Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_weight_decay_0.005.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: 0.11311888694763184
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: 0.10482390224933624
Inter Cos: 0.12363364547491074
Norm Quadratic Average: 63.000221252441406
Nearest Class Center Accuracy: 0.831875

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14898386597633362
Inter Cos: 0.1403351128101349
Norm Quadratic Average: 44.98886489868164
Nearest Class Center Accuracy: 0.84875

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14963777363300323
Inter Cos: 0.1374085545539856
Norm Quadratic Average: 44.835845947265625
Nearest Class Center Accuracy: 0.868

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16368938982486725
Inter Cos: 0.12804874777793884
Norm Quadratic Average: 26.98474884033203
Nearest Class Center Accuracy: 0.90775

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17382872104644775
Inter Cos: 0.11511047184467316
Norm Quadratic Average: 28.66515350341797
Nearest Class Center Accuracy: 0.931625

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2159843146800995
Inter Cos: 0.09095601737499237
Norm Quadratic Average: 19.545970916748047
Nearest Class Center Accuracy: 0.97575

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3103090524673462
Inter Cos: 0.09490777552127838
Norm Quadratic Average: 15.138834953308105
Nearest Class Center Accuracy: 0.998

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.75354766845703
Linear Weight Rank: 4031
Intra Cos: 0.5450155735015869
Inter Cos: 0.1120956763625145
Norm Quadratic Average: 99.71923828125
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.24344253540039
Linear Weight Rank: 3671
Intra Cos: 0.7029997706413269
Inter Cos: 0.1480208933353424
Norm Quadratic Average: 49.09287643432617
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9393874406814575
Linear Weight Rank: 10
Intra Cos: 0.815163254737854
Inter Cos: 0.17162564396858215
Norm Quadratic Average: 29.05204200744629
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9116339087486267
Inter Cos: 0.24138586223125458
Norm Quadratic Average: 14.7449369430542
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.07974527168273926
Accuracy: 0.976
NC1 Within Class Collapse: 1.5648678541183472
NC2 Equinorm: Features: 0.06674746423959732, Weights: 0.009444907307624817
NC2 Equiangle: Features: 0.18391960991753473, Weights: 0.08067299524943033
NC3 Self-Duality: 0.518956184387207
NC4 NCC Mismatch: 0.0050000000000000044

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: 0.12475220113992691
Inter Cos: 0.13119803369045258
Norm Quadratic Average: 61.88780975341797
Nearest Class Center Accuracy: 0.824

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14832648634910583
Inter Cos: 0.15335510671138763
Norm Quadratic Average: 44.43701934814453
Nearest Class Center Accuracy: 0.842

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1470813751220703
Inter Cos: 0.14506253600120544
Norm Quadratic Average: 44.32632064819336
Nearest Class Center Accuracy: 0.864

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15258225798606873
Inter Cos: 0.12616775929927826
Norm Quadratic Average: 26.85062026977539
Nearest Class Center Accuracy: 0.905

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15805786848068237
Inter Cos: 0.11455725878477097
Norm Quadratic Average: 28.542699813842773
Nearest Class Center Accuracy: 0.9275

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1901722550392151
Inter Cos: 0.09382209181785583
Norm Quadratic Average: 19.45850944519043
Nearest Class Center Accuracy: 0.955

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.256931334733963
Inter Cos: 0.1061992421746254
Norm Quadratic Average: 14.983540534973145
Nearest Class Center Accuracy: 0.971

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.75354766845703
Linear Weight Rank: 4031
Intra Cos: 0.4381236732006073
Inter Cos: 0.11566988378763199
Norm Quadratic Average: 96.90467071533203
Nearest Class Center Accuracy: 0.976

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.24344253540039
Linear Weight Rank: 3671
Intra Cos: 0.5746089816093445
Inter Cos: 0.1481037139892578
Norm Quadratic Average: 47.37675857543945
Nearest Class Center Accuracy: 0.978

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9393874406814575
Linear Weight Rank: 10
Intra Cos: 0.6852869987487793
Inter Cos: 0.17911989986896515
Norm Quadratic Average: 27.9398136138916
Nearest Class Center Accuracy: 0.9775

Output Layer:
Intra Cos: 0.786666989326477
Inter Cos: 0.2622520327568054
Norm Quadratic Average: 14.11238956451416
Nearest Class Center Accuracy: 0.974

