Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_weight_decay_0.001.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: 0.11200973391532898
Inter Cos: 0.13494683802127838
Norm Quadratic Average: 46.98609161376953
Nearest Class Center Accuracy: 0.82225

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15344549715518951
Inter Cos: 0.17619796097278595
Norm Quadratic Average: 47.604671478271484
Nearest Class Center Accuracy: 0.802625

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16763606667518616
Inter Cos: 0.19433780014514923
Norm Quadratic Average: 62.92194366455078
Nearest Class Center Accuracy: 0.813625

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1896589994430542
Inter Cos: 0.19271539151668549
Norm Quadratic Average: 41.749298095703125
Nearest Class Center Accuracy: 0.85075

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2162134349346161
Inter Cos: 0.20021137595176697
Norm Quadratic Average: 39.93495559692383
Nearest Class Center Accuracy: 0.88775

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27342793345451355
Inter Cos: 0.1868032068014145
Norm Quadratic Average: 23.39957618713379
Nearest Class Center Accuracy: 0.926625

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.40037038922309875
Inter Cos: 0.2230542153120041
Norm Quadratic Average: 17.552766799926758
Nearest Class Center Accuracy: 0.972625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.642333984375
Linear Weight Rank: 4031
Intra Cos: 0.6113427877426147
Inter Cos: 0.2436518520116806
Norm Quadratic Average: 75.2426528930664
Nearest Class Center Accuracy: 0.99725

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.068336486816406
Linear Weight Rank: 3671
Intra Cos: 0.7238738536834717
Inter Cos: 0.23610776662826538
Norm Quadratic Average: 47.5561637878418
Nearest Class Center Accuracy: 0.999375

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.430777072906494
Linear Weight Rank: 10
Intra Cos: 0.7743825316429138
Inter Cos: 0.2628442645072937
Norm Quadratic Average: 36.36157989501953
Nearest Class Center Accuracy: 0.9995

Output Layer:
Intra Cos: 0.8239423036575317
Inter Cos: 0.37818968296051025
Norm Quadratic Average: 25.617839813232422
Nearest Class Center Accuracy: 0.99975

Test Set:
Average Loss: 0.0785736050158739
Accuracy: 0.981
NC1 Within Class Collapse: 1.8301116228103638
NC2 Equinorm: Features: 0.1057574674487114, Weights: 0.014440657570958138
NC2 Equiangle: Features: 0.2511222415500217, Weights: 0.09127972920735677
NC3 Self-Duality: 0.5340234041213989
NC4 NCC Mismatch: 0.015000000000000013

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: 0.1329766809940338
Inter Cos: 0.14806218445301056
Norm Quadratic Average: 45.58089065551758
Nearest Class Center Accuracy: 0.8195

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16624264419078827
Inter Cos: 0.201313316822052
Norm Quadratic Average: 46.1648063659668
Nearest Class Center Accuracy: 0.801

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17706994712352753
Inter Cos: 0.23031383752822876
Norm Quadratic Average: 60.96521759033203
Nearest Class Center Accuracy: 0.821

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16369913518428802
Inter Cos: 0.21826492249965668
Norm Quadratic Average: 40.68503189086914
Nearest Class Center Accuracy: 0.8495

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18599086999893188
Inter Cos: 0.23072148859500885
Norm Quadratic Average: 39.01298141479492
Nearest Class Center Accuracy: 0.876

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.234538733959198
Inter Cos: 0.2091694325208664
Norm Quadratic Average: 22.807022094726562
Nearest Class Center Accuracy: 0.925

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3405319154262543
Inter Cos: 0.23234286904335022
Norm Quadratic Average: 16.984390258789062
Nearest Class Center Accuracy: 0.9515

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.642333984375
Linear Weight Rank: 4031
Intra Cos: 0.5291444659233093
Inter Cos: 0.24808035790920258
Norm Quadratic Average: 72.43350982666016
Nearest Class Center Accuracy: 0.9705

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.068336486816406
Linear Weight Rank: 3671
Intra Cos: 0.6351444721221924
Inter Cos: 0.2489708513021469
Norm Quadratic Average: 45.67457580566406
Nearest Class Center Accuracy: 0.975

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.430777072906494
Linear Weight Rank: 10
Intra Cos: 0.6827303171157837
Inter Cos: 0.28871795535087585
Norm Quadratic Average: 34.987674713134766
Nearest Class Center Accuracy: 0.9765

Output Layer:
Intra Cos: 0.7234717011451721
Inter Cos: 0.3925199508666992
Norm Quadratic Average: 24.6451473236084
Nearest Class Center Accuracy: 0.9735

