Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_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: 0.08946066349744797
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: 0.10079726576805115
Inter Cos: 0.12944269180297852
Norm Quadratic Average: 55.4306526184082
Nearest Class Center Accuracy: 0.831625

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14940005540847778
Inter Cos: 0.13604937493801117
Norm Quadratic Average: 34.880401611328125
Nearest Class Center Accuracy: 0.8555

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14907030761241913
Inter Cos: 0.1274816244840622
Norm Quadratic Average: 35.38897705078125
Nearest Class Center Accuracy: 0.876875

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19210611283779144
Inter Cos: 0.11886784434318542
Norm Quadratic Average: 22.00567054748535
Nearest Class Center Accuracy: 0.918125

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19961120188236237
Inter Cos: 0.0970211774110794
Norm Quadratic Average: 22.243749618530273
Nearest Class Center Accuracy: 0.947875

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23258990049362183
Inter Cos: 0.1080755740404129
Norm Quadratic Average: 15.074152946472168
Nearest Class Center Accuracy: 0.985

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.37460869550704956
Inter Cos: 0.1172863095998764
Norm Quadratic Average: 11.734427452087402
Nearest Class Center Accuracy: 0.998625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.733673095703125
Linear Weight Rank: 4031
Intra Cos: 0.663216233253479
Inter Cos: 0.1292208582162857
Norm Quadratic Average: 87.47644805908203
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.367679595947266
Linear Weight Rank: 3671
Intra Cos: 0.8150244355201721
Inter Cos: 0.14707204699516296
Norm Quadratic Average: 41.26799774169922
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.7101672887802124
Linear Weight Rank: 10
Intra Cos: 0.8858106136322021
Inter Cos: 0.15901704132556915
Norm Quadratic Average: 23.818740844726562
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9275317788124084
Inter Cos: 0.2679152488708496
Norm Quadratic Average: 12.360698699951172
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.06491106510162353
Accuracy: 0.978
NC1 Within Class Collapse: 1.336543321609497
NC2 Equinorm: Features: 0.06569412350654602, Weights: 0.014798996970057487
NC2 Equiangle: Features: 0.20276862250434027, Weights: 0.08455229865180122
NC3 Self-Duality: 0.37157824635505676
NC4 NCC Mismatch: 0.0040000000000000036

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133805871009827
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: 0.12621700763702393
Inter Cos: 0.1330910176038742
Norm Quadratic Average: 54.68061828613281
Nearest Class Center Accuracy: 0.822

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15500624477863312
Inter Cos: 0.16498975455760956
Norm Quadratic Average: 34.68435287475586
Nearest Class Center Accuracy: 0.8475

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15512333810329437
Inter Cos: 0.14757642149925232
Norm Quadratic Average: 35.1782112121582
Nearest Class Center Accuracy: 0.8705

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17969748377799988
Inter Cos: 0.12515851855278015
Norm Quadratic Average: 21.949914932250977
Nearest Class Center Accuracy: 0.913

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1897340565919876
Inter Cos: 0.10715664178133011
Norm Quadratic Average: 22.268726348876953
Nearest Class Center Accuracy: 0.937

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22424021363258362
Inter Cos: 0.10846330225467682
Norm Quadratic Average: 15.041543006896973
Nearest Class Center Accuracy: 0.962

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3304465413093567
Inter Cos: 0.11502691358327866
Norm Quadratic Average: 11.64510440826416
Nearest Class Center Accuracy: 0.976

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.733673095703125
Linear Weight Rank: 4031
Intra Cos: 0.5573076605796814
Inter Cos: 0.14279508590698242
Norm Quadratic Average: 85.11373138427734
Nearest Class Center Accuracy: 0.9795

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.367679595947266
Linear Weight Rank: 3671
Intra Cos: 0.694797694683075
Inter Cos: 0.16211730241775513
Norm Quadratic Average: 39.9190559387207
Nearest Class Center Accuracy: 0.9805

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.7101672887802124
Linear Weight Rank: 10
Intra Cos: 0.7642244696617126
Inter Cos: 0.15931183099746704
Norm Quadratic Average: 23.010168075561523
Nearest Class Center Accuracy: 0.979

Output Layer:
Intra Cos: 0.804111897945404
Inter Cos: 0.2538585364818573
Norm Quadratic Average: 11.936635971069336
Nearest Class Center Accuracy: 0.9795

