Model save path: ./New_Models/bn_True_dataset_CIFAR100_epochs_200_lr_0.01_model_type_vgg11_rand_seed_265358_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: 0.022893192246556282
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: 0.02688569761812687
Inter Cos: 0.027994690462946892
Norm Quadratic Average: 29.396602630615234
Nearest Class Center Accuracy: 0.0485

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.022028911858797073
Inter Cos: 0.02367975562810898
Norm Quadratic Average: 14.555425643920898
Nearest Class Center Accuracy: 0.06048

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.017719175666570663
Inter Cos: 0.019945785403251648
Norm Quadratic Average: 12.299034118652344
Nearest Class Center Accuracy: 0.0688

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02341603860259056
Inter Cos: 0.02110641822218895
Norm Quadratic Average: 7.824254989624023
Nearest Class Center Accuracy: 0.07926

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02876472659409046
Inter Cos: 0.024252720177173615
Norm Quadratic Average: 6.544069290161133
Nearest Class Center Accuracy: 0.0852

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06754515320062637
Inter Cos: 0.045301713049411774
Norm Quadratic Average: 4.428252220153809
Nearest Class Center Accuracy: 0.09632

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.28183713555336
Inter Cos: 0.1268659383058548
Norm Quadratic Average: 3.468604326248169
Nearest Class Center Accuracy: 0.09982

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 21.720802307128906
Linear Weight Rank: 4029
Intra Cos: 0.6768308877944946
Inter Cos: 0.22635391354560852
Norm Quadratic Average: 36.69355010986328
Nearest Class Center Accuracy: 0.1

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 12.257394790649414
Linear Weight Rank: 3641
Intra Cos: 0.8349190950393677
Inter Cos: 0.2659236788749695
Norm Quadratic Average: 30.690093994140625
Nearest Class Center Accuracy: 0.1

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 8.502346992492676
Linear Weight Rank: 98
Intra Cos: 0.8680589199066162
Inter Cos: 0.2811003625392914
Norm Quadratic Average: 31.13593864440918
Nearest Class Center Accuracy: 0.1

Output Layer:
Intra Cos: 0.8989457488059998
Inter Cos: 0.3701324760913849
Norm Quadratic Average: 43.874046325683594
Nearest Class Center Accuracy: 0.1

Test Set:
Average Loss: 2.4661229038238526
Accuracy: 0.5485
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.2528201639652252, Weights: 0.034556396305561066
NC2 Equiangle: Features: 0.1798842921401515, Weights: 0.0973782502761995
NC3 Self-Duality: 0.41817212104797363
NC4 NCC Mismatch: 0.15849999999999997

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: 0.010587443597614765
Inter Cos: 0.25776785612106323
Norm Quadratic Average: 29.605499267578125
Nearest Class Center Accuracy: 0.2661

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.015270897187292576
Inter Cos: 0.19814826548099518
Norm Quadratic Average: 14.66202163696289
Nearest Class Center Accuracy: 0.3954

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.013424172066152096
Inter Cos: 0.13924762606620789
Norm Quadratic Average: 12.353679656982422
Nearest Class Center Accuracy: 0.5082

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.013924521394073963
Inter Cos: 0.14003807306289673
Norm Quadratic Average: 7.844709396362305
Nearest Class Center Accuracy: 0.5995

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01261692401021719
Inter Cos: 0.12178468704223633
Norm Quadratic Average: 6.53106164932251
Nearest Class Center Accuracy: 0.6381

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.020593468099832535
Inter Cos: 0.17293840646743774
Norm Quadratic Average: 4.363861083984375
Nearest Class Center Accuracy: 0.6286

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06223464384675026
Inter Cos: 0.3420645594596863
Norm Quadratic Average: 3.2122840881347656
Nearest Class Center Accuracy: 0.5901

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 21.720802307128906
Linear Weight Rank: 4029
Intra Cos: 0.17161959409713745
Inter Cos: 0.4701550602912903
Norm Quadratic Average: 30.759864807128906
Nearest Class Center Accuracy: 0.5456

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 12.257394790649414
Linear Weight Rank: 3641
Intra Cos: 0.1971965730190277
Inter Cos: 0.48534074425697327
Norm Quadratic Average: 24.76474380493164
Nearest Class Center Accuracy: 0.5505

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 8.502346992492676
Linear Weight Rank: 98
Intra Cos: 0.19534240663051605
Inter Cos: 0.5286201238632202
Norm Quadratic Average: 25.231243133544922
Nearest Class Center Accuracy: 0.5476

Output Layer:
Intra Cos: 0.20697152614593506
Inter Cos: 0.616536021232605
Norm Quadratic Average: 35.722984313964844
Nearest Class Center Accuracy: 0.5436

