Model save path: ./New_Models/bn_True_dataset_CIFAR10_epochs_200_lr_0.01_model_type_vgg11_rand_seed_314159_test_samples_None_train_samples_None_weight_decay_0.0003.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01989092119038105
Inter Cos: 0.10477276146411896
Norm Quadratic Average: 27.59718132019043
Nearest Class Center Accuracy: 0.26968

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01843789964914322
Inter Cos: 0.07229937613010406
Norm Quadratic Average: 37.745521545410156
Nearest Class Center Accuracy: 0.40256

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.019885409623384476
Inter Cos: 0.055016420781612396
Norm Quadratic Average: 19.592164993286133
Nearest Class Center Accuracy: 0.53036

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.015741484239697456
Inter Cos: 0.04604317992925644
Norm Quadratic Average: 19.408000946044922
Nearest Class Center Accuracy: 0.60998

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02285011112689972
Inter Cos: 0.04052899405360222
Norm Quadratic Average: 12.982980728149414
Nearest Class Center Accuracy: 0.7178

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.038842808455228806
Inter Cos: 0.04278014972805977
Norm Quadratic Average: 16.05843734741211
Nearest Class Center Accuracy: 0.81404

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12435312569141388
Inter Cos: 0.09822874516248703
Norm Quadratic Average: 12.520357131958008
Nearest Class Center Accuracy: 0.93728

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.47325965762138367
Inter Cos: 0.1485542505979538
Norm Quadratic Average: 10.148058891296387
Nearest Class Center Accuracy: 0.99328

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.62332534790039
Linear Weight Rank: 4031
Intra Cos: 0.7723615765571594
Inter Cos: 0.17613977193832397
Norm Quadratic Average: 60.54237365722656
Nearest Class Center Accuracy: 0.98842

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 16.296640396118164
Linear Weight Rank: 3667
Intra Cos: 0.9533396363258362
Inter Cos: -0.007763550616800785
Norm Quadratic Average: 41.812530517578125
Nearest Class Center Accuracy: 0.9999

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 3.143381357192993
Linear Weight Rank: 10
Intra Cos: 0.941076397895813
Inter Cos: -0.013144901022315025
Norm Quadratic Average: 23.111480712890625
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.987940788269043
Inter Cos: 0.2894352972507477
Norm Quadratic Average: 19.01573371887207
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.9915934543609619
Accuracy: 0.8425
NC1 Within Class Collapse: 4.609488487243652
NC2 Equinorm: Features: 0.23283621668815613, Weights: 0.022363940253853798
NC2 Equiangle: Features: 0.1074789047241211, Weights: 0.07801119486490886
NC3 Self-Duality: 0.46841293573379517
NC4 NCC Mismatch: 0.0655

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018526073545217514
Inter Cos: 0.1042705774307251
Norm Quadratic Average: 27.550134658813477
Nearest Class Center Accuracy: 0.284

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01739746518433094
Inter Cos: 0.07401783764362335
Norm Quadratic Average: 37.71896743774414
Nearest Class Center Accuracy: 0.4186

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01865445077419281
Inter Cos: 0.05634607374668121
Norm Quadratic Average: 19.599029541015625
Nearest Class Center Accuracy: 0.5416

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01456976868212223
Inter Cos: 0.04702488332986832
Norm Quadratic Average: 19.41940689086914
Nearest Class Center Accuracy: 0.6139

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.019560862332582474
Inter Cos: 0.041431691497564316
Norm Quadratic Average: 12.987030029296875
Nearest Class Center Accuracy: 0.6889

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03078257292509079
Inter Cos: 0.0451156385242939
Norm Quadratic Average: 16.02597999572754
Nearest Class Center Accuracy: 0.7373

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08882362395524979
Inter Cos: 0.10552534461021423
Norm Quadratic Average: 12.431229591369629
Nearest Class Center Accuracy: 0.7796

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.28092730045318604
Inter Cos: 0.1907656043767929
Norm Quadratic Average: 9.819292068481445
Nearest Class Center Accuracy: 0.8131

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.62332534790039
Linear Weight Rank: 4031
Intra Cos: 0.5241468548774719
Inter Cos: 0.31685972213745117
Norm Quadratic Average: 57.388912200927734
Nearest Class Center Accuracy: 0.7958

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 16.296640396118164
Linear Weight Rank: 3667
Intra Cos: 0.563103199005127
Inter Cos: 0.24211469292640686
Norm Quadratic Average: 37.71673583984375
Nearest Class Center Accuracy: 0.8106

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 3.143381357192993
Linear Weight Rank: 10
Intra Cos: 0.5375757217407227
Inter Cos: 0.23190663754940033
Norm Quadratic Average: 21.222755432128906
Nearest Class Center Accuracy: 0.8227

Output Layer:
Intra Cos: 0.5777110457420349
Inter Cos: 0.32307401299476624
Norm Quadratic Average: 17.165328979492188
Nearest Class Center Accuracy: 0.836

