Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_weight_decay_0.0005.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: 23.53293800354004
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11132195591926575
Inter Cos: 0.128970205783844
Norm Quadratic Average: 45.65281295776367
Nearest Class Center Accuracy: 0.8235

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15735860168933868
Inter Cos: 0.1632058471441269
Norm Quadratic Average: 42.89916229248047
Nearest Class Center Accuracy: 0.8165

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17814330756664276
Inter Cos: 0.17923671007156372
Norm Quadratic Average: 55.506690979003906
Nearest Class Center Accuracy: 0.832375

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.196120023727417
Inter Cos: 0.180585116147995
Norm Quadratic Average: 37.1486930847168
Nearest Class Center Accuracy: 0.8665

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2234387844800949
Inter Cos: 0.19676437973976135
Norm Quadratic Average: 35.924293518066406
Nearest Class Center Accuracy: 0.9095

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.29383358359336853
Inter Cos: 0.17507342994213104
Norm Quadratic Average: 21.798566818237305
Nearest Class Center Accuracy: 0.949625

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4171063005924225
Inter Cos: 0.2228173464536667
Norm Quadratic Average: 17.224807739257812
Nearest Class Center Accuracy: 0.983

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.98406219482422
Linear Weight Rank: 4031
Intra Cos: 0.6390142440795898
Inter Cos: 0.26461702585220337
Norm Quadratic Average: 76.71334075927734
Nearest Class Center Accuracy: 0.998375

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.01892852783203
Linear Weight Rank: 3671
Intra Cos: 0.7312113642692566
Inter Cos: 0.26397404074668884
Norm Quadratic Average: 49.82025909423828
Nearest Class Center Accuracy: 0.999625

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.481961727142334
Linear Weight Rank: 10
Intra Cos: 0.7704906463623047
Inter Cos: 0.259062796831131
Norm Quadratic Average: 38.688995361328125
Nearest Class Center Accuracy: 0.99975

Output Layer:
Intra Cos: 0.8017697930335999
Inter Cos: 0.3240048587322235
Norm Quadratic Average: 28.07904815673828
Nearest Class Center Accuracy: 0.999875

Test Set:
Average Loss: 0.08793048607930541
Accuracy: 0.9795
NC1 Within Class Collapse: 1.6889939308166504
NC2 Equinorm: Features: 0.11435674875974655, Weights: 0.012584848329424858
NC2 Equiangle: Features: 0.24885082244873047, Weights: 0.09878038830227322
NC3 Self-Duality: 0.5477150678634644
NC4 NCC Mismatch: 0.009499999999999953

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133805871009827
Inter Cos: 0.11957792192697525
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: 0.13233686983585358
Inter Cos: 0.14571934938430786
Norm Quadratic Average: 44.79377365112305
Nearest Class Center Accuracy: 0.816

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17126142978668213
Inter Cos: 0.20016270875930786
Norm Quadratic Average: 42.164329528808594
Nearest Class Center Accuracy: 0.8175

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17771203815937042
Inter Cos: 0.21693556010723114
Norm Quadratic Average: 54.546058654785156
Nearest Class Center Accuracy: 0.829

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1783241331577301
Inter Cos: 0.21074466407299042
Norm Quadratic Average: 36.49277877807617
Nearest Class Center Accuracy: 0.856

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20328889787197113
Inter Cos: 0.2266390025615692
Norm Quadratic Average: 35.35963439941406
Nearest Class Center Accuracy: 0.897

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2654682993888855
Inter Cos: 0.1868053674697876
Norm Quadratic Average: 21.39795684814453
Nearest Class Center Accuracy: 0.937

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.36946094036102295
Inter Cos: 0.21429449319839478
Norm Quadratic Average: 16.84526252746582
Nearest Class Center Accuracy: 0.96

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.98406219482422
Linear Weight Rank: 4031
Intra Cos: 0.5730721950531006
Inter Cos: 0.23783144354820251
Norm Quadratic Average: 74.52506256103516
Nearest Class Center Accuracy: 0.974

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.01892852783203
Linear Weight Rank: 3671
Intra Cos: 0.6579394340515137
Inter Cos: 0.2374648004770279
Norm Quadratic Average: 48.28425216674805
Nearest Class Center Accuracy: 0.976

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.481961727142334
Linear Weight Rank: 10
Intra Cos: 0.6914560198783875
Inter Cos: 0.2641580402851105
Norm Quadratic Average: 37.52754211425781
Nearest Class Center Accuracy: 0.9785

Output Layer:
Intra Cos: 0.7118707299232483
Inter Cos: 0.3603714406490326
Norm Quadratic Average: 27.23108673095703
Nearest Class Center Accuracy: 0.977

