Model save path: ./New_Models/bn_False_dataset_CIFAR100_epochs_200_lr_0.01_model_type_vgg11_rand_seed_979323_test_samples_None_train_samples_None_weight_decay_0.01.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: 0.03613262623548508
Inter Cos: 0.07316485047340393
Norm Quadratic Average: 32.001548767089844
Nearest Class Center Accuracy: 0.0431

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03670794889330864
Inter Cos: 0.03533737361431122
Norm Quadratic Average: 25.290477752685547
Nearest Class Center Accuracy: 0.0562

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03291495889425278
Inter Cos: 0.03106672130525112
Norm Quadratic Average: 14.560388565063477
Nearest Class Center Accuracy: 0.0659

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.04883841052651405
Inter Cos: 0.04395519942045212
Norm Quadratic Average: 2.6314520835876465
Nearest Class Center Accuracy: 0.07562

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27500802278518677
Inter Cos: 0.2233189046382904
Norm Quadratic Average: 0.9095054268836975
Nearest Class Center Accuracy: 0.0944

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7444400787353516
Inter Cos: 0.569383442401886
Norm Quadratic Average: 1.2174873352050781
Nearest Class Center Accuracy: 0.09802

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8551073670387268
Inter Cos: 0.6535651087760925
Norm Quadratic Average: 2.9319024085998535
Nearest Class Center Accuracy: 0.09866

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 4.009329319000244
Linear Weight Rank: 16
Intra Cos: 0.8845080733299255
Inter Cos: 0.6770166158676147
Norm Quadratic Average: 33.87258529663086
Nearest Class Center Accuracy: 0.09932

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 4.109086036682129
Linear Weight Rank: 2756
Intra Cos: 0.8864710927009583
Inter Cos: 0.6860703825950623
Norm Quadratic Average: 53.656227111816406
Nearest Class Center Accuracy: 0.09972

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 4.480928897857666
Linear Weight Rank: 97
Intra Cos: 0.8610982298851013
Inter Cos: 0.6263404488563538
Norm Quadratic Average: 63.83536148071289
Nearest Class Center Accuracy: 0.09978

Output Layer:
Intra Cos: 0.9144103527069092
Inter Cos: 0.7147494554519653
Norm Quadratic Average: 79.5748519897461
Nearest Class Center Accuracy: 0.09996

Test Set:
Average Loss: 3.9329208827972413
Accuracy: 0.3905
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.28166648745536804, Weights: 0.04789410158991814
NC2 Equiangle: Features: 0.3387171519886364, Weights: 0.1703381224352904
NC3 Self-Duality: 0.4897196292877197
NC4 NCC Mismatch: 0.3055

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: 0.013144728727638721
Inter Cos: 0.32298412919044495
Norm Quadratic Average: 32.18485641479492
Nearest Class Center Accuracy: 0.2078

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.022660117596387863
Inter Cos: 0.29224032163619995
Norm Quadratic Average: 25.456363677978516
Nearest Class Center Accuracy: 0.3044

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.023680541664361954
Inter Cos: 0.22225980460643768
Norm Quadratic Average: 14.645429611206055
Nearest Class Center Accuracy: 0.4212

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.025513924658298492
Inter Cos: 0.28276199102401733
Norm Quadratic Average: 2.6434922218322754
Nearest Class Center Accuracy: 0.5061

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06533244252204895
Inter Cos: 0.5911107063293457
Norm Quadratic Average: 0.9003660082817078
Nearest Class Center Accuracy: 0.4656

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12228024750947952
Inter Cos: 0.7646230459213257
Norm Quadratic Average: 1.1674878597259521
Nearest Class Center Accuracy: 0.3743

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15402895212173462
Inter Cos: 0.8021515607833862
Norm Quadratic Average: 2.7940378189086914
Nearest Class Center Accuracy: 0.3756

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 4.009329319000244
Linear Weight Rank: 16
Intra Cos: 0.1671275496482849
Inter Cos: 0.815718412399292
Norm Quadratic Average: 32.19750213623047
Nearest Class Center Accuracy: 0.3744

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 4.109086036682129
Linear Weight Rank: 2756
Intra Cos: 0.18375255167484283
Inter Cos: 0.8075041174888611
Norm Quadratic Average: 50.96474838256836
Nearest Class Center Accuracy: 0.3762

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 4.480928897857666
Linear Weight Rank: 97
Intra Cos: 0.22620442509651184
Inter Cos: 0.7698914408683777
Norm Quadratic Average: 61.04246520996094
Nearest Class Center Accuracy: 0.3766

Output Layer:
Intra Cos: 0.1946941614151001
Inter Cos: 0.81168532371521
Norm Quadratic Average: 75.70642852783203
Nearest Class Center Accuracy: 0.3784

