Model save path: ./New_Models/bn_True_dataset_CIFAR10_epochs_200_lr_0.01_model_type_vgg11_rand_seed_979323_test_samples_None_train_samples_None_weight_decay_0.005.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0198909230530262
Inter Cos: 0.10477276891469955
Norm Quadratic Average: 27.59718894958496
Nearest Class Center Accuracy: 0.26968

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.020000584423542023
Inter Cos: 0.07429234683513641
Norm Quadratic Average: 3.3118696212768555
Nearest Class Center Accuracy: 0.4085

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.020028825849294662
Inter Cos: 0.05712038278579712
Norm Quadratic Average: 1.6607142686843872
Nearest Class Center Accuracy: 0.54218

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01663830503821373
Inter Cos: 0.048333462327718735
Norm Quadratic Average: 1.2949665784835815
Nearest Class Center Accuracy: 0.62236

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.024316702038049698
Inter Cos: 0.04535960778594017
Norm Quadratic Average: 0.877376914024353
Nearest Class Center Accuracy: 0.75924

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.05670211464166641
Inter Cos: 0.06410636007785797
Norm Quadratic Average: 0.6242964267730713
Nearest Class Center Accuracy: 0.9012

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3466199040412903
Inter Cos: 0.21259765326976776
Norm Quadratic Average: 0.4397294819355011
Nearest Class Center Accuracy: 0.99772

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8783083558082581
Inter Cos: 0.06684748828411102
Norm Quadratic Average: 0.7429160475730896
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.210655689239502
Linear Weight Rank: 166
Intra Cos: 0.9845746159553528
Inter Cos: 0.016281194984912872
Norm Quadratic Average: 23.673423767089844
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.2239246368408203
Linear Weight Rank: 1019
Intra Cos: 0.9910065531730652
Inter Cos: 0.05610869079828262
Norm Quadratic Average: 16.303932189941406
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2103421688079834
Linear Weight Rank: 9
Intra Cos: 0.9928604364395142
Inter Cos: 0.0792481079697609
Norm Quadratic Average: 11.49478530883789
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9939139485359192
Inter Cos: 0.09526322782039642
Norm Quadratic Average: 8.472613334655762
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.4010389477729797
Accuracy: 0.8773
NC1 Within Class Collapse: 2.9595980644226074
NC2 Equinorm: Features: 0.11537154763936996, Weights: 0.003251211019232869
NC2 Equiangle: Features: 0.12091929117838542, Weights: 0.0149879256884257
NC3 Self-Duality: 0.04675566032528877
NC4 NCC Mismatch: 0.01419999999999999

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018526077270507812
Inter Cos: 0.1042705774307251
Norm Quadratic Average: 27.550140380859375
Nearest Class Center Accuracy: 0.284

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018734121695160866
Inter Cos: 0.07593736052513123
Norm Quadratic Average: 3.3094632625579834
Nearest Class Center Accuracy: 0.4301

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018993036821484566
Inter Cos: 0.05831877142190933
Norm Quadratic Average: 1.66120183467865
Nearest Class Center Accuracy: 0.5522

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.015641380101442337
Inter Cos: 0.049331359565258026
Norm Quadratic Average: 1.2964324951171875
Nearest Class Center Accuracy: 0.6265

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.021181922405958176
Inter Cos: 0.046298105269670486
Norm Quadratic Average: 0.8775865435600281
Nearest Class Center Accuracy: 0.7216

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.042841002345085144
Inter Cos: 0.06590629369020462
Norm Quadratic Average: 0.620305597782135
Nearest Class Center Accuracy: 0.7966

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23690278828144073
Inter Cos: 0.2298465073108673
Norm Quadratic Average: 0.42630717158317566
Nearest Class Center Accuracy: 0.8594

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5007761716842651
Inter Cos: 0.23726607859134674
Norm Quadratic Average: 0.6779826879501343
Nearest Class Center Accuracy: 0.8758

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.210655689239502
Linear Weight Rank: 166
Intra Cos: 0.6064100861549377
Inter Cos: 0.2444790005683899
Norm Quadratic Average: 20.879825592041016
Nearest Class Center Accuracy: 0.876

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.2239246368408203
Linear Weight Rank: 1019
Intra Cos: 0.6175260543823242
Inter Cos: 0.254218190908432
Norm Quadratic Average: 14.357159614562988
Nearest Class Center Accuracy: 0.8766

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2103421688079834
Linear Weight Rank: 9
Intra Cos: 0.6231010556221008
Inter Cos: 0.26479920744895935
Norm Quadratic Average: 10.12109375
Nearest Class Center Accuracy: 0.8768

Output Layer:
Intra Cos: 0.627918004989624
Inter Cos: 0.27077972888946533
Norm Quadratic Average: 7.463155269622803
Nearest Class Center Accuracy: 0.8776

