Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_weight_decay_0.0001.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: 23.532936096191406
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10493304580450058
Inter Cos: 0.12060224264860153
Norm Quadratic Average: 86.5949935913086
Nearest Class Center Accuracy: 0.835125

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.144180566072464
Inter Cos: 0.13501080870628357
Norm Quadratic Average: 60.572784423828125
Nearest Class Center Accuracy: 0.847125

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14242421090602875
Inter Cos: 0.12068068236112595
Norm Quadratic Average: 56.695030212402344
Nearest Class Center Accuracy: 0.868875

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16196373105049133
Inter Cos: 0.09934689849615097
Norm Quadratic Average: 34.45777130126953
Nearest Class Center Accuracy: 0.903875

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1671120822429657
Inter Cos: 0.08451032638549805
Norm Quadratic Average: 35.69691848754883
Nearest Class Center Accuracy: 0.928125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19285546243190765
Inter Cos: 0.07219894975423813
Norm Quadratic Average: 24.088369369506836
Nearest Class Center Accuracy: 0.970625

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.26764151453971863
Inter Cos: 0.08534488826990128
Norm Quadratic Average: 18.84581184387207
Nearest Class Center Accuracy: 0.9955

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.88624572753906
Linear Weight Rank: 4031
Intra Cos: 0.47947317361831665
Inter Cos: 0.12496641278266907
Norm Quadratic Average: 118.44586944580078
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.775909423828125
Linear Weight Rank: 3671
Intra Cos: 0.6216940879821777
Inter Cos: 0.16011455655097961
Norm Quadratic Average: 65.21617126464844
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2914507389068604
Linear Weight Rank: 10
Intra Cos: 0.7405446171760559
Inter Cos: 0.184657022356987
Norm Quadratic Average: 42.2239990234375
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.8984769582748413
Inter Cos: 0.27950039505958557
Norm Quadratic Average: 23.347980499267578
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.09941924268007278
Accuracy: 0.975
NC1 Within Class Collapse: 1.6852593421936035
NC2 Equinorm: Features: 0.08222457021474838, Weights: 0.016057252883911133
NC2 Equiangle: Features: 0.2120338863796658, Weights: 0.08901229434543186
NC3 Self-Duality: 0.6551033854484558
NC4 NCC Mismatch: 0.005499999999999949

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
Inter Cos: 0.11957792192697525
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: 0.12090980261564255
Inter Cos: 0.13037841022014618
Norm Quadratic Average: 85.18647003173828
Nearest Class Center Accuracy: 0.8255

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1433233767747879
Inter Cos: 0.15196175873279572
Norm Quadratic Average: 59.58518600463867
Nearest Class Center Accuracy: 0.84

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1416410207748413
Inter Cos: 0.14043468236923218
Norm Quadratic Average: 55.86387252807617
Nearest Class Center Accuracy: 0.8615

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15270425379276276
Inter Cos: 0.1160712018609047
Norm Quadratic Average: 34.210731506347656
Nearest Class Center Accuracy: 0.8985

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15660899877548218
Inter Cos: 0.10381656140089035
Norm Quadratic Average: 35.478878021240234
Nearest Class Center Accuracy: 0.92

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18298625946044922
Inter Cos: 0.08797671645879745
Norm Quadratic Average: 23.87911605834961
Nearest Class Center Accuracy: 0.9465

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24739085137844086
Inter Cos: 0.09369051456451416
Norm Quadratic Average: 18.60547637939453
Nearest Class Center Accuracy: 0.9685

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.88624572753906
Linear Weight Rank: 4031
Intra Cos: 0.3958900272846222
Inter Cos: 0.12164534628391266
Norm Quadratic Average: 115.90412902832031
Nearest Class Center Accuracy: 0.973

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.775909423828125
Linear Weight Rank: 3671
Intra Cos: 0.5137773752212524
Inter Cos: 0.15780891478061676
Norm Quadratic Average: 63.4883918762207
Nearest Class Center Accuracy: 0.9755

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2914507389068604
Linear Weight Rank: 10
Intra Cos: 0.6206748485565186
Inter Cos: 0.18501883745193481
Norm Quadratic Average: 40.937767028808594
Nearest Class Center Accuracy: 0.975

Output Layer:
Intra Cos: 0.7741205096244812
Inter Cos: 0.2803032398223877
Norm Quadratic Average: 22.483917236328125
Nearest Class Center Accuracy: 0.9725

