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_0.02.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: 0.10826187580823898
Inter Cos: 0.11283883452415466
Norm Quadratic Average: 1.9204736948013306
Nearest Class Center Accuracy: 0.8560333333333333

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1765938550233841
Inter Cos: 0.14471986889839172
Norm Quadratic Average: 0.9798263311386108
Nearest Class Center Accuracy: 0.9117666666666666

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23305171728134155
Inter Cos: 0.16747045516967773
Norm Quadratic Average: 0.6089227795600891
Nearest Class Center Accuracy: 0.9496833333333333

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3133973479270935
Inter Cos: 0.13984666764736176
Norm Quadratic Average: 0.2506099045276642
Nearest Class Center Accuracy: 0.988

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6814603805541992
Inter Cos: 0.21061329543590546
Norm Quadratic Average: 0.18473730981349945
Nearest Class Center Accuracy: 0.9993833333333333

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8939253687858582
Inter Cos: 0.33871880173683167
Norm Quadratic Average: 0.2929231822490692
Nearest Class Center Accuracy: 0.9999833333333333

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9859105348587036
Inter Cos: 0.3357713222503662
Norm Quadratic Average: 0.6573421359062195
Nearest Class Center Accuracy: 0.9999833333333333

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.9394444227218628
Linear Weight Rank: 7
Intra Cos: 0.9970155358314514
Inter Cos: 0.3275766372680664
Norm Quadratic Average: 21.415973663330078
Nearest Class Center Accuracy: 0.9999833333333333

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.9402451515197754
Linear Weight Rank: 1273
Intra Cos: 0.9978739023208618
Inter Cos: 0.2682443857192993
Norm Quadratic Average: 15.493383407592773
Nearest Class Center Accuracy: 0.9999833333333333

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9411243200302124
Linear Weight Rank: 7
Intra Cos: 0.9981844425201416
Inter Cos: 0.19381067156791687
Norm Quadratic Average: 11.408012390136719
Nearest Class Center Accuracy: 0.9999833333333333

Output Layer:
Intra Cos: 0.9984288215637207
Inter Cos: 0.26517254114151
Norm Quadratic Average: 9.176989555358887
Nearest Class Center Accuracy: 0.9999833333333333

Test Set:
Average Loss: 0.024405169247090817
Accuracy: 0.9957
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.03412448614835739, Weights: 0.02126484364271164
NC2 Equiangle: Features: 0.22102942996554906, Weights: 0.22111523946126302
NC3 Self-Duality: 0.013800445944070816
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: 0.11856647580862045
Inter Cos: 0.11302900314331055
Norm Quadratic Average: 1.911770224571228
Nearest Class Center Accuracy: 0.869

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18919281661510468
Inter Cos: 0.14192023873329163
Norm Quadratic Average: 0.9762347340583801
Nearest Class Center Accuracy: 0.9224

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24517932534217834
Inter Cos: 0.1635328233242035
Norm Quadratic Average: 0.6083243489265442
Nearest Class Center Accuracy: 0.9534

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3266028165817261
Inter Cos: 0.14895235002040863
Norm Quadratic Average: 0.25042203068733215
Nearest Class Center Accuracy: 0.9857

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6867316961288452
Inter Cos: 0.22429479658603668
Norm Quadratic Average: 0.18505631387233734
Nearest Class Center Accuracy: 0.9935

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8888223171234131
Inter Cos: 0.3394066095352173
Norm Quadratic Average: 0.29288357496261597
Nearest Class Center Accuracy: 0.9955

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9743995070457458
Inter Cos: 0.3390657901763916
Norm Quadratic Average: 0.6549656987190247
Nearest Class Center Accuracy: 0.9956

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.9394444227218628
Linear Weight Rank: 7
Intra Cos: 0.9821455478668213
Inter Cos: 0.3283166289329529
Norm Quadratic Average: 21.32244873046875
Nearest Class Center Accuracy: 0.9957

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.9402451515197754
Linear Weight Rank: 1273
Intra Cos: 0.9827020168304443
Inter Cos: 0.26954272389411926
Norm Quadratic Average: 15.42667007446289
Nearest Class Center Accuracy: 0.9957

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9411243200302124
Linear Weight Rank: 7
Intra Cos: 0.9829736351966858
Inter Cos: 0.1959429830312729
Norm Quadratic Average: 11.359640121459961
Nearest Class Center Accuracy: 0.9955

Output Layer:
Intra Cos: 0.9833317995071411
Inter Cos: 0.263921856880188
Norm Quadratic Average: 9.139175415039062
Nearest Class Center Accuracy: 0.9955

