002333333333333

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19219788908958435
Inter Cos: 0.13950592279434204
Norm Quadratic Average: 18.89804458618164
Nearest Class Center Accuracy: 0.9297333333333333

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24623601138591766
Inter Cos: 0.10552987456321716
Norm Quadratic Average: 12.628641128540039
Nearest Class Center Accuracy: 0.9787

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3295404314994812
Inter Cos: 0.11246838420629501
Norm Quadratic Average: 13.830469131469727
Nearest Class Center Accuracy: 0.9936

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4635062515735626
Inter Cos: 0.14629121124744415
Norm Quadratic Average: 10.743948936462402
Nearest Class Center Accuracy: 0.9998666666666667

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7679320573806763
Inter Cos: 0.09388727694749832
Norm Quadratic Average: 8.191893577575684
Nearest Class Center Accuracy: 0.9999833333333333

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 31.687580108642578
Linear Weight Rank: 4031
Intra Cos: 0.9495962262153625
Inter Cos: -0.005165256559848785
Norm Quadratic Average: 68.292724609375
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 12.964882850646973
Linear Weight Rank: 3670
Intra Cos: 0.9848066568374634
Inter Cos: 0.02442029118537903
Norm Quadratic Average: 40.65769958496094
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9286097288131714
Linear Weight Rank: 10
Intra Cos: 0.9883016347885132
Inter Cos: 0.008938191458582878
Norm Quadratic Average: 23.296688079833984
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9963191747665405
Inter Cos: 0.07953693717718124
Norm Quadratic Average: 14.205970764160156
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.018188106989325024
Accuracy: 0.9954
NC1 Within Class Collapse: 0.2175459861755371
NC2 Equinorm: Features: 0.026128361001610756, Weights: 0.011837063357234001
NC2 Equiangle: Features: 0.07007866435580784, Weights: 0.046167045169406465
NC3 Self-Duality: 0.14116162061691284
NC4 NCC Mismatch: 0.0004999999999999449

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: 0.10349805653095245
Inter Cos: 0.1026395857334137
Norm Quadratic Average: 25.572437286376953
Nearest Class Center Accuracy: 0.8606

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17390067875385284
Inter Cos: 0.1267738938331604
Norm Quadratic Average: 18.40860366821289
Nearest Class Center Accuracy: 0.911

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2067139744758606
Inter Cos: 0.136951744556427
Norm Quadratic Average: 18.797901153564453
Nearest Class Center Accuracy: 0.9372

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2603354752063751
Inter Cos: 0.1013549417257309
Norm Quadratic Average: 12.576163291931152
Nearest Class Center Accuracy: 0.9771

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3429638147354126
Inter Cos: 0.11689557880163193
Norm Quadratic Average: 13.789204597473145
Nearest Class Center Accuracy: 0.9891

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.46802765130996704
Inter Cos: 0.148081436753273
Norm Quadratic Average: 10.729331970214844
Nearest Class Center Accuracy: 0.9935

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7608456015586853
Inter Cos: 0.09349530935287476
Norm Quadratic Average: 8.184882164001465
Nearest Class Center Accuracy: 0.995

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 31.687580108642578
Linear Weight Rank: 4031
Intra Cos: 0.9361250400543213
Inter Cos: 0.0030488185584545135
Norm Quadratic Average: 68.20525360107422
Nearest Class Center Accuracy: 0.9952

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 12.964882850646973
Linear Weight Rank: 3670
Intra Cos: 0.9675193428993225
Inter Cos: 0.020252060145139694
Norm Quadratic Average: 40.57661056518555
Nearest Class Center Accuracy: 0.9951

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9286097288131714
Linear Weight Rank: 10
Intra Cos: 0.9678180813789368
Inter Cos: 0.02116357535123825
Norm Quadratic Average: 23.25221061706543
Nearest Class Center Accuracy: 0.9952

Output Layer:
Intra Cos: 0.9813569188117981
Inter Cos: 0.09209536015987396
Norm Quadratic Average: 14.174471855163574
Nearest Class Center Accuracy: 0.9953

