Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_weight_decay_0.0007.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946066349744797
Inter Cos: 0.11311887949705124
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: 0.09997216612100601
Inter Cos: 0.11859714239835739
Norm Quadratic Average: 85.07335662841797
Nearest Class Center Accuracy: 0.83625

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1378253847360611
Inter Cos: 0.1359771192073822
Norm Quadratic Average: 55.933677673339844
Nearest Class Center Accuracy: 0.84575

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13805094361305237
Inter Cos: 0.12403755635023117
Norm Quadratic Average: 55.753944396972656
Nearest Class Center Accuracy: 0.865375

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1606036275625229
Inter Cos: 0.09860310703516006
Norm Quadratic Average: 34.52763366699219
Nearest Class Center Accuracy: 0.901375

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16590136289596558
Inter Cos: 0.092745341360569
Norm Quadratic Average: 35.14217758178711
Nearest Class Center Accuracy: 0.929875

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18863874673843384
Inter Cos: 0.10166610777378082
Norm Quadratic Average: 23.756851196289062
Nearest Class Center Accuracy: 0.972

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2845793068408966
Inter Cos: 0.11327514797449112
Norm Quadratic Average: 18.20564842224121
Nearest Class Center Accuracy: 0.9965

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.0140380859375
Linear Weight Rank: 4031
Intra Cos: 0.482456773519516
Inter Cos: 0.13538208603858948
Norm Quadratic Average: 115.5077896118164
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.63239288330078
Linear Weight Rank: 3671
Intra Cos: 0.6131076812744141
Inter Cos: 0.15301115810871124
Norm Quadratic Average: 61.749576568603516
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2452592849731445
Linear Weight Rank: 10
Intra Cos: 0.7307147979736328
Inter Cos: 0.20807194709777832
Norm Quadratic Average: 39.08726119995117
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.8861691951751709
Inter Cos: 0.2922571301460266
Norm Quadratic Average: 21.013471603393555
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.10584074556827545
Accuracy: 0.973
NC1 Within Class Collapse: 1.724972128868103
NC2 Equinorm: Features: 0.06287039816379547, Weights: 0.012537951581180096
NC2 Equiangle: Features: 0.194792726304796, Weights: 0.0906044430202908
NC3 Self-Duality: 0.6318909525871277
NC4 NCC Mismatch: 0.009499999999999953

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: 0.12092462927103043
Inter Cos: 0.12616273760795593
Norm Quadratic Average: 84.17686462402344
Nearest Class Center Accuracy: 0.8285

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.151126429438591
Inter Cos: 0.15041980147361755
Norm Quadratic Average: 55.4780158996582
Nearest Class Center Accuracy: 0.8365

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15008877217769623
Inter Cos: 0.13516992330551147
Norm Quadratic Average: 55.26713562011719
Nearest Class Center Accuracy: 0.859

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1592138111591339
Inter Cos: 0.12481033056974411
Norm Quadratic Average: 34.40471267700195
Nearest Class Center Accuracy: 0.899

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16961273550987244
Inter Cos: 0.11440609395503998
Norm Quadratic Average: 35.07728576660156
Nearest Class Center Accuracy: 0.9165

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1948240101337433
Inter Cos: 0.10888941586017609
Norm Quadratic Average: 23.736352920532227
Nearest Class Center Accuracy: 0.941

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24116364121437073
Inter Cos: 0.11419741064310074
Norm Quadratic Average: 18.074504852294922
Nearest Class Center Accuracy: 0.963

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.0140380859375
Linear Weight Rank: 4031
Intra Cos: 0.39181777834892273
Inter Cos: 0.1389385312795639
Norm Quadratic Average: 113.3351821899414
Nearest Class Center Accuracy: 0.972

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.63239288330078
Linear Weight Rank: 3671
Intra Cos: 0.5036161541938782
Inter Cos: 0.16092292964458466
Norm Quadratic Average: 60.26020812988281
Nearest Class Center Accuracy: 0.972

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2452592849731445
Linear Weight Rank: 10
Intra Cos: 0.6118830442428589
Inter Cos: 0.21582026779651642
Norm Quadratic Average: 38.00725555419922
Nearest Class Center Accuracy: 0.9695

Output Layer:
Intra Cos: 0.7632865905761719
Inter Cos: 0.2981276214122772
Norm Quadratic Average: 20.336040496826172
Nearest Class Center Accuracy: 0.97

