Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_weight_decay_0.0005.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: 0.11311887949705124
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: 0.1017584353685379
Inter Cos: 0.1238035038113594
Norm Quadratic Average: 86.14828491210938
Nearest Class Center Accuracy: 0.8315

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13886459171772003
Inter Cos: 0.13582833111286163
Norm Quadratic Average: 54.3923454284668
Nearest Class Center Accuracy: 0.849125

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1398470252752304
Inter Cos: 0.1282721757888794
Norm Quadratic Average: 55.33464813232422
Nearest Class Center Accuracy: 0.86875

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1685309112071991
Inter Cos: 0.09713154286146164
Norm Quadratic Average: 34.445533752441406
Nearest Class Center Accuracy: 0.9065

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17780137062072754
Inter Cos: 0.09001561254262924
Norm Quadratic Average: 35.44038772583008
Nearest Class Center Accuracy: 0.930875

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20045307278633118
Inter Cos: 0.0791674256324768
Norm Quadratic Average: 24.127565383911133
Nearest Class Center Accuracy: 0.974125

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27203860878944397
Inter Cos: 0.08355722576379776
Norm Quadratic Average: 18.83736801147461
Nearest Class Center Accuracy: 0.996625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.97300720214844
Linear Weight Rank: 4031
Intra Cos: 0.466908723115921
Inter Cos: 0.10144398361444473
Norm Quadratic Average: 116.49909210205078
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.998329162597656
Linear Weight Rank: 3671
Intra Cos: 0.6135161519050598
Inter Cos: 0.13404542207717896
Norm Quadratic Average: 62.90232467651367
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.25765061378479
Linear Weight Rank: 10
Intra Cos: 0.7437639236450195
Inter Cos: 0.15405291318893433
Norm Quadratic Average: 39.77812576293945
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.8972923159599304
Inter Cos: 0.28397586941719055
Norm Quadratic Average: 21.2396297454834
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.1094264298081398
Accuracy: 0.973
NC1 Within Class Collapse: 1.7218701839447021
NC2 Equinorm: Features: 0.06727863103151321, Weights: 0.011029926128685474
NC2 Equiangle: Features: 0.19342062208387586, Weights: 0.08563258912828234
NC3 Self-Duality: 0.6348648071289062
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: 0.11957792937755585
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: 0.1281191110610962
Inter Cos: 0.13253961503505707
Norm Quadratic Average: 84.59342956542969
Nearest Class Center Accuracy: 0.827

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15457585453987122
Inter Cos: 0.1535048931837082
Norm Quadratic Average: 53.79469299316406
Nearest Class Center Accuracy: 0.8435

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14949066936969757
Inter Cos: 0.13613013923168182
Norm Quadratic Average: 54.777828216552734
Nearest Class Center Accuracy: 0.865

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1541285514831543
Inter Cos: 0.11976051330566406
Norm Quadratic Average: 34.24861526489258
Nearest Class Center Accuracy: 0.901

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15998773276805878
Inter Cos: 0.11490534245967865
Norm Quadratic Average: 35.2999382019043
Nearest Class Center Accuracy: 0.919

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18784329295158386
Inter Cos: 0.093915194272995
Norm Quadratic Average: 24.034147262573242
Nearest Class Center Accuracy: 0.9495

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24010249972343445
Inter Cos: 0.09382374584674835
Norm Quadratic Average: 18.63907814025879
Nearest Class Center Accuracy: 0.974

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.97300720214844
Linear Weight Rank: 4031
Intra Cos: 0.38728415966033936
Inter Cos: 0.11667464673519135
Norm Quadratic Average: 113.54522705078125
Nearest Class Center Accuracy: 0.974

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.998329162597656
Linear Weight Rank: 3671
Intra Cos: 0.5024596452713013
Inter Cos: 0.14760535955429077
Norm Quadratic Average: 60.931575775146484
Nearest Class Center Accuracy: 0.976

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.25765061378479
Linear Weight Rank: 10
Intra Cos: 0.6151207089424133
Inter Cos: 0.20578990876674652
Norm Quadratic Average: 38.36155700683594
Nearest Class Center Accuracy: 0.9745

Output Layer:
Intra Cos: 0.7661767601966858
Inter Cos: 0.3395354151725769
Norm Quadratic Average: 20.349531173706055
Nearest Class Center Accuracy: 0.975

