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_0.001.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: 0.09341336786746979
Inter Cos: 0.0981115773320198
Norm Quadratic Average: 3.9560093879699707
Nearest Class Center Accuracy: 0.8583

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1581731140613556
Inter Cos: 0.11761801689863205
Norm Quadratic Average: 2.327960729598999
Nearest Class Center Accuracy: 0.9180666666666667

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1831735521554947
Inter Cos: 0.11505234986543655
Norm Quadratic Average: 1.6011192798614502
Nearest Class Center Accuracy: 0.9514666666666667

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25415557622909546
Inter Cos: 0.09440989792346954
Norm Quadratic Average: 1.1712939739227295
Nearest Class Center Accuracy: 0.9904666666666667

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.47720983624458313
Inter Cos: 0.11144349724054337
Norm Quadratic Average: 0.8972876071929932
Nearest Class Center Accuracy: 0.9984666666666666

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6982495188713074
Inter Cos: 0.07195909321308136
Norm Quadratic Average: 0.7702654600143433
Nearest Class Center Accuracy: 0.9999833333333333

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9592971205711365
Inter Cos: 0.021775510162115097
Norm Quadratic Average: 1.021450400352478
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 3.1026499271392822
Linear Weight Rank: 4028
Intra Cos: 0.9954189658164978
Inter Cos: -0.028909988701343536
Norm Quadratic Average: 25.928207397460938
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.4751908779144287
Linear Weight Rank: 3637
Intra Cos: 0.9973886013031006
Inter Cos: -0.0007239188998937607
Norm Quadratic Average: 18.720388412475586
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.301156520843506
Linear Weight Rank: 9
Intra Cos: 0.9977701902389526
Inter Cos: 0.017013274133205414
Norm Quadratic Average: 13.632119178771973
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9982640147209167
Inter Cos: 0.0543973445892334
Norm Quadratic Average: 10.604705810546875
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.01824052899675444
Accuracy: 0.9953
NC1 Within Class Collapse: 0.11601758003234863
NC2 Equinorm: Features: 0.024409610778093338, Weights: 0.006453297566622496
NC2 Equiangle: Features: 0.07345654699537489, Weights: 0.03568703863355849
NC3 Self-Duality: 0.013468122109770775
NC4 NCC Mismatch: 9.999999999998899e-05

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: 0.10252754390239716
Inter Cos: 0.09924652427434921
Norm Quadratic Average: 3.9298346042633057
Nearest Class Center Accuracy: 0.8708

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1683807224035263
Inter Cos: 0.11661917716264725
Norm Quadratic Average: 2.3146445751190186
Nearest Class Center Accuracy: 0.9261

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19461707770824432
Inter Cos: 0.11265046149492264
Norm Quadratic Average: 1.5938043594360352
Nearest Class Center Accuracy: 0.9543

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2660769820213318
Inter Cos: 0.09860227257013321
Norm Quadratic Average: 1.1659398078918457
Nearest Class Center Accuracy: 0.9863

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4891666769981384
Inter Cos: 0.11278344690799713
Norm Quadratic Average: 0.8955057859420776
Nearest Class Center Accuracy: 0.9925

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6984083652496338
Inter Cos: 0.07738352566957474
Norm Quadratic Average: 0.7698143720626831
Nearest Class Center Accuracy: 0.9946

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9476739168167114
Inter Cos: 0.03180614858865738
Norm Quadratic Average: 1.0167561769485474
Nearest Class Center Accuracy: 0.995

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 3.1026499271392822
Linear Weight Rank: 4028
Intra Cos: 0.9769986867904663
Inter Cos: -0.016299515962600708
Norm Quadratic Average: 25.77236557006836
Nearest Class Center Accuracy: 0.9952

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.4751908779144287
Linear Weight Rank: 3637
Intra Cos: 0.9793134331703186
Inter Cos: 0.011840182356536388
Norm Quadratic Average: 18.606765747070312
Nearest Class Center Accuracy: 0.9952

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.301156520843506
Linear Weight Rank: 9
Intra Cos: 0.979931116104126
Inter Cos: 0.030306588858366013
Norm Quadratic Average: 13.550310134887695
Nearest Class Center Accuracy: 0.9952

Output Layer:
Intra Cos: 0.9813598394393921
Inter Cos: 0.06399895995855331
Norm Quadratic Average: 10.541202545166016
Nearest Class Center Accuracy: 0.9952

