Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_265358_test_samples_None_train_samples_None_weight_decay_0.03.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09116753190755844
Inter Cos: 0.10967151820659637
Norm Quadratic Average: 23.567670822143555
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10867896676063538
Inter Cos: 0.11607492715120316
Norm Quadratic Average: 1.8648439645767212
Nearest Class Center Accuracy: 0.85465

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17998623847961426
Inter Cos: 0.14181089401245117
Norm Quadratic Average: 0.9306575655937195
Nearest Class Center Accuracy: 0.91275

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23375727236270905
Inter Cos: 0.16629880666732788
Norm Quadratic Average: 0.6103166341781616
Nearest Class Center Accuracy: 0.94915

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.33168312907218933
Inter Cos: 0.15552590787410736
Norm Quadratic Average: 0.23429101705551147
Nearest Class Center Accuracy: 0.9864

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7360904812812805
Inter Cos: 0.18904317915439606
Norm Quadratic Average: 0.17212030291557312
Nearest Class Center Accuracy: 0.9992166666666666

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8965121507644653
Inter Cos: 0.35375404357910156
Norm Quadratic Average: 0.24387381970882416
Nearest Class Center Accuracy: 0.9999333333333333

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.987200915813446
Inter Cos: 0.3623230755329132
Norm Quadratic Average: 0.5805911421775818
Nearest Class Center Accuracy: 0.99995

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.897359848022461
Linear Weight Rank: 7
Intra Cos: 0.9965574741363525
Inter Cos: 0.3071315586566925
Norm Quadratic Average: 21.163249969482422
Nearest Class Center Accuracy: 0.99995

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.898160696029663
Linear Weight Rank: 1407
Intra Cos: 0.9973888993263245
Inter Cos: 0.25528016686439514
Norm Quadratic Average: 14.993391036987305
Nearest Class Center Accuracy: 0.99995

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.8991895914077759
Linear Weight Rank: 7
Intra Cos: 0.9978308081626892
Inter Cos: 0.19257161021232605
Norm Quadratic Average: 10.803475379943848
Nearest Class Center Accuracy: 0.99995

Output Layer:
Intra Cos: 0.9983983039855957
Inter Cos: 0.25297436118125916
Norm Quadratic Average: 8.482593536376953
Nearest Class Center Accuracy: 0.99995

Test Set:
Average Loss: 0.030674746036529543
Accuracy: 0.9952
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.025358213111758232, Weights: 0.014298364520072937
NC2 Equiangle: Features: 0.2264078352186415, Weights: 0.22550718519422744
NC3 Self-Duality: 0.014059615321457386
NC4 NCC Mismatch: 9.999999999998899e-05

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219583660364151
Inter Cos: 0.12048852443695068
Norm Quadratic Average: 23.595197677612305
Nearest Class Center Accuracy: 0.8229

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11940819770097733
Inter Cos: 0.11634416878223419
Norm Quadratic Average: 1.8568545579910278
Nearest Class Center Accuracy: 0.8663

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1926468163728714
Inter Cos: 0.13908863067626953
Norm Quadratic Average: 0.9271788597106934
Nearest Class Center Accuracy: 0.9222

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2467648983001709
Inter Cos: 0.16178834438323975
Norm Quadratic Average: 0.6095350980758667
Nearest Class Center Accuracy: 0.9541

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.34469643235206604
Inter Cos: 0.16585832834243774
Norm Quadratic Average: 0.2340795397758484
Nearest Class Center Accuracy: 0.9854

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7353686690330505
Inter Cos: 0.20138157904148102
Norm Quadratic Average: 0.17234954237937927
Nearest Class Center Accuracy: 0.9939

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8878400921821594
Inter Cos: 0.363982617855072
Norm Quadratic Average: 0.24382685124874115
Nearest Class Center Accuracy: 0.9952

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9750069379806519
Inter Cos: 0.36088070273399353
Norm Quadratic Average: 0.578525960445404
Nearest Class Center Accuracy: 0.9952

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.897359848022461
Linear Weight Rank: 7
Intra Cos: 0.9808115363121033
Inter Cos: 0.3072667121887207
Norm Quadratic Average: 21.078983306884766
Nearest Class Center Accuracy: 0.9951

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.898160696029663
Linear Weight Rank: 1407
Intra Cos: 0.981501579284668
Inter Cos: 0.25614845752716064
Norm Quadratic Average: 14.932397842407227
Nearest Class Center Accuracy: 0.9951

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.8991895914077759
Linear Weight Rank: 7
Intra Cos: 0.981835126876831
Inter Cos: 0.1943254917860031
Norm Quadratic Average: 10.759204864501953
Nearest Class Center Accuracy: 0.9951

Output Layer:
Intra Cos: 0.9823818802833557
Inter Cos: 0.25204387307167053
Norm Quadratic Average: 8.445612907409668
Nearest Class Center Accuracy: 0.9951

