Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_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: 23.53293800354004
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10326385498046875
Inter Cos: 0.12368958443403244
Norm Quadratic Average: 33.0758056640625
Nearest Class Center Accuracy: 0.8355

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1550346314907074
Inter Cos: 0.1474975198507309
Norm Quadratic Average: 21.935165405273438
Nearest Class Center Accuracy: 0.8545

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15577267110347748
Inter Cos: 0.14278265833854675
Norm Quadratic Average: 21.7255802154541
Nearest Class Center Accuracy: 0.876

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19747425615787506
Inter Cos: 0.1220972090959549
Norm Quadratic Average: 13.394571304321289
Nearest Class Center Accuracy: 0.925875

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21899954974651337
Inter Cos: 0.11007529497146606
Norm Quadratic Average: 13.41230583190918
Nearest Class Center Accuracy: 0.958375

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.29319438338279724
Inter Cos: 0.11732746660709381
Norm Quadratic Average: 9.07840347290039
Nearest Class Center Accuracy: 0.99475

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5439818501472473
Inter Cos: 0.12352093309164047
Norm Quadratic Average: 7.314756870269775
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.79924774169922
Linear Weight Rank: 4031
Intra Cos: 0.851313054561615
Inter Cos: 0.11630745977163315
Norm Quadratic Average: 69.67064666748047
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 15.723865509033203
Linear Weight Rank: 3670
Intra Cos: 0.9367154836654663
Inter Cos: 0.12893494963645935
Norm Quadratic Average: 32.15680694580078
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.5484817028045654
Linear Weight Rank: 10
Intra Cos: 0.9527099132537842
Inter Cos: 0.15304172039031982
Norm Quadratic Average: 17.910680770874023
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9590646028518677
Inter Cos: 0.2514957785606384
Norm Quadratic Average: 9.76431941986084
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.0644211392402649
Accuracy: 0.9835
NC1 Within Class Collapse: 0.9851560592651367
NC2 Equinorm: Features: 0.06496874988079071, Weights: 0.017232604324817657
NC2 Equiangle: Features: 0.20496919420030382, Weights: 0.09729114108615451
NC3 Self-Duality: 0.1742105931043625
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: 0.11957792192697525
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: 0.12171309441328049
Inter Cos: 0.12797990441322327
Norm Quadratic Average: 32.51313781738281
Nearest Class Center Accuracy: 0.83

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1568479686975479
Inter Cos: 0.15622635185718536
Norm Quadratic Average: 21.755308151245117
Nearest Class Center Accuracy: 0.847

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16075271368026733
Inter Cos: 0.14693208038806915
Norm Quadratic Average: 21.52176856994629
Nearest Class Center Accuracy: 0.8695

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1870409995317459
Inter Cos: 0.13344959914684296
Norm Quadratic Average: 13.346427917480469
Nearest Class Center Accuracy: 0.917

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20861996710300446
Inter Cos: 0.12822449207305908
Norm Quadratic Average: 13.39330005645752
Nearest Class Center Accuracy: 0.9435

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27367186546325684
Inter Cos: 0.12410509586334229
Norm Quadratic Average: 9.049272537231445
Nearest Class Center Accuracy: 0.976

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4551580846309662
Inter Cos: 0.1358390599489212
Norm Quadratic Average: 7.215214729309082
Nearest Class Center Accuracy: 0.9845

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.79924774169922
Linear Weight Rank: 4031
Intra Cos: 0.7312520146369934
Inter Cos: 0.13962695002555847
Norm Quadratic Average: 67.25245666503906
Nearest Class Center Accuracy: 0.984

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 15.723865509033203
Linear Weight Rank: 3670
Intra Cos: 0.8230358362197876
Inter Cos: 0.15577353537082672
Norm Quadratic Average: 30.963346481323242
Nearest Class Center Accuracy: 0.984

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.5484817028045654
Linear Weight Rank: 10
Intra Cos: 0.8384128212928772
Inter Cos: 0.15735696256160736
Norm Quadratic Average: 17.287303924560547
Nearest Class Center Accuracy: 0.9845

Output Layer:
Intra Cos: 0.8458881378173828
Inter Cos: 0.24550089240074158
Norm Quadratic Average: 9.428841590881348
Nearest Class Center Accuracy: 0.984

