Model save path: ./New_Models/bn_True_dataset_CIFAR10_epochs_200_lr_0.01_model_type_vgg11_rand_seed_314159_test_samples_None_train_samples_None_weight_decay_0.0001.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: 0.10477276146411896
Norm Quadratic Average: 27.59718132019043
Nearest Class Center Accuracy: 0.26968

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018393121659755707
Inter Cos: 0.07285024225711823
Norm Quadratic Average: 69.29163360595703
Nearest Class Center Accuracy: 0.4019

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.021259555593132973
Inter Cos: 0.05657066032290459
Norm Quadratic Average: 40.23164749145508
Nearest Class Center Accuracy: 0.5286

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.017077896744012833
Inter Cos: 0.0450739786028862
Norm Quadratic Average: 42.531681060791016
Nearest Class Center Accuracy: 0.60842

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.024569865316152573
Inter Cos: 0.04095900431275368
Norm Quadratic Average: 29.43829345703125
Nearest Class Center Accuracy: 0.70626

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.040258634835481644
Inter Cos: 0.052135169506073
Norm Quadratic Average: 34.0490837097168
Nearest Class Center Accuracy: 0.7979

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12082915753126144
Inter Cos: 0.12486978620290756
Norm Quadratic Average: 24.316810607910156
Nearest Class Center Accuracy: 0.92152

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.42220935225486755
Inter Cos: 0.1841663420200348
Norm Quadratic Average: 19.294095993041992
Nearest Class Center Accuracy: 0.98302

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 73.61524963378906
Linear Weight Rank: 4031
Intra Cos: 0.7058766484260559
Inter Cos: 0.31573671102523804
Norm Quadratic Average: 102.65673065185547
Nearest Class Center Accuracy: 0.9711

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 30.584468841552734
Linear Weight Rank: 3668
Intra Cos: 0.9462757706642151
Inter Cos: 0.029921771958470345
Norm Quadratic Average: 75.60563659667969
Nearest Class Center Accuracy: 0.99772

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 4.075098037719727
Linear Weight Rank: 10
Intra Cos: 0.9394538998603821
Inter Cos: 0.00378167862072587
Norm Quadratic Average: 30.525863647460938
Nearest Class Center Accuracy: 0.99994

Output Layer:
Intra Cos: 0.9873531460762024
Inter Cos: 0.4124588072299957
Norm Quadratic Average: 21.954490661621094
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 1.0534315181732177
Accuracy: 0.8404
NC1 Within Class Collapse: 5.029068946838379
NC2 Equinorm: Features: 0.270031213760376, Weights: 0.023471618071198463
NC2 Equiangle: Features: 0.08975457085503472, Weights: 0.11985621982150607
NC3 Self-Duality: 0.9755561947822571
NC4 NCC Mismatch: 0.09630000000000005

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018526073545217514
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: 0.017306074500083923
Inter Cos: 0.074716717004776
Norm Quadratic Average: 69.23960876464844
Nearest Class Center Accuracy: 0.4193

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.020013226196169853
Inter Cos: 0.05807086080312729
Norm Quadratic Average: 40.24589920043945
Nearest Class Center Accuracy: 0.5382

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.015821725130081177
Inter Cos: 0.046087026596069336
Norm Quadratic Average: 42.56767654418945
Nearest Class Center Accuracy: 0.6155

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.021259089931845665
Inter Cos: 0.041886940598487854
Norm Quadratic Average: 29.451372146606445
Nearest Class Center Accuracy: 0.6805

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03263288363814354
Inter Cos: 0.054400164633989334
Norm Quadratic Average: 34.00801086425781
Nearest Class Center Accuracy: 0.7297

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08730676770210266
Inter Cos: 0.12919573485851288
Norm Quadratic Average: 24.176475524902344
Nearest Class Center Accuracy: 0.7755

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.273396760225296
Inter Cos: 0.20840469002723694
Norm Quadratic Average: 18.82711410522461
Nearest Class Center Accuracy: 0.8067

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 73.61524963378906
Linear Weight Rank: 4031
Intra Cos: 0.5020212531089783
Inter Cos: 0.3858290910720825
Norm Quadratic Average: 98.83966827392578
Nearest Class Center Accuracy: 0.7854

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 30.584468841552734
Linear Weight Rank: 3668
Intra Cos: 0.5793115496635437
Inter Cos: 0.26939794421195984
Norm Quadratic Average: 68.37529754638672
Nearest Class Center Accuracy: 0.7914

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 4.075098037719727
Linear Weight Rank: 10
Intra Cos: 0.537995457649231
Inter Cos: 0.2475799322128296
Norm Quadratic Average: 27.761966705322266
Nearest Class Center Accuracy: 0.8046

Output Layer:
Intra Cos: 0.6057246327400208
Inter Cos: 0.421640545129776
Norm Quadratic Average: 19.712440490722656
Nearest Class Center Accuracy: 0.8328

