Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_265358_test_samples_None_train_samples_None_weight_decay_0.03.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09116753190755844
Inter Cos: 0.10967151820659637
Norm Quadratic Average: 23.567670822143555
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12506571412086487
Inter Cos: 0.15763084590435028
Norm Quadratic Average: 35.39130783081055
Nearest Class Center Accuracy: 0.7983833333333333

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1540498286485672
Inter Cos: 0.19507206976413727
Norm Quadratic Average: 35.75416946411133
Nearest Class Center Accuracy: 0.7769166666666667

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18845944106578827
Inter Cos: 0.2302374392747879
Norm Quadratic Average: 41.84980773925781
Nearest Class Center Accuracy: 0.7904666666666667

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16459067165851593
Inter Cos: 0.2634308338165283
Norm Quadratic Average: 30.84938621520996
Nearest Class Center Accuracy: 0.8089666666666666

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20685215294361115
Inter Cos: 0.3499017357826233
Norm Quadratic Average: 23.649276733398438
Nearest Class Center Accuracy: 0.8656333333333334

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.36739620566368103
Inter Cos: 0.4180287718772888
Norm Quadratic Average: 13.461671829223633
Nearest Class Center Accuracy: 0.9035

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.46643006801605225
Inter Cos: 0.38527122139930725
Norm Quadratic Average: 12.461600303649902
Nearest Class Center Accuracy: 0.9397

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.5618852376937866
Linear Weight Rank: 6
Intra Cos: 0.6216880083084106
Inter Cos: 0.3614646792411804
Norm Quadratic Average: 50.9390983581543
Nearest Class Center Accuracy: 0.9593333333333334

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.5632895231246948
Linear Weight Rank: 2685
Intra Cos: 0.6916334629058838
Inter Cos: 0.37477144598960876
Norm Quadratic Average: 32.550724029541016
Nearest Class Center Accuracy: 0.9632

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.559645414352417
Linear Weight Rank: 9
Intra Cos: 0.7309883236885071
Inter Cos: 0.37243935465812683
Norm Quadratic Average: 19.966476440429688
Nearest Class Center Accuracy: 0.9646

Output Layer:
Intra Cos: 0.7605675458908081
Inter Cos: 0.4122559726238251
Norm Quadratic Average: 13.58010196685791
Nearest Class Center Accuracy: 0.96575

Test Set:
Average Loss: 0.08920456354618073
Accuracy: 0.9733
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.1564093977212906, Weights: 0.03757639601826668
NC2 Equiangle: Features: 0.3171315511067708, Weights: 0.23564253913031685
NC3 Self-Duality: 0.11445397883653641
NC4 NCC Mismatch: 0.017199999999999993

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219583660364151
Inter Cos: 0.12048852443695068
Norm Quadratic Average: 23.595197677612305
Nearest Class Center Accuracy: 0.8229

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13860662281513214
Inter Cos: 0.1726766973733902
Norm Quadratic Average: 35.47813415527344
Nearest Class Center Accuracy: 0.8164

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17070883512496948
Inter Cos: 0.2148216962814331
Norm Quadratic Average: 35.76741027832031
Nearest Class Center Accuracy: 0.7955

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20238681137561798
Inter Cos: 0.25175991654396057
Norm Quadratic Average: 41.830223083496094
Nearest Class Center Accuracy: 0.8102

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17625810205936432
Inter Cos: 0.26058563590049744
Norm Quadratic Average: 30.822996139526367
Nearest Class Center Accuracy: 0.8309

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21823127567768097
Inter Cos: 0.34345370531082153
Norm Quadratic Average: 23.675222396850586
Nearest Class Center Accuracy: 0.8808

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3829711675643921
Inter Cos: 0.41331350803375244
Norm Quadratic Average: 13.5252685546875
Nearest Class Center Accuracy: 0.9097

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.47801047563552856
Inter Cos: 0.381526917219162
Norm Quadratic Average: 12.570894241333008
Nearest Class Center Accuracy: 0.9405

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.5618852376937866
Linear Weight Rank: 6
Intra Cos: 0.6325558423995972
Inter Cos: 0.3866598308086395
Norm Quadratic Average: 51.62411117553711
Nearest Class Center Accuracy: 0.9596

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.5632895231246948
Linear Weight Rank: 2685
Intra Cos: 0.6940659284591675
Inter Cos: 0.4013236463069916
Norm Quadratic Average: 33.060340881347656
Nearest Class Center Accuracy: 0.9646

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.559645414352417
Linear Weight Rank: 9
Intra Cos: 0.7266339063644409
Inter Cos: 0.3809317648410797
Norm Quadratic Average: 20.292407989501953
Nearest Class Center Accuracy: 0.9668

Output Layer:
Intra Cos: 0.7516003847122192
Inter Cos: 0.4188085198402405
Norm Quadratic Average: 13.803982734680176
Nearest Class Center Accuracy: 0.9684

