Model save path: ./New_Models/bn_False_dataset_CIFAR100_epochs_200_lr_0.01_model_type_vgg11_rand_seed_314159_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: 0.022893192246556282
Inter Cos: 0.07011394202709198
Norm Quadratic Average: 29.326322555541992
Nearest Class Center Accuracy: 0.03258

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.035468947142362595
Inter Cos: 0.06523618847131729
Norm Quadratic Average: 29.87136459350586
Nearest Class Center Accuracy: 0.04398

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03194553032517433
Inter Cos: 0.03295421972870827
Norm Quadratic Average: 19.579578399658203
Nearest Class Center Accuracy: 0.05514

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03018655627965927
Inter Cos: 0.02764737978577614
Norm Quadratic Average: 9.045733451843262
Nearest Class Center Accuracy: 0.06582

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.05071253702044487
Inter Cos: 0.0396224781870842
Norm Quadratic Average: 1.69802987575531
Nearest Class Center Accuracy: 0.07574

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4092063307762146
Inter Cos: 0.3498573899269104
Norm Quadratic Average: 0.8094710111618042
Nearest Class Center Accuracy: 0.08786

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6165990829467773
Inter Cos: 0.6066680550575256
Norm Quadratic Average: 1.6567473411560059
Nearest Class Center Accuracy: 0.08954

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7129782438278198
Inter Cos: 0.6887105703353882
Norm Quadratic Average: 4.270174503326416
Nearest Class Center Accuracy: 0.09282

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 3.8762905597686768
Linear Weight Rank: 17
Intra Cos: 0.802738606929779
Inter Cos: 0.744419515132904
Norm Quadratic Average: 46.52789306640625
Nearest Class Center Accuracy: 0.09548

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 4.020724773406982
Linear Weight Rank: 2180
Intra Cos: 0.8578615188598633
Inter Cos: 0.7765785455703735
Norm Quadratic Average: 68.65965270996094
Nearest Class Center Accuracy: 0.09652

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 4.513658046722412
Linear Weight Rank: 97
Intra Cos: 0.8742465376853943
Inter Cos: 0.7382502555847168
Norm Quadratic Average: 76.6170883178711
Nearest Class Center Accuracy: 0.09802

Output Layer:
Intra Cos: 0.9217436909675598
Inter Cos: 0.8018332719802856
Norm Quadratic Average: 96.2645263671875
Nearest Class Center Accuracy: 0.0983

Test Set:
Average Loss: 5.480238200378418
Accuracy: 0.305
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.3308914005756378, Weights: 0.055922430008649826
NC2 Equiangle: Features: 0.35483654908459594, Weights: 0.1668874536379419
NC3 Self-Duality: 0.5758776068687439
NC4 NCC Mismatch: 0.43899999999999995

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.006621268577873707
Inter Cos: 0.4067547917366028
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: 0.013700698502361774
Inter Cos: 0.31008484959602356
Norm Quadratic Average: 30.052133560180664
Nearest Class Center Accuracy: 0.2182

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.019225794821977615
Inter Cos: 0.25757384300231934
Norm Quadratic Average: 19.71461296081543
Nearest Class Center Accuracy: 0.3141

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.019833039492368698
Inter Cos: 0.23900821805000305
Norm Quadratic Average: 9.0886869430542
Nearest Class Center Accuracy: 0.4331

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.027525365352630615
Inter Cos: 0.3331657946109772
Norm Quadratic Average: 1.7016675472259521
Nearest Class Center Accuracy: 0.4782

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.07497285306453705
Inter Cos: 0.7160192728042603
Norm Quadratic Average: 0.7927950024604797
Nearest Class Center Accuracy: 0.344

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09215640276670456
Inter Cos: 0.8334678411483765
Norm Quadratic Average: 1.5925406217575073
Nearest Class Center Accuracy: 0.2919

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09264657646417618
Inter Cos: 0.8343576788902283
Norm Quadratic Average: 4.061318397521973
Nearest Class Center Accuracy: 0.3018

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 3.8762905597686768
Linear Weight Rank: 17
Intra Cos: 0.115177221596241
Inter Cos: 0.8104474544525146
Norm Quadratic Average: 43.83073043823242
Nearest Class Center Accuracy: 0.3121

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 4.020724773406982
Linear Weight Rank: 2180
Intra Cos: 0.13880321383476257
Inter Cos: 0.7739038467407227
Norm Quadratic Average: 64.3915786743164
Nearest Class Center Accuracy: 0.305

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 4.513658046722412
Linear Weight Rank: 97
Intra Cos: 0.18306833505630493
Inter Cos: 0.711925745010376
Norm Quadratic Average: 72.01069641113281
Nearest Class Center Accuracy: 0.3005

Output Layer:
Intra Cos: 0.1888883113861084
Inter Cos: 0.7556177973747253
Norm Quadratic Average: 89.33421325683594
Nearest Class Center Accuracy: 0.2897

