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_0.0005.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: 0.019198764115571976
Inter Cos: 0.0742601826786995
Norm Quadratic Average: 23.549604415893555
Nearest Class Center Accuracy: 0.40356

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018937259912490845
Inter Cos: 0.05174732208251953
Norm Quadratic Average: 11.695596694946289
Nearest Class Center Accuracy: 0.5344

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01443214900791645
Inter Cos: 0.04029481112957001
Norm Quadratic Average: 10.09519100189209
Nearest Class Center Accuracy: 0.6119

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.020888157188892365
Inter Cos: 0.03488318249583244
Norm Quadratic Average: 6.438863277435303
Nearest Class Center Accuracy: 0.7313

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.034296050667762756
Inter Cos: 0.03320477902889252
Norm Quadratic Average: 6.481383323669434
Nearest Class Center Accuracy: 0.83462

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12496859580278397
Inter Cos: 0.0808660015463829
Norm Quadratic Average: 6.120338439941406
Nearest Class Center Accuracy: 0.95092

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5427849888801575
Inter Cos: 0.12783220410346985
Norm Quadratic Average: 5.294491291046143
Nearest Class Center Accuracy: 0.99906

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 20.37102508544922
Linear Weight Rank: 4031
Intra Cos: 0.8385521173477173
Inter Cos: 0.12255431711673737
Norm Quadratic Average: 38.98651885986328
Nearest Class Center Accuracy: 0.99858

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 8.925902366638184
Linear Weight Rank: 3665
Intra Cos: 0.9558045864105225
Inter Cos: -0.010161888785660267
Norm Quadratic Average: 27.182945251464844
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.809352159500122
Linear Weight Rank: 10
Intra Cos: 0.9461904764175415
Inter Cos: 0.02241664007306099
Norm Quadratic Average: 18.461040496826172
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9893766045570374
Inter Cos: 0.22307327389717102
Norm Quadratic Average: 15.67137336730957
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.833127131652832
Accuracy: 0.844
NC1 Within Class Collapse: 4.280437469482422
NC2 Equinorm: Features: 0.19222640991210938, Weights: 0.024741580709815025
NC2 Equiangle: Features: 0.1138541751437717, Weights: 0.060158591800265844
NC3 Self-Duality: 0.22662940621376038
NC4 NCC Mismatch: 0.04679999999999995

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: 0.018185898661613464
Inter Cos: 0.07580134272575378
Norm Quadratic Average: 23.531309127807617
Nearest Class Center Accuracy: 0.4207

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.017631614580750465
Inter Cos: 0.05283699184656143
Norm Quadratic Average: 11.696345329284668
Nearest Class Center Accuracy: 0.5447

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.013267426751554012
Inter Cos: 0.040954094380140305
Norm Quadratic Average: 10.10020637512207
Nearest Class Center Accuracy: 0.6181

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.017543639987707138
Inter Cos: 0.035622142255306244
Norm Quadratic Average: 6.442115783691406
Nearest Class Center Accuracy: 0.6939

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.025959473103284836
Inter Cos: 0.03559916466474533
Norm Quadratic Average: 6.467141151428223
Nearest Class Center Accuracy: 0.7418

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08559706062078476
Inter Cos: 0.08926752209663391
Norm Quadratic Average: 6.061341285705566
Nearest Class Center Accuracy: 0.7958

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3014870285987854
Inter Cos: 0.19630707800388336
Norm Quadratic Average: 5.054905891418457
Nearest Class Center Accuracy: 0.8285

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 20.37102508544922
Linear Weight Rank: 4031
Intra Cos: 0.5797085762023926
Inter Cos: 0.3377719521522522
Norm Quadratic Average: 36.099571228027344
Nearest Class Center Accuracy: 0.8123

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 8.925902366638184
Linear Weight Rank: 3665
Intra Cos: 0.548876166343689
Inter Cos: 0.24967455863952637
Norm Quadratic Average: 24.399398803710938
Nearest Class Center Accuracy: 0.8288

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.809352159500122
Linear Weight Rank: 10
Intra Cos: 0.5440611243247986
Inter Cos: 0.2611919939517975
Norm Quadratic Average: 16.826824188232422
Nearest Class Center Accuracy: 0.835

Output Layer:
Intra Cos: 0.5752172470092773
Inter Cos: 0.333599716424942
Norm Quadratic Average: 14.07327938079834
Nearest Class Center Accuracy: 0.8418

