Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_weight_decay_0.003.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: 0.11311887204647064
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: 0.11280553787946701
Inter Cos: 0.13610368967056274
Norm Quadratic Average: 44.97207260131836
Nearest Class Center Accuracy: 0.821125

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15352444350719452
Inter Cos: 0.17849405109882355
Norm Quadratic Average: 46.00376892089844
Nearest Class Center Accuracy: 0.79875

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16739672422409058
Inter Cos: 0.19704456627368927
Norm Quadratic Average: 59.532684326171875
Nearest Class Center Accuracy: 0.809375

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19143792986869812
Inter Cos: 0.1944267302751541
Norm Quadratic Average: 38.55657958984375
Nearest Class Center Accuracy: 0.84225

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21800310909748077
Inter Cos: 0.2049790322780609
Norm Quadratic Average: 34.81141662597656
Nearest Class Center Accuracy: 0.879625

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2798174321651459
Inter Cos: 0.19663041830062866
Norm Quadratic Average: 19.38485336303711
Nearest Class Center Accuracy: 0.922125

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.409423828125
Inter Cos: 0.2369787096977234
Norm Quadratic Average: 13.933147430419922
Nearest Class Center Accuracy: 0.97025

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.80313110351562
Linear Weight Rank: 4031
Intra Cos: 0.6248092651367188
Inter Cos: 0.27024829387664795
Norm Quadratic Average: 59.501949310302734
Nearest Class Center Accuracy: 0.9965

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.50133514404297
Linear Weight Rank: 3671
Intra Cos: 0.733650267124176
Inter Cos: 0.2617228627204895
Norm Quadratic Average: 38.1357536315918
Nearest Class Center Accuracy: 0.99925

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.326472520828247
Linear Weight Rank: 10
Intra Cos: 0.7758750915527344
Inter Cos: 0.2818242311477661
Norm Quadratic Average: 29.441102981567383
Nearest Class Center Accuracy: 0.9995

Output Layer:
Intra Cos: 0.8153243660926819
Inter Cos: 0.3846508860588074
Norm Quadratic Average: 20.982593536376953
Nearest Class Center Accuracy: 0.99925

Test Set:
Average Loss: 0.068570108294487
Accuracy: 0.98
NC1 Within Class Collapse: 1.9758172035217285
NC2 Equinorm: Features: 0.11119307577610016, Weights: 0.01835750974714756
NC2 Equiangle: Features: 0.2588433159722222, Weights: 0.09583988189697265
NC3 Self-Duality: 0.4778267741203308
NC4 NCC Mismatch: 0.014499999999999957

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: 0.13385049998760223
Inter Cos: 0.14965945482254028
Norm Quadratic Average: 43.603763580322266
Nearest Class Center Accuracy: 0.819

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1668098419904709
Inter Cos: 0.20413325726985931
Norm Quadratic Average: 44.5834846496582
Nearest Class Center Accuracy: 0.7985

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17898815870285034
Inter Cos: 0.23386166989803314
Norm Quadratic Average: 57.65571975708008
Nearest Class Center Accuracy: 0.81

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16586759686470032
Inter Cos: 0.2227213829755783
Norm Quadratic Average: 37.56117630004883
Nearest Class Center Accuracy: 0.839

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18782465159893036
Inter Cos: 0.23861508071422577
Norm Quadratic Average: 34.01352310180664
Nearest Class Center Accuracy: 0.8715

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2411225289106369
Inter Cos: 0.21714551746845245
Norm Quadratic Average: 18.890933990478516
Nearest Class Center Accuracy: 0.9185

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.35190349817276
Inter Cos: 0.24494144320487976
Norm Quadratic Average: 13.48051643371582
Nearest Class Center Accuracy: 0.951

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.80313110351562
Linear Weight Rank: 4031
Intra Cos: 0.5456166863441467
Inter Cos: 0.2638322412967682
Norm Quadratic Average: 57.24871826171875
Nearest Class Center Accuracy: 0.969

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.50133514404297
Linear Weight Rank: 3671
Intra Cos: 0.6477029919624329
Inter Cos: 0.2655133605003357
Norm Quadratic Average: 36.58389663696289
Nearest Class Center Accuracy: 0.9745

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.326472520828247
Linear Weight Rank: 10
Intra Cos: 0.686927855014801
Inter Cos: 0.30187177658081055
Norm Quadratic Average: 28.28926658630371
Nearest Class Center Accuracy: 0.9755

Output Layer:
Intra Cos: 0.7174861431121826
Inter Cos: 0.3933175206184387
Norm Quadratic Average: 20.13644027709961
Nearest Class Center Accuracy: 0.9725

