Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_weight_decay_0.0007.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: 0.1118735671043396
Inter Cos: 0.1347798854112625
Norm Quadratic Average: 47.331275939941406
Nearest Class Center Accuracy: 0.8225

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15350380539894104
Inter Cos: 0.17578117549419403
Norm Quadratic Average: 48.03278350830078
Nearest Class Center Accuracy: 0.8035

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16776424646377563
Inter Cos: 0.19270192086696625
Norm Quadratic Average: 63.73049545288086
Nearest Class Center Accuracy: 0.815375

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1903725266456604
Inter Cos: 0.1898970901966095
Norm Quadratic Average: 42.715206146240234
Nearest Class Center Accuracy: 0.851125

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21665295958518982
Inter Cos: 0.19886358082294464
Norm Quadratic Average: 41.24989318847656
Nearest Class Center Accuracy: 0.8875

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27174147963523865
Inter Cos: 0.18351998925209045
Norm Quadratic Average: 24.311819076538086
Nearest Class Center Accuracy: 0.928375

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3964743912220001
Inter Cos: 0.21547745168209076
Norm Quadratic Average: 18.406768798828125
Nearest Class Center Accuracy: 0.97325

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.04280853271484
Linear Weight Rank: 4031
Intra Cos: 0.6097161173820496
Inter Cos: 0.23683632910251617
Norm Quadratic Average: 79.1094970703125
Nearest Class Center Accuracy: 0.99725

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.633705139160156
Linear Weight Rank: 3671
Intra Cos: 0.7207269668579102
Inter Cos: 0.23296213150024414
Norm Quadratic Average: 49.978477478027344
Nearest Class Center Accuracy: 0.99925

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.4507803916931152
Linear Weight Rank: 10
Intra Cos: 0.7723329663276672
Inter Cos: 0.264454185962677
Norm Quadratic Average: 38.12507247924805
Nearest Class Center Accuracy: 0.9995

Output Layer:
Intra Cos: 0.823859453201294
Inter Cos: 0.38409245014190674
Norm Quadratic Average: 26.801666259765625
Nearest Class Center Accuracy: 0.999875

Test Set:
Average Loss: 0.0791215581893921
Accuracy: 0.9795
NC1 Within Class Collapse: 1.8033945560455322
NC2 Equinorm: Features: 0.10570202022790909, Weights: 0.014109344221651554
NC2 Equiangle: Features: 0.24721419016520182, Weights: 0.09123063617282444
NC3 Self-Duality: 0.5432897806167603
NC4 NCC Mismatch: 0.017000000000000015

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: 0.1328539103269577
Inter Cos: 0.1477949470281601
Norm Quadratic Average: 45.92008590698242
Nearest Class Center Accuracy: 0.8195

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1661464124917984
Inter Cos: 0.20059502124786377
Norm Quadratic Average: 46.58588790893555
Nearest Class Center Accuracy: 0.8015

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17680124938488007
Inter Cos: 0.22754810750484467
Norm Quadratic Average: 61.76316833496094
Nearest Class Center Accuracy: 0.8215

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16435714066028595
Inter Cos: 0.21510611474514008
Norm Quadratic Average: 41.63588333129883
Nearest Class Center Accuracy: 0.849

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18606777489185333
Inter Cos: 0.22685208916664124
Norm Quadratic Average: 40.294151306152344
Nearest Class Center Accuracy: 0.8765

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2333907037973404
Inter Cos: 0.2065885066986084
Norm Quadratic Average: 23.701993942260742
Nearest Class Center Accuracy: 0.9235

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.33835309743881226
Inter Cos: 0.2370358109474182
Norm Quadratic Average: 17.817686080932617
Nearest Class Center Accuracy: 0.9535

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.04280853271484
Linear Weight Rank: 4031
Intra Cos: 0.5274705290794373
Inter Cos: 0.24721553921699524
Norm Quadratic Average: 76.13607025146484
Nearest Class Center Accuracy: 0.971

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.633705139160156
Linear Weight Rank: 3671
Intra Cos: 0.6306605339050293
Inter Cos: 0.24593490362167358
Norm Quadratic Average: 47.97974395751953
Nearest Class Center Accuracy: 0.9755

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.4507803916931152
Linear Weight Rank: 10
Intra Cos: 0.6788753867149353
Inter Cos: 0.2880706191062927
Norm Quadratic Average: 36.64004135131836
Nearest Class Center Accuracy: 0.976

Output Layer:
Intra Cos: 0.7213390469551086
Inter Cos: 0.3953855335712433
Norm Quadratic Average: 25.74772834777832
Nearest Class Center Accuracy: 0.974

