Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_weight_decay_0.01.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946067094802856
Inter Cos: 0.11311887204647064
Norm Quadratic Average: 23.53293800354004
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10356239974498749
Inter Cos: 0.12362530827522278
Norm Quadratic Average: 53.15932083129883
Nearest Class Center Accuracy: 0.834875

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14477252960205078
Inter Cos: 0.1324957013130188
Norm Quadratic Average: 35.80113220214844
Nearest Class Center Accuracy: 0.850875

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14195819199085236
Inter Cos: 0.12575575709342957
Norm Quadratic Average: 35.51832962036133
Nearest Class Center Accuracy: 0.872125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1669112592935562
Inter Cos: 0.09395740181207657
Norm Quadratic Average: 21.68279266357422
Nearest Class Center Accuracy: 0.919625

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19087357819080353
Inter Cos: 0.08805852383375168
Norm Quadratic Average: 21.895713806152344
Nearest Class Center Accuracy: 0.94975

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2372681349515915
Inter Cos: 0.08287803828716278
Norm Quadratic Average: 14.772294998168945
Nearest Class Center Accuracy: 0.98775

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.38188010454177856
Inter Cos: 0.11586638540029526
Norm Quadratic Average: 11.755820274353027
Nearest Class Center Accuracy: 0.999625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.73493576049805
Linear Weight Rank: 4031
Intra Cos: 0.6613242626190186
Inter Cos: 0.13550294935703278
Norm Quadratic Average: 88.16181945800781
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.368276596069336
Linear Weight Rank: 3671
Intra Cos: 0.8219279646873474
Inter Cos: 0.15616728365421295
Norm Quadratic Average: 41.766212463378906
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.7075753211975098
Linear Weight Rank: 10
Intra Cos: 0.8943918943405151
Inter Cos: 0.18292412161827087
Norm Quadratic Average: 24.316253662109375
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9357405304908752
Inter Cos: 0.23724350333213806
Norm Quadratic Average: 12.738661766052246
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.06884011852741241
Accuracy: 0.9785
NC1 Within Class Collapse: 1.3426141738891602
NC2 Equinorm: Features: 0.06832727789878845, Weights: 0.015253494493663311
NC2 Equiangle: Features: 0.22130877176920574, Weights: 0.08978489769829644
NC3 Self-Duality: 0.3867087960243225
NC4 NCC Mismatch: 0.00649999999999995

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
Inter Cos: 0.11957792192697525
Norm Quadratic Average: 22.82430076599121
Nearest Class Center Accuracy: 0.809

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12174148112535477
Inter Cos: 0.12701085209846497
Norm Quadratic Average: 52.086509704589844
Nearest Class Center Accuracy: 0.829

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1485685259103775
Inter Cos: 0.14304934442043304
Norm Quadratic Average: 35.4170036315918
Nearest Class Center Accuracy: 0.846

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14309759438037872
Inter Cos: 0.13614395260810852
Norm Quadratic Average: 35.14879608154297
Nearest Class Center Accuracy: 0.8685

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16932521760463715
Inter Cos: 0.11426962912082672
Norm Quadratic Average: 21.542903900146484
Nearest Class Center Accuracy: 0.914

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18507517874240875
Inter Cos: 0.11051137000322342
Norm Quadratic Average: 21.783708572387695
Nearest Class Center Accuracy: 0.937

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23154041171073914
Inter Cos: 0.09727102518081665
Norm Quadratic Average: 14.706284523010254
Nearest Class Center Accuracy: 0.961

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3377104103565216
Inter Cos: 0.1230003833770752
Norm Quadratic Average: 11.637173652648926
Nearest Class Center Accuracy: 0.9755

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.73493576049805
Linear Weight Rank: 4031
Intra Cos: 0.5632688403129578
Inter Cos: 0.14639347791671753
Norm Quadratic Average: 85.58183288574219
Nearest Class Center Accuracy: 0.9805

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.368276596069336
Linear Weight Rank: 3671
Intra Cos: 0.7039644718170166
Inter Cos: 0.1713261604309082
Norm Quadratic Average: 40.289676666259766
Nearest Class Center Accuracy: 0.978

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.7075753211975098
Linear Weight Rank: 10
Intra Cos: 0.7738118767738342
Inter Cos: 0.1847502589225769
Norm Quadratic Average: 23.419660568237305
Nearest Class Center Accuracy: 0.977

Output Layer:
Intra Cos: 0.8150936961174011
Inter Cos: 0.23586198687553406
Norm Quadratic Average: 12.247007369995117
Nearest Class Center Accuracy: 0.976

