Model save path: ./New_Models/bn_False_dataset_CIFAR100_epochs_200_lr_0.01_model_type_vgg11_rand_seed_265358_test_samples_None_train_samples_None_weight_decay_0.0001.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.022893192246556282
Inter Cos: 0.07011394202709198
Norm Quadratic Average: 29.326324462890625
Nearest Class Center Accuracy: 0.03258

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.030311796814203262
Inter Cos: 0.03059757687151432
Norm Quadratic Average: 42.11024856567383
Nearest Class Center Accuracy: 0.04708

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.029605884104967117
Inter Cos: 0.030999111011624336
Norm Quadratic Average: 54.25292205810547
Nearest Class Center Accuracy: 0.05682

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.025550998747348785
Inter Cos: 0.024638444185256958
Norm Quadratic Average: 89.8838119506836
Nearest Class Center Accuracy: 0.0651

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.031317271292209625
Inter Cos: 0.025451336055994034
Norm Quadratic Average: 68.68775177001953
Nearest Class Center Accuracy: 0.07224

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03204875439405441
Inter Cos: 0.026501167565584183
Norm Quadratic Average: 66.01597595214844
Nearest Class Center Accuracy: 0.0759

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06371060013771057
Inter Cos: 0.04068872705101967
Norm Quadratic Average: 31.412382125854492
Nearest Class Center Accuracy: 0.0877

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18846680223941803
Inter Cos: 0.09902484714984894
Norm Quadratic Average: 17.06084632873535
Nearest Class Center Accuracy: 0.09674

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 74.55078125
Linear Weight Rank: 4031
Intra Cos: 0.5718863606452942
Inter Cos: 0.18135103583335876
Norm Quadratic Average: 61.83989715576172
Nearest Class Center Accuracy: 0.09922

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 33.23082733154297
Linear Weight Rank: 3664
Intra Cos: 0.7169297337532043
Inter Cos: 0.16858991980552673
Norm Quadratic Average: 45.52302551269531
Nearest Class Center Accuracy: 0.0998

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 13.724163055419922
Linear Weight Rank: 98
Intra Cos: 0.8016127943992615
Inter Cos: 0.22417302429676056
Norm Quadratic Average: 39.726646423339844
Nearest Class Center Accuracy: 0.0999

Output Layer:
Intra Cos: 0.8856590390205383
Inter Cos: 0.47235557436943054
Norm Quadratic Average: 71.8371810913086
Nearest Class Center Accuracy: 0.09998

Test Set:
Average Loss: 3.888859314727783
Accuracy: 0.4812
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.394242525100708, Weights: 0.026805376634001732
NC2 Equiangle: Features: 0.1516644225457702, Weights: 0.09842288855350378
NC3 Self-Duality: 0.6586855053901672
NC4 NCC Mismatch: 0.22409999999999997

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.006621266715228558
Inter Cos: 0.4067547917366028
Norm Quadratic Average: 29.42218589782715
Nearest Class Center Accuracy: 0.1136

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.012943447567522526
Inter Cos: 0.23317377269268036
Norm Quadratic Average: 42.409481048583984
Nearest Class Center Accuracy: 0.2476

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.017673280090093613
Inter Cos: 0.23169541358947754
Norm Quadratic Average: 54.68603515625
Nearest Class Center Accuracy: 0.3379

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01683361828327179
Inter Cos: 0.18731077015399933
Norm Quadratic Average: 90.55421447753906
Nearest Class Center Accuracy: 0.4192

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018685664981603622
Inter Cos: 0.18078410625457764
Norm Quadratic Average: 69.18533325195312
Nearest Class Center Accuracy: 0.5031

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.017634354531764984
Inter Cos: 0.13897967338562012
Norm Quadratic Average: 66.09361267089844
Nearest Class Center Accuracy: 0.5433

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.020238902419805527
Inter Cos: 0.18190084397792816
Norm Quadratic Average: 30.745426177978516
Nearest Class Center Accuracy: 0.5355

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03860524296760559
Inter Cos: 0.2554469704627991
Norm Quadratic Average: 15.752842903137207
Nearest Class Center Accuracy: 0.517

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 74.55078125
Linear Weight Rank: 4031
Intra Cos: 0.0860564336180687
Inter Cos: 0.36993348598480225
Norm Quadratic Average: 50.94344711303711
Nearest Class Center Accuracy: 0.4706

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 33.23082733154297
Linear Weight Rank: 3664
Intra Cos: 0.10657588392496109
Inter Cos: 0.37098634243011475
Norm Quadratic Average: 35.311012268066406
Nearest Class Center Accuracy: 0.4704

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 13.724163055419922
Linear Weight Rank: 98
Intra Cos: 0.11308666318655014
Inter Cos: 0.4396357536315918
Norm Quadratic Average: 30.087650299072266
Nearest Class Center Accuracy: 0.4678

Output Layer:
Intra Cos: 0.11140814423561096
Inter Cos: 0.6618990898132324
Norm Quadratic Average: 54.0573616027832
Nearest Class Center Accuracy: 0.4602

