Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_weight_decay_0.02.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: 23.532939910888672
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10816255956888199
Inter Cos: 0.12657077610492706
Norm Quadratic Average: 33.059906005859375
Nearest Class Center Accuracy: 0.82375

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15115788578987122
Inter Cos: 0.14131395518779755
Norm Quadratic Average: 20.701236724853516
Nearest Class Center Accuracy: 0.845

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1564057320356369
Inter Cos: 0.13865497708320618
Norm Quadratic Average: 21.283679962158203
Nearest Class Center Accuracy: 0.87375

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18790219724178314
Inter Cos: 0.11401928216218948
Norm Quadratic Average: 13.20447826385498
Nearest Class Center Accuracy: 0.925875

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21928860247135162
Inter Cos: 0.10583220422267914
Norm Quadratic Average: 13.956077575683594
Nearest Class Center Accuracy: 0.96275

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3155558705329895
Inter Cos: 0.10859881341457367
Norm Quadratic Average: 9.377652168273926
Nearest Class Center Accuracy: 0.996

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5463031530380249
Inter Cos: 0.12166052311658859
Norm Quadratic Average: 7.447301387786865
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.801204681396484
Linear Weight Rank: 4031
Intra Cos: 0.8579651117324829
Inter Cos: 0.0862077921628952
Norm Quadratic Average: 69.58065795898438
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 15.724549293518066
Linear Weight Rank: 3670
Intra Cos: 0.9387107491493225
Inter Cos: 0.1255975365638733
Norm Quadratic Average: 31.746339797973633
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.553430438041687
Linear Weight Rank: 10
Intra Cos: 0.9550969004631042
Inter Cos: 0.16273990273475647
Norm Quadratic Average: 17.481483459472656
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.961365818977356
Inter Cos: 0.22082556784152985
Norm Quadratic Average: 9.319665908813477
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.06542504918575287
Accuracy: 0.9825
NC1 Within Class Collapse: 0.9689919352531433
NC2 Equinorm: Features: 0.06608907878398895, Weights: 0.01749800704419613
NC2 Equiangle: Features: 0.18634173075358074, Weights: 0.08333171208699544
NC3 Self-Duality: 0.163178950548172
NC4 NCC Mismatch: 0.0030000000000000027

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
Inter Cos: 0.11957794427871704
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: 0.1313118040561676
Inter Cos: 0.14484363794326782
Norm Quadratic Average: 32.500083923339844
Nearest Class Center Accuracy: 0.8175

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15843535959720612
Inter Cos: 0.17123709619045258
Norm Quadratic Average: 20.4681453704834
Nearest Class Center Accuracy: 0.8435

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.155784010887146
Inter Cos: 0.15704064071178436
Norm Quadratic Average: 21.09392547607422
Nearest Class Center Accuracy: 0.8675

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1765420138835907
Inter Cos: 0.1292247325181961
Norm Quadratic Average: 13.154363632202148
Nearest Class Center Accuracy: 0.9165

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20310069620609283
Inter Cos: 0.11991102248430252
Norm Quadratic Average: 13.940817832946777
Nearest Class Center Accuracy: 0.9465

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2891681492328644
Inter Cos: 0.11054562032222748
Norm Quadratic Average: 9.34559440612793
Nearest Class Center Accuracy: 0.971

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4889688193798065
Inter Cos: 0.12214495986700058
Norm Quadratic Average: 7.337701320648193
Nearest Class Center Accuracy: 0.981

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.801204681396484
Linear Weight Rank: 4031
Intra Cos: 0.7514393925666809
Inter Cos: 0.12449394911527634
Norm Quadratic Average: 67.09986114501953
Nearest Class Center Accuracy: 0.9825

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 15.724549293518066
Linear Weight Rank: 3670
Intra Cos: 0.8433047533035278
Inter Cos: 0.15405525267124176
Norm Quadratic Average: 30.507890701293945
Nearest Class Center Accuracy: 0.983

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.553430438041687
Linear Weight Rank: 10
Intra Cos: 0.8610075116157532
Inter Cos: 0.1650320142507553
Norm Quadratic Average: 16.818803787231445
Nearest Class Center Accuracy: 0.9835

Output Layer:
Intra Cos: 0.8664090037345886
Inter Cos: 0.23206740617752075
Norm Quadratic Average: 8.959178924560547
Nearest Class Center Accuracy: 0.9845

