Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_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: 0.08946067094802856
Inter Cos: 0.11311887949705124
Norm Quadratic Average: 23.532936096191406
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10028471052646637
Inter Cos: 0.1208638921380043
Norm Quadratic Average: 57.13267135620117
Nearest Class Center Accuracy: 0.831875

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1413111835718155
Inter Cos: 0.14005805552005768
Norm Quadratic Average: 35.616920471191406
Nearest Class Center Accuracy: 0.850125

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13894064724445343
Inter Cos: 0.13134469091892242
Norm Quadratic Average: 35.68198776245117
Nearest Class Center Accuracy: 0.870125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1753712296485901
Inter Cos: 0.10859523713588715
Norm Quadratic Average: 22.035205841064453
Nearest Class Center Accuracy: 0.91775

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2005620151758194
Inter Cos: 0.09401047229766846
Norm Quadratic Average: 22.56293296813965
Nearest Class Center Accuracy: 0.948875

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24150659143924713
Inter Cos: 0.11571476608514786
Norm Quadratic Average: 15.17434024810791
Nearest Class Center Accuracy: 0.9865

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.37644049525260925
Inter Cos: 0.10986313968896866
Norm Quadratic Average: 11.736043930053711
Nearest Class Center Accuracy: 0.999375

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.74105453491211
Linear Weight Rank: 4031
Intra Cos: 0.656571626663208
Inter Cos: 0.12401096522808075
Norm Quadratic Average: 87.96430969238281
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.377212524414062
Linear Weight Rank: 3671
Intra Cos: 0.8165141940116882
Inter Cos: 0.16163361072540283
Norm Quadratic Average: 41.4160270690918
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.7120460271835327
Linear Weight Rank: 10
Intra Cos: 0.8914803862571716
Inter Cos: 0.2015564739704132
Norm Quadratic Average: 23.992284774780273
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.935319185256958
Inter Cos: 0.2647007405757904
Norm Quadratic Average: 12.560572624206543
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.07151077699661255
Accuracy: 0.9795
NC1 Within Class Collapse: 1.3474652767181396
NC2 Equinorm: Features: 0.08286654204130173, Weights: 0.017523543909192085
NC2 Equiangle: Features: 0.20059390597873264, Weights: 0.08719798194037544
NC3 Self-Duality: 0.37884220480918884
NC4 NCC Mismatch: 0.0024999999999999467

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
Inter Cos: 0.11957791447639465
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: 0.1287251114845276
Inter Cos: 0.13109204173088074
Norm Quadratic Average: 56.249881744384766
Nearest Class Center Accuracy: 0.827

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16208069026470184
Inter Cos: 0.15473248064517975
Norm Quadratic Average: 35.2973518371582
Nearest Class Center Accuracy: 0.842

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16170288622379303
Inter Cos: 0.14249999821186066
Norm Quadratic Average: 35.37453079223633
Nearest Class Center Accuracy: 0.8655

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1757572889328003
Inter Cos: 0.1224619671702385
Norm Quadratic Average: 21.959440231323242
Nearest Class Center Accuracy: 0.916

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1905597448348999
Inter Cos: 0.11706997454166412
Norm Quadratic Average: 22.517568588256836
Nearest Class Center Accuracy: 0.9345

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23748275637626648
Inter Cos: 0.12452251464128494
Norm Quadratic Average: 15.147260665893555
Nearest Class Center Accuracy: 0.9595

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3368740379810333
Inter Cos: 0.1215907409787178
Norm Quadratic Average: 11.671529769897461
Nearest Class Center Accuracy: 0.9765

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.74105453491211
Linear Weight Rank: 4031
Intra Cos: 0.5562281012535095
Inter Cos: 0.15540432929992676
Norm Quadratic Average: 85.95291900634766
Nearest Class Center Accuracy: 0.9805

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.377212524414062
Linear Weight Rank: 3671
Intra Cos: 0.7114689350128174
Inter Cos: 0.17087072134017944
Norm Quadratic Average: 40.19841384887695
Nearest Class Center Accuracy: 0.979

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.7120460271835327
Linear Weight Rank: 10
Intra Cos: 0.7964560985565186
Inter Cos: 0.1903809905052185
Norm Quadratic Average: 23.225486755371094
Nearest Class Center Accuracy: 0.979

Output Layer:
Intra Cos: 0.829984724521637
Inter Cos: 0.24676723778247833
Norm Quadratic Average: 12.11418342590332
Nearest Class Center Accuracy: 0.977

