Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_979323_test_samples_None_train_samples_None_weight_decay_0.003.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: 0.12218017876148224
Inter Cos: 0.1479325145483017
Norm Quadratic Average: 40.44145965576172
Nearest Class Center Accuracy: 0.8091833333333334

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18261142075061798
Inter Cos: 0.17689180374145508
Norm Quadratic Average: 41.08283615112305
Nearest Class Center Accuracy: 0.8308

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2139221578836441
Inter Cos: 0.2020776867866516
Norm Quadratic Average: 38.645721435546875
Nearest Class Center Accuracy: 0.8799166666666667

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22025556862354279
Inter Cos: 0.2021515965461731
Norm Quadratic Average: 17.500171661376953
Nearest Class Center Accuracy: 0.9258666666666666

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3209531605243683
Inter Cos: 0.2784665822982788
Norm Quadratic Average: 9.91474723815918
Nearest Class Center Accuracy: 0.9532166666666667

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5336599946022034
Inter Cos: 0.3569031059741974
Norm Quadratic Average: 5.84119176864624
Nearest Class Center Accuracy: 0.97925

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7583364844322205
Inter Cos: 0.40650299191474915
Norm Quadratic Average: 6.166577339172363
Nearest Class Center Accuracy: 0.9918333333333333

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.095676898956299
Linear Weight Rank: 344
Intra Cos: 0.8349927067756653
Inter Cos: 0.33695292472839355
Norm Quadratic Average: 31.464082717895508
Nearest Class Center Accuracy: 0.9963

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.107830762863159
Linear Weight Rank: 2716
Intra Cos: 0.8957894444465637
Inter Cos: 0.342529296875
Norm Quadratic Average: 26.376869201660156
Nearest Class Center Accuracy: 0.9985166666666667

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.094898223876953
Linear Weight Rank: 9
Intra Cos: 0.9127864837646484
Inter Cos: 0.32467955350875854
Norm Quadratic Average: 21.253965377807617
Nearest Class Center Accuracy: 0.9990666666666667

Output Layer:
Intra Cos: 0.9442935585975647
Inter Cos: 0.3915446698665619
Norm Quadratic Average: 19.404876708984375
Nearest Class Center Accuracy: 0.9993666666666666

Test Set:
Average Loss: 0.025086892397142947
Accuracy: 0.9923
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.10540742427110672, Weights: 0.04406210780143738
NC2 Equiangle: Features: 0.26479195488823787, Weights: 0.23310453626844618
NC3 Self-Duality: 0.056242819875478745
NC4 NCC Mismatch: 0.0030999999999999917

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: 0.13572140038013458
Inter Cos: 0.1620766967535019
Norm Quadratic Average: 40.46932601928711
Nearest Class Center Accuracy: 0.8236

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19766715168952942
Inter Cos: 0.18786543607711792
Norm Quadratic Average: 40.9903450012207
Nearest Class Center Accuracy: 0.8485

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22826506197452545
Inter Cos: 0.21842578053474426
Norm Quadratic Average: 38.60567855834961
Nearest Class Center Accuracy: 0.8919

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23142224550247192
Inter Cos: 0.20359013974666595
Norm Quadratic Average: 17.486740112304688
Nearest Class Center Accuracy: 0.9356

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3314991891384125
Inter Cos: 0.3028353750705719
Norm Quadratic Average: 9.925605773925781
Nearest Class Center Accuracy: 0.9603

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5459097623825073
Inter Cos: 0.38657400012016296
Norm Quadratic Average: 5.870284557342529
Nearest Class Center Accuracy: 0.9769

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7609561085700989
Inter Cos: 0.4179726839065552
Norm Quadratic Average: 6.221981048583984
Nearest Class Center Accuracy: 0.9848

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.095676898956299
Linear Weight Rank: 344
Intra Cos: 0.8375692963600159
Inter Cos: 0.3603036105632782
Norm Quadratic Average: 31.76686668395996
Nearest Class Center Accuracy: 0.9884

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.107830762863159
Linear Weight Rank: 2716
Intra Cos: 0.893988311290741
Inter Cos: 0.36514467000961304
Norm Quadratic Average: 26.63877296447754
Nearest Class Center Accuracy: 0.9907

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.094898223876953
Linear Weight Rank: 9
Intra Cos: 0.9096799492835999
Inter Cos: 0.3459394574165344
Norm Quadratic Average: 21.462574005126953
Nearest Class Center Accuracy: 0.9908

Output Layer:
Intra Cos: 0.9369180798530579
Inter Cos: 0.4118952453136444
Norm Quadratic Average: 19.595518112182617
Nearest Class Center Accuracy: 0.9912

