Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_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: 0.08946064114570618
Inter Cos: 0.11311884969472885
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: 0.10893946886062622
Inter Cos: 0.13259518146514893
Norm Quadratic Average: 46.9553108215332
Nearest Class Center Accuracy: 0.82475

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15170341730117798
Inter Cos: 0.17005868256092072
Norm Quadratic Average: 46.30091857910156
Nearest Class Center Accuracy: 0.805125

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17009498178958893
Inter Cos: 0.1778746098279953
Norm Quadratic Average: 60.59917068481445
Nearest Class Center Accuracy: 0.816625

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18904830515384674
Inter Cos: 0.17156097292900085
Norm Quadratic Average: 39.0827751159668
Nearest Class Center Accuracy: 0.85375

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2160486876964569
Inter Cos: 0.18969613313674927
Norm Quadratic Average: 38.062530517578125
Nearest Class Center Accuracy: 0.894125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27340951561927795
Inter Cos: 0.17918634414672852
Norm Quadratic Average: 22.199655532836914
Nearest Class Center Accuracy: 0.939125

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3931109309196472
Inter Cos: 0.19922995567321777
Norm Quadratic Average: 17.09427833557129
Nearest Class Center Accuracy: 0.9785

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.6350326538086
Linear Weight Rank: 4031
Intra Cos: 0.6270350813865662
Inter Cos: 0.2518865168094635
Norm Quadratic Average: 74.32034301757812
Nearest Class Center Accuracy: 0.99775

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.06776809692383
Linear Weight Rank: 3670
Intra Cos: 0.733879029750824
Inter Cos: 0.2637699544429779
Norm Quadratic Average: 47.233882904052734
Nearest Class Center Accuracy: 0.999375

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.436986207962036
Linear Weight Rank: 10
Intra Cos: 0.7796332240104675
Inter Cos: 0.25518330931663513
Norm Quadratic Average: 36.074440002441406
Nearest Class Center Accuracy: 0.999625

Output Layer:
Intra Cos: 0.8265700340270996
Inter Cos: 0.33932116627693176
Norm Quadratic Average: 25.513538360595703
Nearest Class Center Accuracy: 0.999625

Test Set:
Average Loss: 0.08108662104606629
Accuracy: 0.9815
NC1 Within Class Collapse: 1.7616567611694336
NC2 Equinorm: Features: 0.10069337487220764, Weights: 0.014668582007288933
NC2 Equiangle: Features: 0.24300721486409504, Weights: 0.09427091810438368
NC3 Self-Duality: 0.5313544273376465
NC4 NCC Mismatch: 0.01200000000000001

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133809596300125
Inter Cos: 0.11957789212465286
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: 0.13291096687316895
Inter Cos: 0.14476381242275238
Norm Quadratic Average: 45.82860565185547
Nearest Class Center Accuracy: 0.8165

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17300169169902802
Inter Cos: 0.19859854876995087
Norm Quadratic Average: 45.10275650024414
Nearest Class Center Accuracy: 0.801

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18149948120117188
Inter Cos: 0.21751876175403595
Norm Quadratic Average: 58.94027328491211
Nearest Class Center Accuracy: 0.813

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17321071028709412
Inter Cos: 0.20662078261375427
Norm Quadratic Average: 38.060855865478516
Nearest Class Center Accuracy: 0.844

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19536568224430084
Inter Cos: 0.22310757637023926
Norm Quadratic Average: 37.16107177734375
Nearest Class Center Accuracy: 0.8835

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24985121190547943
Inter Cos: 0.20967353880405426
Norm Quadratic Average: 21.693267822265625
Nearest Class Center Accuracy: 0.9335

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3549502193927765
Inter Cos: 0.2389800101518631
Norm Quadratic Average: 16.59423828125
Nearest Class Center Accuracy: 0.9545

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.6350326538086
Linear Weight Rank: 4031
Intra Cos: 0.5678321719169617
Inter Cos: 0.269549161195755
Norm Quadratic Average: 71.55216217041016
Nearest Class Center Accuracy: 0.974

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.06776809692383
Linear Weight Rank: 3670
Intra Cos: 0.6687259078025818
Inter Cos: 0.25940680503845215
Norm Quadratic Average: 45.303955078125
Nearest Class Center Accuracy: 0.9775

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.436986207962036
Linear Weight Rank: 10
Intra Cos: 0.7096010446548462
Inter Cos: 0.24712136387825012
Norm Quadratic Average: 34.61194610595703
Nearest Class Center Accuracy: 0.9775

Output Layer:
Intra Cos: 0.748956024646759
Inter Cos: 0.32624250650405884
Norm Quadratic Average: 24.4526424407959
Nearest Class Center Accuracy: 0.976

