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_0.0001.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: 0.10745704174041748
Inter Cos: 0.12130221724510193
Norm Quadratic Average: 34.664241790771484
Nearest Class Center Accuracy: 0.8346166666666667

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18955351412296295
Inter Cos: 0.15889427065849304
Norm Quadratic Average: 29.956396102905273
Nearest Class Center Accuracy: 0.89265

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21213680505752563
Inter Cos: 0.17085140943527222
Norm Quadratic Average: 32.216957092285156
Nearest Class Center Accuracy: 0.9154166666666667

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25060564279556274
Inter Cos: 0.16258220374584198
Norm Quadratic Average: 16.745607376098633
Nearest Class Center Accuracy: 0.9648666666666667

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3558102250099182
Inter Cos: 0.1840537041425705
Norm Quadratic Average: 12.898711204528809
Nearest Class Center Accuracy: 0.9808333333333333

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5004547238349915
Inter Cos: 0.2244422882795334
Norm Quadratic Average: 7.0921831130981445
Nearest Class Center Accuracy: 0.9947166666666667

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7688407301902771
Inter Cos: 0.25585511326789856
Norm Quadratic Average: 6.008331775665283
Nearest Class Center Accuracy: 0.99895

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 68.80490112304688
Linear Weight Rank: 4031
Intra Cos: 0.9065536260604858
Inter Cos: 0.19930976629257202
Norm Quadratic Average: 33.413211822509766
Nearest Class Center Accuracy: 0.9996833333333334

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 27.919422149658203
Linear Weight Rank: 3671
Intra Cos: 0.9318253993988037
Inter Cos: 0.18799975514411926
Norm Quadratic Average: 28.01698875427246
Nearest Class Center Accuracy: 0.9999

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.9787750244140625
Linear Weight Rank: 10
Intra Cos: 0.9390595555305481
Inter Cos: 0.18036992847919464
Norm Quadratic Average: 25.363685607910156
Nearest Class Center Accuracy: 0.9999666666666667

Output Layer:
Intra Cos: 0.9677562117576599
Inter Cos: 0.23068147897720337
Norm Quadratic Average: 24.73293685913086
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.021407299409899862
Accuracy: 0.9944
NC1 Within Class Collapse: 0.4516277313232422
NC2 Equinorm: Features: 0.08222653716802597, Weights: 0.023698333650827408
NC2 Equiangle: Features: 0.17083713743421766, Weights: 0.09832854800754123
NC3 Self-Duality: 0.2385055422782898
NC4 NCC Mismatch: 0.0027000000000000357

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: 0.11909328401088715
Inter Cos: 0.12929129600524902
Norm Quadratic Average: 34.562862396240234
Nearest Class Center Accuracy: 0.8465

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20255152881145477
Inter Cos: 0.17257197201251984
Norm Quadratic Average: 29.852964401245117
Nearest Class Center Accuracy: 0.9025

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22465360164642334
Inter Cos: 0.18432092666625977
Norm Quadratic Average: 32.13450241088867
Nearest Class Center Accuracy: 0.9259

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2601318061351776
Inter Cos: 0.17466743290424347
Norm Quadratic Average: 16.716981887817383
Nearest Class Center Accuracy: 0.9684

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.36799725890159607
Inter Cos: 0.20198938250541687
Norm Quadratic Average: 12.89987564086914
Nearest Class Center Accuracy: 0.9821

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5101296305656433
Inter Cos: 0.2435159981250763
Norm Quadratic Average: 7.118004322052002
Nearest Class Center Accuracy: 0.9898

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7732001543045044
Inter Cos: 0.27755552530288696
Norm Quadratic Average: 6.044902801513672
Nearest Class Center Accuracy: 0.9923

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 68.80490112304688
Linear Weight Rank: 4031
Intra Cos: 0.9055852293968201
Inter Cos: 0.21768520772457123
Norm Quadratic Average: 33.63948059082031
Nearest Class Center Accuracy: 0.9933

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 27.919422149658203
Linear Weight Rank: 3671
Intra Cos: 0.9289054274559021
Inter Cos: 0.18880704045295715
Norm Quadratic Average: 28.193979263305664
Nearest Class Center Accuracy: 0.9934

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.9787750244140625
Linear Weight Rank: 10
Intra Cos: 0.9347214102745056
Inter Cos: 0.18110144138336182
Norm Quadratic Average: 25.517473220825195
Nearest Class Center Accuracy: 0.9935

Output Layer:
Intra Cos: 0.9584846496582031
Inter Cos: 0.23568803071975708
Norm Quadratic Average: 24.884449005126953
Nearest Class Center Accuracy: 0.9942

