Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_weight_decay_0.0003.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946067094802856
Inter Cos: 0.11311887204647064
Norm Quadratic Average: 23.532939910888672
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11179099231958389
Inter Cos: 0.13461259007453918
Norm Quadratic Average: 47.89717102050781
Nearest Class Center Accuracy: 0.822625

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15383949875831604
Inter Cos: 0.17588606476783752
Norm Quadratic Average: 48.69518280029297
Nearest Class Center Accuracy: 0.80425

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16865696012973785
Inter Cos: 0.19358667731285095
Norm Quadratic Average: 64.95447540283203
Nearest Class Center Accuracy: 0.81675

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19097083806991577
Inter Cos: 0.19071075320243835
Norm Quadratic Average: 43.986915588378906
Nearest Class Center Accuracy: 0.85375

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2184516042470932
Inter Cos: 0.1968432068824768
Norm Quadratic Average: 42.935237884521484
Nearest Class Center Accuracy: 0.891375

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2739078104496002
Inter Cos: 0.1793278008699417
Norm Quadratic Average: 25.68540382385254
Nearest Class Center Accuracy: 0.93025

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3971143662929535
Inter Cos: 0.20817884802818298
Norm Quadratic Average: 19.667665481567383
Nearest Class Center Accuracy: 0.973

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.94112396240234
Linear Weight Rank: 4031
Intra Cos: 0.6081245541572571
Inter Cos: 0.2355838268995285
Norm Quadratic Average: 84.61707305908203
Nearest Class Center Accuracy: 0.997125

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.40007019042969
Linear Weight Rank: 3671
Intra Cos: 0.7160472869873047
Inter Cos: 0.226853609085083
Norm Quadratic Average: 53.375030517578125
Nearest Class Center Accuracy: 0.999375

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.4787516593933105
Linear Weight Rank: 10
Intra Cos: 0.7677968144416809
Inter Cos: 0.26146653294563293
Norm Quadratic Average: 40.739967346191406
Nearest Class Center Accuracy: 0.999625

Output Layer:
Intra Cos: 0.8210409879684448
Inter Cos: 0.38345521688461304
Norm Quadratic Average: 28.652450561523438
Nearest Class Center Accuracy: 0.999875

Test Set:
Average Loss: 0.08489290870726109
Accuracy: 0.9805
NC1 Within Class Collapse: 1.7996242046356201
NC2 Equinorm: Features: 0.10443704575300217, Weights: 0.013146224431693554
NC2 Equiangle: Features: 0.2457792494032118, Weights: 0.09048997031317817
NC3 Self-Duality: 0.5548793077468872
NC4 NCC Mismatch: 0.018000000000000016

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
Inter Cos: 0.11957792937755585
Norm Quadratic Average: 22.82430076599121
Nearest Class Center Accuracy: 0.809

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13268481194972992
Inter Cos: 0.14753524959087372
Norm Quadratic Average: 46.47250747680664
Nearest Class Center Accuracy: 0.8195

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16606572270393372
Inter Cos: 0.20007142424583435
Norm Quadratic Average: 47.2341194152832
Nearest Class Center Accuracy: 0.804

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17637306451797485
Inter Cos: 0.22841142117977142
Norm Quadratic Average: 62.959022521972656
Nearest Class Center Accuracy: 0.825

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16472746431827545
Inter Cos: 0.21713034808635712
Norm Quadratic Average: 42.887359619140625
Nearest Class Center Accuracy: 0.851

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18752387166023254
Inter Cos: 0.23046346008777618
Norm Quadratic Average: 41.946903228759766
Nearest Class Center Accuracy: 0.878

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23559783399105072
Inter Cos: 0.20683512091636658
Norm Quadratic Average: 25.04401397705078
Nearest Class Center Accuracy: 0.9265

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.33888381719589233
Inter Cos: 0.2330162078142166
Norm Quadratic Average: 19.030553817749023
Nearest Class Center Accuracy: 0.9505

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.94112396240234
Linear Weight Rank: 4031
Intra Cos: 0.5269913077354431
Inter Cos: 0.23469826579093933
Norm Quadratic Average: 81.48452758789062
Nearest Class Center Accuracy: 0.969

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.40007019042969
Linear Weight Rank: 3671
Intra Cos: 0.626576840877533
Inter Cos: 0.2423790693283081
Norm Quadratic Average: 51.2663688659668
Nearest Class Center Accuracy: 0.9745

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.4787516593933105
Linear Weight Rank: 10
Intra Cos: 0.6745880842208862
Inter Cos: 0.2865874469280243
Norm Quadratic Average: 39.205074310302734
Nearest Class Center Accuracy: 0.975

Output Layer:
Intra Cos: 0.7184833288192749
Inter Cos: 0.39705339074134827
Norm Quadratic Average: 27.56821060180664
Nearest Class Center Accuracy: 0.9725

