Model save path: ./New_Models/bn_False_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: 0.12528204917907715
Inter Cos: 0.15626998245716095
Norm Quadratic Average: 36.27130889892578
Nearest Class Center Accuracy: 0.8004166666666667

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.154812753200531
Inter Cos: 0.19220617413520813
Norm Quadratic Average: 40.33884811401367
Nearest Class Center Accuracy: 0.7725

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19100134074687958
Inter Cos: 0.2262219786643982
Norm Quadratic Average: 50.49729919433594
Nearest Class Center Accuracy: 0.79145

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17357581853866577
Inter Cos: 0.24363593757152557
Norm Quadratic Average: 32.33826446533203
Nearest Class Center Accuracy: 0.8259833333333333

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22597584128379822
Inter Cos: 0.31451377272605896
Norm Quadratic Average: 20.9736270904541
Nearest Class Center Accuracy: 0.8750833333333333

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3875524401664734
Inter Cos: 0.4376833140850067
Norm Quadratic Average: 11.843976020812988
Nearest Class Center Accuracy: 0.90965

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5652605295181274
Inter Cos: 0.4669301509857178
Norm Quadratic Average: 10.844242095947266
Nearest Class Center Accuracy: 0.9504666666666667

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.657274603843689
Linear Weight Rank: 6
Intra Cos: 0.6492832899093628
Inter Cos: 0.41215455532073975
Norm Quadratic Average: 46.99369430541992
Nearest Class Center Accuracy: 0.9726666666666667

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.6601403951644897
Linear Weight Rank: 2750
Intra Cos: 0.6677483916282654
Inter Cos: 0.3989000916481018
Norm Quadratic Average: 31.590368270874023
Nearest Class Center Accuracy: 0.9765333333333334

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.654747486114502
Linear Weight Rank: 9
Intra Cos: 0.6855551600456238
Inter Cos: 0.36895355582237244
Norm Quadratic Average: 20.23912239074707
Nearest Class Center Accuracy: 0.9767

Output Layer:
Intra Cos: 0.6993861794471741
Inter Cos: 0.3938163220882416
Norm Quadratic Average: 14.403162002563477
Nearest Class Center Accuracy: 0.9766

Test Set:
Average Loss: 0.06385776417255401
Accuracy: 0.9816
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.17541788518428802, Weights: 0.048959456384181976
NC2 Equiangle: Features: 0.3007473203870985, Weights: 0.21737386915418838
NC3 Self-Duality: 0.11428796499967575
NC4 NCC Mismatch: 0.012800000000000034

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: 0.13867981731891632
Inter Cos: 0.171115443110466
Norm Quadratic Average: 36.353546142578125
Nearest Class Center Accuracy: 0.818

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17111438512802124
Inter Cos: 0.21203254163265228
Norm Quadratic Average: 40.339263916015625
Nearest Class Center Accuracy: 0.7909

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20525747537612915
Inter Cos: 0.2475372552871704
Norm Quadratic Average: 50.48281478881836
Nearest Class Center Accuracy: 0.8107

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1831260621547699
Inter Cos: 0.24004940688610077
Norm Quadratic Average: 32.290287017822266
Nearest Class Center Accuracy: 0.8442

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23748858273029327
Inter Cos: 0.3211413621902466
Norm Quadratic Average: 20.995315551757812
Nearest Class Center Accuracy: 0.8885

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4086405336856842
Inter Cos: 0.435014933347702
Norm Quadratic Average: 11.89672565460205
Nearest Class Center Accuracy: 0.9173

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5760233402252197
Inter Cos: 0.4544532001018524
Norm Quadratic Average: 10.935988426208496
Nearest Class Center Accuracy: 0.9528

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.657274603843689
Linear Weight Rank: 6
Intra Cos: 0.6571641564369202
Inter Cos: 0.39301031827926636
Norm Quadratic Average: 47.520835876464844
Nearest Class Center Accuracy: 0.971

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.6601403951644897
Linear Weight Rank: 2750
Intra Cos: 0.6667392253875732
Inter Cos: 0.4112730324268341
Norm Quadratic Average: 32.01288604736328
Nearest Class Center Accuracy: 0.9763

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.654747486114502
Linear Weight Rank: 9
Intra Cos: 0.6754761934280396
Inter Cos: 0.3786098062992096
Norm Quadratic Average: 20.53292465209961
Nearest Class Center Accuracy: 0.9768

Output Layer:
Intra Cos: 0.6795596480369568
Inter Cos: 0.41164207458496094
Norm Quadratic Average: 14.625971794128418
Nearest Class Center Accuracy: 0.9755

