Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_weight_decay_0.005.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946064859628677
Inter Cos: 0.11311884224414825
Norm Quadratic Average: 23.53293800354004
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10084828734397888
Inter Cos: 0.12438879907131195
Norm Quadratic Average: 65.44712829589844
Nearest Class Center Accuracy: 0.83

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14110304415225983
Inter Cos: 0.13403944671154022
Norm Quadratic Average: 44.48810577392578
Nearest Class Center Accuracy: 0.847375

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14504355192184448
Inter Cos: 0.12435692548751831
Norm Quadratic Average: 44.89531707763672
Nearest Class Center Accuracy: 0.869125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17173920571804047
Inter Cos: 0.10931230336427689
Norm Quadratic Average: 27.289194107055664
Nearest Class Center Accuracy: 0.904

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17597639560699463
Inter Cos: 0.09292517602443695
Norm Quadratic Average: 27.990245819091797
Nearest Class Center Accuracy: 0.935125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.217340886592865
Inter Cos: 0.08979671448469162
Norm Quadratic Average: 19.249446868896484
Nearest Class Center Accuracy: 0.978

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.31413236260414124
Inter Cos: 0.10556603968143463
Norm Quadratic Average: 14.832395553588867
Nearest Class Center Accuracy: 0.997625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.7441635131836
Linear Weight Rank: 4031
Intra Cos: 0.5568057894706726
Inter Cos: 0.12381800264120102
Norm Quadratic Average: 100.294677734375
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.24436950683594
Linear Weight Rank: 3670
Intra Cos: 0.7136151790618896
Inter Cos: 0.14919595420360565
Norm Quadratic Average: 49.07052230834961
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9354184865951538
Linear Weight Rank: 10
Intra Cos: 0.8223372101783752
Inter Cos: 0.16436220705509186
Norm Quadratic Average: 28.80789566040039
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9190999269485474
Inter Cos: 0.20209763944149017
Norm Quadratic Average: 14.574728012084961
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.07612923038005828
Accuracy: 0.976
NC1 Within Class Collapse: 1.5364677906036377
NC2 Equinorm: Features: 0.05253676325082779, Weights: 0.010130774229764938
NC2 Equiangle: Features: 0.1842023213704427, Weights: 0.08312638070848254
NC3 Self-Duality: 0.5155739188194275
NC4 NCC Mismatch: 0.009000000000000008

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133810341358185
Inter Cos: 0.11957789957523346
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: 0.12375063449144363
Inter Cos: 0.1297559142112732
Norm Quadratic Average: 64.21575164794922
Nearest Class Center Accuracy: 0.8225

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1467660814523697
Inter Cos: 0.15421752631664276
Norm Quadratic Average: 43.86214828491211
Nearest Class Center Accuracy: 0.8445

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14667461812496185
Inter Cos: 0.1447063535451889
Norm Quadratic Average: 44.35041427612305
Nearest Class Center Accuracy: 0.8685

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16510896384716034
Inter Cos: 0.12686598300933838
Norm Quadratic Average: 27.149080276489258
Nearest Class Center Accuracy: 0.899

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16716130077838898
Inter Cos: 0.11300172656774521
Norm Quadratic Average: 27.890623092651367
Nearest Class Center Accuracy: 0.922

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20080852508544922
Inter Cos: 0.09827504307031631
Norm Quadratic Average: 19.20261573791504
Nearest Class Center Accuracy: 0.953

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.28010714054107666
Inter Cos: 0.10750646144151688
Norm Quadratic Average: 14.729935646057129
Nearest Class Center Accuracy: 0.971

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.7441635131836
Linear Weight Rank: 4031
Intra Cos: 0.45542511343955994
Inter Cos: 0.1313442438840866
Norm Quadratic Average: 98.10939025878906
Nearest Class Center Accuracy: 0.9765

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.24436950683594
Linear Weight Rank: 3670
Intra Cos: 0.5959117412567139
Inter Cos: 0.16094925999641418
Norm Quadratic Average: 47.65294647216797
Nearest Class Center Accuracy: 0.974

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9354184865951538
Linear Weight Rank: 10
Intra Cos: 0.7043384909629822
Inter Cos: 0.18193472921848297
Norm Quadratic Average: 27.873130798339844
Nearest Class Center Accuracy: 0.975

Output Layer:
Intra Cos: 0.8079428672790527
Inter Cos: 0.24586544930934906
Norm Quadratic Average: 14.037382125854492
Nearest Class Center Accuracy: 0.9765

