Model save path: ./New_Models/bn_False_dataset_CIFAR10_epochs_200_lr_0.01_model_type_vgg11_rand_seed_265358_test_samples_None_train_samples_None_weight_decay_0.001.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01989092119038105
Inter Cos: 0.10477277636528015
Norm Quadratic Average: 27.59717559814453
Nearest Class Center Accuracy: 0.26968

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.025121118873357773
Inter Cos: 0.10175923258066177
Norm Quadratic Average: 25.78424644470215
Nearest Class Center Accuracy: 0.38322

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.029731903225183487
Inter Cos: 0.09627924859523773
Norm Quadratic Average: 23.958539962768555
Nearest Class Center Accuracy: 0.47032

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03020545095205307
Inter Cos: 0.0796273872256279
Norm Quadratic Average: 28.898086547851562
Nearest Class Center Accuracy: 0.54558

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.030688870698213577
Inter Cos: 0.05912907421588898
Norm Quadratic Average: 14.215380668640137
Nearest Class Center Accuracy: 0.63412

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.04999123141169548
Inter Cos: 0.063162662088871
Norm Quadratic Average: 7.903275966644287
Nearest Class Center Accuracy: 0.71156

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15445218980312347
Inter Cos: 0.1772172898054123
Norm Quadratic Average: 2.804636001586914
Nearest Class Center Accuracy: 0.85026

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5615638494491577
Inter Cos: 0.3386828303337097
Norm Quadratic Average: 1.5775400400161743
Nearest Class Center Accuracy: 0.99492

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 5.401697158813477
Linear Weight Rank: 4028
Intra Cos: 0.7625378370285034
Inter Cos: 0.29545772075653076
Norm Quadratic Average: 10.847384452819824
Nearest Class Center Accuracy: 0.99744

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 4.056579113006592
Linear Weight Rank: 3644
Intra Cos: 0.8342494964599609
Inter Cos: 0.2309158742427826
Norm Quadratic Average: 11.73924446105957
Nearest Class Center Accuracy: 0.99954

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 3.6032793521881104
Linear Weight Rank: 9
Intra Cos: 0.8500415086746216
Inter Cos: 0.20266281068325043
Norm Quadratic Average: 12.976319313049316
Nearest Class Center Accuracy: 0.99998

Output Layer:
Intra Cos: 0.8730823397636414
Inter Cos: 0.2341982126235962
Norm Quadratic Average: 15.976937294006348
Nearest Class Center Accuracy: 0.99998

Test Set:
Average Loss: 0.8843221786975861
Accuracy: 0.8116
NC1 Within Class Collapse: 6.248187065124512
NC2 Equinorm: Features: 0.21332666277885437, Weights: 0.04041046276688576
NC2 Equiangle: Features: 0.21921713087293837, Weights: 0.06902866363525391
NC3 Self-Duality: 0.15978887677192688
NC4 NCC Mismatch: 0.04730000000000001

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: 27.550134658813477
Nearest Class Center Accuracy: 0.284

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.023870768025517464
Inter Cos: 0.10226242989301682
Norm Quadratic Average: 25.76604652404785
Nearest Class Center Accuracy: 0.3983

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.027979159727692604
Inter Cos: 0.09800782054662704
Norm Quadratic Average: 23.966012954711914
Nearest Class Center Accuracy: 0.4773

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.028015591204166412
Inter Cos: 0.08088929206132889
Norm Quadratic Average: 28.926244735717773
Nearest Class Center Accuracy: 0.5497

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.026995927095413208
Inter Cos: 0.06046658381819725
Norm Quadratic Average: 14.232775688171387
Nearest Class Center Accuracy: 0.6277

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.04351074621081352
Inter Cos: 0.06480760872364044
Norm Quadratic Average: 7.902120113372803
Nearest Class Center Accuracy: 0.6792

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12586265802383423
Inter Cos: 0.17881937325000763
Norm Quadratic Average: 2.797177791595459
Nearest Class Center Accuracy: 0.7384

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.37015658617019653
Inter Cos: 0.3499396741390228
Norm Quadratic Average: 1.5483016967773438
Nearest Class Center Accuracy: 0.7974

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 5.401697158813477
Linear Weight Rank: 4028
Intra Cos: 0.47808700799942017
Inter Cos: 0.364895761013031
Norm Quadratic Average: 10.524142265319824
Nearest Class Center Accuracy: 0.7977

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 4.056579113006592
Linear Weight Rank: 3644
Intra Cos: 0.4944618344306946
Inter Cos: 0.34350618720054626
Norm Quadratic Average: 11.301555633544922
Nearest Class Center Accuracy: 0.8022

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 3.6032793521881104
Linear Weight Rank: 9
Intra Cos: 0.4792027771472931
Inter Cos: 0.31407421827316284
Norm Quadratic Average: 12.44836711883545
Nearest Class Center Accuracy: 0.8049

Output Layer:
Intra Cos: 0.48534095287323
Inter Cos: 0.320828914642334
Norm Quadratic Average: 15.281678199768066
Nearest Class Center Accuracy: 0.8059

