Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_979323_test_samples_None_train_samples_None_weight_decay_0.01.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09116753935813904
Inter Cos: 0.10967151820659637
Norm Quadratic Average: 23.567676544189453
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1036975085735321
Inter Cos: 0.10660486668348312
Norm Quadratic Average: 2.1888279914855957
Nearest Class Center Accuracy: 0.8585666666666667

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17576956748962402
Inter Cos: 0.1318790316581726
Norm Quadratic Average: 1.1029868125915527
Nearest Class Center Accuracy: 0.9173

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22299808263778687
Inter Cos: 0.1440391093492508
Norm Quadratic Average: 0.6876876354217529
Nearest Class Center Accuracy: 0.9545833333333333

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.31056392192840576
Inter Cos: 0.13286933302879333
Norm Quadratic Average: 0.33618614077568054
Nearest Class Center Accuracy: 0.9897333333333334

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6390530467033386
Inter Cos: 0.1912284642457962
Norm Quadratic Average: 0.31258779764175415
Nearest Class Center Accuracy: 0.9996

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8633337616920471
Inter Cos: 0.21871481835842133
Norm Quadratic Average: 0.48103711009025574
Nearest Class Center Accuracy: 1.0

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9806625247001648
Inter Cos: 0.22232754528522491
Norm Quadratic Average: 0.8732452988624573
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.04032826423645
Linear Weight Rank: 8
Intra Cos: 0.9971944689750671
Inter Cos: 0.2191656231880188
Norm Quadratic Average: 22.9791259765625
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.0413894653320312
Linear Weight Rank: 1163
Intra Cos: 0.997922420501709
Inter Cos: 0.18755373358726501
Norm Quadratic Average: 16.37748908996582
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.0423452854156494
Linear Weight Rank: 8
Intra Cos: 0.9983499646186829
Inter Cos: 0.1633192002773285
Norm Quadratic Average: 11.926608085632324
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9982074499130249
Inter Cos: 0.15709441900253296
Norm Quadratic Average: 9.31682300567627
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.01814973718971014
Accuracy: 0.9955
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.032734498381614685, Weights: 0.01222047209739685
NC2 Equiangle: Features: 0.1729419920179579, Weights: 0.15564600626627603
NC3 Self-Duality: 0.03118346817791462
NC4 NCC Mismatch: 0.00019999999999997797

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219582170248032
Inter Cos: 0.12048851698637009
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: 0.1143009141087532
Inter Cos: 0.10723736882209778
Norm Quadratic Average: 2.1776809692382812
Nearest Class Center Accuracy: 0.8708

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18702945113182068
Inter Cos: 0.13025064766407013
Norm Quadratic Average: 1.0985668897628784
Nearest Class Center Accuracy: 0.9267

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23588912189006805
Inter Cos: 0.14087149500846863
Norm Quadratic Average: 0.6865135431289673
Nearest Class Center Accuracy: 0.9562

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.32048141956329346
Inter Cos: 0.14617398381233215
Norm Quadratic Average: 0.3353653848171234
Nearest Class Center Accuracy: 0.9873

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6459394693374634
Inter Cos: 0.19177377223968506
Norm Quadratic Average: 0.3123411238193512
Nearest Class Center Accuracy: 0.9934

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8551183342933655
Inter Cos: 0.22377441823482513
Norm Quadratic Average: 0.48080679774284363
Nearest Class Center Accuracy: 0.9949

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9704968929290771
Inter Cos: 0.22645556926727295
Norm Quadratic Average: 0.8695748448371887
Nearest Class Center Accuracy: 0.9957

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.04032826423645
Linear Weight Rank: 8
Intra Cos: 0.9816979169845581
Inter Cos: 0.22427231073379517
Norm Quadratic Average: 22.876022338867188
Nearest Class Center Accuracy: 0.9956

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.0413894653320312
Linear Weight Rank: 1163
Intra Cos: 0.9824675917625427
Inter Cos: 0.18862217664718628
Norm Quadratic Average: 16.300525665283203
Nearest Class Center Accuracy: 0.9955

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.0423452854156494
Linear Weight Rank: 8
Intra Cos: 0.9826769232749939
Inter Cos: 0.16447076201438904
Norm Quadratic Average: 11.8687744140625
Nearest Class Center Accuracy: 0.9955

Output Layer:
Intra Cos: 0.9837313294410706
Inter Cos: 0.1622626781463623
Norm Quadratic Average: 9.268013000488281
Nearest Class Center Accuracy: 0.9956

