Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_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: 0.08946067094802856
Inter Cos: 0.11311887949705124
Norm Quadratic Average: 23.532934188842773
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11944299936294556
Inter Cos: 0.13998916745185852
Norm Quadratic Average: 43.89802169799805
Nearest Class Center Accuracy: 0.813875

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16366282105445862
Inter Cos: 0.1740097552537918
Norm Quadratic Average: 44.573726654052734
Nearest Class Center Accuracy: 0.792875

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17803440988063812
Inter Cos: 0.18850959837436676
Norm Quadratic Average: 56.28293228149414
Nearest Class Center Accuracy: 0.798875

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1867121458053589
Inter Cos: 0.18504317104816437
Norm Quadratic Average: 34.72971725463867
Nearest Class Center Accuracy: 0.838625

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21440914273262024
Inter Cos: 0.20723560452461243
Norm Quadratic Average: 29.44046974182129
Nearest Class Center Accuracy: 0.88425

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.30219128727912903
Inter Cos: 0.19491681456565857
Norm Quadratic Average: 15.514935493469238
Nearest Class Center Accuracy: 0.9325

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4410199820995331
Inter Cos: 0.2297888547182083
Norm Quadratic Average: 11.103379249572754
Nearest Class Center Accuracy: 0.97025

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.762451171875
Linear Weight Rank: 4031
Intra Cos: 0.6699532866477966
Inter Cos: 0.260027676820755
Norm Quadratic Average: 48.62184524536133
Nearest Class Center Accuracy: 0.99575

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.26079177856445
Linear Weight Rank: 3670
Intra Cos: 0.7670400738716125
Inter Cos: 0.27621954679489136
Norm Quadratic Average: 32.30458450317383
Nearest Class Center Accuracy: 0.999125

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2742908000946045
Linear Weight Rank: 10
Intra Cos: 0.8001214861869812
Inter Cos: 0.2651234567165375
Norm Quadratic Average: 25.63836097717285
Nearest Class Center Accuracy: 0.99925

Output Layer:
Intra Cos: 0.8314242959022522
Inter Cos: 0.3463245630264282
Norm Quadratic Average: 18.985454559326172
Nearest Class Center Accuracy: 0.99875

Test Set:
Average Loss: 0.06616454929113388
Accuracy: 0.9785
NC1 Within Class Collapse: 2.0883593559265137
NC2 Equinorm: Features: 0.09727523475885391, Weights: 0.017933417111635208
NC2 Equiangle: Features: 0.259162966410319, Weights: 0.10747961468166775
NC3 Self-Duality: 0.40933001041412354
NC4 NCC Mismatch: 0.01200000000000001

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133805871009827
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: 0.13495202362537384
Inter Cos: 0.1526443511247635
Norm Quadratic Average: 42.580501556396484
Nearest Class Center Accuracy: 0.8085

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16805920004844666
Inter Cos: 0.20126992464065552
Norm Quadratic Average: 43.28256607055664
Nearest Class Center Accuracy: 0.791

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17747202515602112
Inter Cos: 0.22662241756916046
Norm Quadratic Average: 54.544315338134766
Nearest Class Center Accuracy: 0.8045

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16892504692077637
Inter Cos: 0.22384563088417053
Norm Quadratic Average: 33.74919891357422
Nearest Class Center Accuracy: 0.8295

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19381271302700043
Inter Cos: 0.2435884177684784
Norm Quadratic Average: 28.67022132873535
Nearest Class Center Accuracy: 0.8735

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2680168151855469
Inter Cos: 0.23174482583999634
Norm Quadratic Average: 15.06005859375
Nearest Class Center Accuracy: 0.931

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3898698389530182
Inter Cos: 0.2607620358467102
Norm Quadratic Average: 10.719680786132812
Nearest Class Center Accuracy: 0.9535

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.762451171875
Linear Weight Rank: 4031
Intra Cos: 0.6006516218185425
Inter Cos: 0.2981249690055847
Norm Quadratic Average: 46.664794921875
Nearest Class Center Accuracy: 0.9675

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.26079177856445
Linear Weight Rank: 3670
Intra Cos: 0.6970568895339966
Inter Cos: 0.29108288884162903
Norm Quadratic Average: 30.949548721313477
Nearest Class Center Accuracy: 0.9755

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2742908000946045
Linear Weight Rank: 10
Intra Cos: 0.7286804914474487
Inter Cos: 0.2759377360343933
Norm Quadratic Average: 24.56519889831543
Nearest Class Center Accuracy: 0.975

Output Layer:
Intra Cos: 0.7544939517974854
Inter Cos: 0.31661662459373474
Norm Quadratic Average: 18.169090270996094
Nearest Class Center Accuracy: 0.9745

