Model save path: ./New_Models/bn_True_dataset_CIFAR100_epochs_200_lr_0.01_model_type_vgg11_rand_seed_979323_test_samples_None_train_samples_None_weight_decay_0.003.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.022893190383911133
Inter Cos: 0.07011394202709198
Norm Quadratic Average: 29.326318740844727
Nearest Class Center Accuracy: 0.03258

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.025678740814328194
Inter Cos: 0.02923343889415264
Norm Quadratic Average: 8.415238380432129
Nearest Class Center Accuracy: 0.04816

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.023254070430994034
Inter Cos: 0.024146102368831635
Norm Quadratic Average: 4.469756126403809
Nearest Class Center Accuracy: 0.06094

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01754116453230381
Inter Cos: 0.017940344288945198
Norm Quadratic Average: 3.339694023132324
Nearest Class Center Accuracy: 0.06952

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02324880100786686
Inter Cos: 0.019228149205446243
Norm Quadratic Average: 2.2850356101989746
Nearest Class Center Accuracy: 0.08018

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02603144198656082
Inter Cos: 0.020189622417092323
Norm Quadratic Average: 1.5486249923706055
Nearest Class Center Accuracy: 0.08848

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08272552490234375
Inter Cos: 0.05256663262844086
Norm Quadratic Average: 1.066929817199707
Nearest Class Center Accuracy: 0.09936

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5162009596824646
Inter Cos: 0.15185585618019104
Norm Quadratic Average: 1.1039389371871948
Nearest Class Center Accuracy: 0.1

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 4.507725715637207
Linear Weight Rank: 510
Intra Cos: 0.9056800603866577
Inter Cos: 0.2627105712890625
Norm Quadratic Average: 41.06413650512695
Nearest Class Center Accuracy: 0.1

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 4.731169700622559
Linear Weight Rank: 1571
Intra Cos: 0.9426450133323669
Inter Cos: 0.320584774017334
Norm Quadratic Average: 31.79363250732422
Nearest Class Center Accuracy: 0.1

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 4.826894283294678
Linear Weight Rank: 97
Intra Cos: 0.943645715713501
Inter Cos: 0.36550596356391907
Norm Quadratic Average: 29.443899154663086
Nearest Class Center Accuracy: 0.1

Output Layer:
Intra Cos: 0.9497511386871338
Inter Cos: 0.4097778797149658
Norm Quadratic Average: 29.998018264770508
Nearest Class Center Accuracy: 0.1

Test Set:
Average Loss: 1.7291927740097046
Accuracy: 0.5917
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.23890092968940735, Weights: 0.01594417542219162
NC2 Equiangle: Features: 0.19435588798137626, Weights: 0.14348928740530303
NC3 Self-Duality: 0.24969777464866638
NC4 NCC Mismatch: 0.15639999999999998

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.006621268577873707
Inter Cos: 0.4067547619342804
Norm Quadratic Average: 29.42218780517578
Nearest Class Center Accuracy: 0.1136

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.012669534422457218
Inter Cos: 0.24596606194972992
Norm Quadratic Average: 8.474102973937988
Nearest Class Center Accuracy: 0.2595

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01630912721157074
Inter Cos: 0.2040158212184906
Norm Quadratic Average: 4.501820087432861
Nearest Class Center Accuracy: 0.3935

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.014101273380219936
Inter Cos: 0.1374337524175644
Norm Quadratic Average: 3.3548216819763184
Nearest Class Center Accuracy: 0.5139

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01264291163533926
Inter Cos: 0.1430162787437439
Norm Quadratic Average: 2.290536642074585
Nearest Class Center Accuracy: 0.6255

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.010400920175015926
Inter Cos: 0.13157358765602112
Norm Quadratic Average: 1.5396802425384521
Nearest Class Center Accuracy: 0.6919

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02140244096517563
Inter Cos: 0.1853206902742386
Norm Quadratic Average: 1.0298912525177002
Nearest Class Center Accuracy: 0.6738

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06562136113643646
Inter Cos: 0.4139278531074524
Norm Quadratic Average: 0.9317108988761902
Nearest Class Center Accuracy: 0.6102

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 4.507725715637207
Linear Weight Rank: 510
Intra Cos: 0.2232895940542221
Inter Cos: 0.5206527709960938
Norm Quadratic Average: 31.0501708984375
Nearest Class Center Accuracy: 0.5929

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 4.731169700622559
Linear Weight Rank: 1571
Intra Cos: 0.262112557888031
Inter Cos: 0.5568200349807739
Norm Quadratic Average: 24.24658966064453
Nearest Class Center Accuracy: 0.5915

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 4.826894283294678
Linear Weight Rank: 97
Intra Cos: 0.25985464453697205
Inter Cos: 0.566728413105011
Norm Quadratic Average: 22.798112869262695
Nearest Class Center Accuracy: 0.5908

Output Layer:
Intra Cos: 0.267855167388916
Inter Cos: 0.5917878150939941
Norm Quadratic Average: 23.08809471130371
Nearest Class Center Accuracy: 0.5898

