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_0.0005.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: 0.09421883523464203
Inter Cos: 0.09953655302524567
Norm Quadratic Average: 11.424817085266113
Nearest Class Center Accuracy: 0.8527666666666667

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1608278602361679
Inter Cos: 0.12817366421222687
Norm Quadratic Average: 8.073770523071289
Nearest Class Center Accuracy: 0.9072333333333333

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19856801629066467
Inter Cos: 0.14156317710876465
Norm Quadratic Average: 8.493452072143555
Nearest Class Center Accuracy: 0.93715

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25636154413223267
Inter Cos: 0.1144200935959816
Norm Quadratic Average: 5.635093688964844
Nearest Class Center Accuracy: 0.9824833333333334

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3784196972846985
Inter Cos: 0.1377992480993271
Norm Quadratic Average: 6.428516387939453
Nearest Class Center Accuracy: 0.9962666666666666

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5262181758880615
Inter Cos: 0.14257000386714935
Norm Quadratic Average: 4.912806987762451
Nearest Class Center Accuracy: 0.9999166666666667

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8513927459716797
Inter Cos: 0.08982142806053162
Norm Quadratic Average: 3.912400484085083
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 14.683841705322266
Linear Weight Rank: 4031
Intra Cos: 0.9849569201469421
Inter Cos: -0.04056346416473389
Norm Quadratic Average: 41.98176956176758
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 6.2420268058776855
Linear Weight Rank: 3668
Intra Cos: 0.9952700734138489
Inter Cos: -0.017724577337503433
Norm Quadratic Average: 26.821392059326172
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.034841299057007
Linear Weight Rank: 10
Intra Cos: 0.9959558248519897
Inter Cos: -0.0039269402623176575
Norm Quadratic Average: 17.376785278320312
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9978117942810059
Inter Cos: 0.028805498033761978
Norm Quadratic Average: 11.857414245605469
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.02031415398577228
Accuracy: 0.9945
NC1 Within Class Collapse: 0.1372418999671936
NC2 Equinorm: Features: 0.021541835740208626, Weights: 0.007372609805315733
NC2 Equiangle: Features: 0.07076393233405219, Weights: 0.03309334648980035
NC3 Self-Duality: 0.029698381200432777
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: 0.10354696959257126
Inter Cos: 0.09964654594659805
Norm Quadratic Average: 11.357806205749512
Nearest Class Center Accuracy: 0.8642

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17062006890773773
Inter Cos: 0.12668290734291077
Norm Quadratic Average: 8.024511337280273
Nearest Class Center Accuracy: 0.9183

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2103293240070343
Inter Cos: 0.13934606313705444
Norm Quadratic Average: 8.452974319458008
Nearest Class Center Accuracy: 0.9429

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2689213156700134
Inter Cos: 0.11546800285577774
Norm Quadratic Average: 5.614558696746826
Nearest Class Center Accuracy: 0.9804

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3890339136123657
Inter Cos: 0.1535574495792389
Norm Quadratic Average: 6.4113640785217285
Nearest Class Center Accuracy: 0.9905

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5274236798286438
Inter Cos: 0.14245328307151794
Norm Quadratic Average: 4.90354061126709
Nearest Class Center Accuracy: 0.9935

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8404154181480408
Inter Cos: 0.09067801386117935
Norm Quadratic Average: 3.895536184310913
Nearest Class Center Accuracy: 0.9942

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 14.683841705322266
Linear Weight Rank: 4031
Intra Cos: 0.9677144885063171
Inter Cos: -0.027598923072218895
Norm Quadratic Average: 41.70903396606445
Nearest Class Center Accuracy: 0.9945

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 6.2420268058776855
Linear Weight Rank: 3668
Intra Cos: 0.9753575325012207
Inter Cos: -0.005115652922540903
Norm Quadratic Average: 26.636844635009766
Nearest Class Center Accuracy: 0.9944

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.034841299057007
Linear Weight Rank: 10
Intra Cos: 0.9758114218711853
Inter Cos: 0.011218995787203312
Norm Quadratic Average: 17.2584228515625
Nearest Class Center Accuracy: 0.9944

Output Layer:
Intra Cos: 0.9786365032196045
Inter Cos: 0.044190432876348495
Norm Quadratic Average: 11.776317596435547
Nearest Class Center Accuracy: 0.9943

