Model save path: ./New_Models/bn_True_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: 0.09607971459627151
Inter Cos: 0.09832435101270676
Norm Quadratic Average: 2.217841625213623
Nearest Class Center Accuracy: 0.8601833333333333

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16870802640914917
Inter Cos: 0.12641511857509613
Norm Quadratic Average: 1.3576436042785645
Nearest Class Center Accuracy: 0.9182333333333333

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20372618734836578
Inter Cos: 0.13185924291610718
Norm Quadratic Average: 1.0073144435882568
Nearest Class Center Accuracy: 0.9535833333333333

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2936403751373291
Inter Cos: 0.11275508254766464
Norm Quadratic Average: 0.6610912084579468
Nearest Class Center Accuracy: 0.9910333333333333

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5762700438499451
Inter Cos: 0.19403687119483948
Norm Quadratic Average: 0.542256772518158
Nearest Class Center Accuracy: 0.9989333333333333

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.783181369304657
Inter Cos: 0.12341437488794327
Norm Quadratic Average: 0.615349292755127
Nearest Class Center Accuracy: 1.0

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.979436993598938
Inter Cos: 0.027193034067749977
Norm Quadratic Average: 0.9835533499717712
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.2047526836395264
Linear Weight Rank: 169
Intra Cos: 0.9969627261161804
Inter Cos: -0.017324725165963173
Norm Quadratic Average: 25.265018463134766
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.2097012996673584
Linear Weight Rank: 1199
Intra Cos: 0.9975621700286865
Inter Cos: 0.005946115590631962
Norm Quadratic Average: 17.44257354736328
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.20646071434021
Linear Weight Rank: 9
Intra Cos: 0.9978667497634888
Inter Cos: 0.016567371785640717
Norm Quadratic Average: 12.255227088928223
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9980459809303284
Inter Cos: 0.033577729016542435
Norm Quadratic Average: 9.064431190490723
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.015442991534806789
Accuracy: 0.996
NC1 Within Class Collapse: 0.11795106530189514
NC2 Equinorm: Features: 0.024797804653644562, Weights: 0.006643347907811403
NC2 Equiangle: Features: 0.05967316097683377, Weights: 0.019684799512227378
NC3 Self-Duality: 0.008306937292218208
NC4 NCC Mismatch: 0.00019999999999997797

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: 0.10562756657600403
Inter Cos: 0.09935604780912399
Norm Quadratic Average: 2.204059600830078
Nearest Class Center Accuracy: 0.8737

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17963239550590515
Inter Cos: 0.12529003620147705
Norm Quadratic Average: 1.3500953912734985
Nearest Class Center Accuracy: 0.9245

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2160707265138626
Inter Cos: 0.12950630486011505
Norm Quadratic Average: 1.0030245780944824
Nearest Class Center Accuracy: 0.9568

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3042125999927521
Inter Cos: 0.12442870438098907
Norm Quadratic Average: 0.658295750617981
Nearest Class Center Accuracy: 0.988

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5839525461196899
Inter Cos: 0.2078171819448471
Norm Quadratic Average: 0.5412692427635193
Nearest Class Center Accuracy: 0.9937

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7787496447563171
Inter Cos: 0.1312258392572403
Norm Quadratic Average: 0.6139841079711914
Nearest Class Center Accuracy: 0.9958

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9681671261787415
Inter Cos: 0.03919936344027519
Norm Quadratic Average: 0.9788601398468018
Nearest Class Center Accuracy: 0.9959

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.2047526836395264
Linear Weight Rank: 169
Intra Cos: 0.9771942496299744
Inter Cos: -0.010099377483129501
Norm Quadratic Average: 25.1274471282959
Nearest Class Center Accuracy: 0.996

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.2097012996673584
Linear Weight Rank: 1199
Intra Cos: 0.9782154560089111
Inter Cos: 0.0123554402962327
Norm Quadratic Average: 17.34778594970703
Nearest Class Center Accuracy: 0.996

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.20646071434021
Linear Weight Rank: 9
Intra Cos: 0.9787665009498596
Inter Cos: 0.027230864390730858
Norm Quadratic Average: 12.18933391571045
Nearest Class Center Accuracy: 0.996

Output Layer:
Intra Cos: 0.9795930981636047
Inter Cos: 0.04398726671934128
Norm Quadratic Average: 9.015948295593262
Nearest Class Center Accuracy: 0.996

