Model save path: ./New_Models/bn_True_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: 0.08946065604686737
Inter Cos: 0.11311887204647064
Norm Quadratic Average: 23.532936096191406
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10098925232887268
Inter Cos: 0.11838589608669281
Norm Quadratic Average: 85.00947570800781
Nearest Class Center Accuracy: 0.829875

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13839106261730194
Inter Cos: 0.13639800250530243
Norm Quadratic Average: 51.956546783447266
Nearest Class Center Accuracy: 0.84975

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13810914754867554
Inter Cos: 0.12732484936714172
Norm Quadratic Average: 54.396751403808594
Nearest Class Center Accuracy: 0.86825

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15987221896648407
Inter Cos: 0.10900188237428665
Norm Quadratic Average: 33.830326080322266
Nearest Class Center Accuracy: 0.912375

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1681608110666275
Inter Cos: 0.09368692338466644
Norm Quadratic Average: 35.440181732177734
Nearest Class Center Accuracy: 0.936625

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19414032995700836
Inter Cos: 0.07984518259763718
Norm Quadratic Average: 23.940685272216797
Nearest Class Center Accuracy: 0.975875

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27973759174346924
Inter Cos: 0.08321589231491089
Norm Quadratic Average: 18.843984603881836
Nearest Class Center Accuracy: 0.997375

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.97700500488281
Linear Weight Rank: 4031
Intra Cos: 0.47929394245147705
Inter Cos: 0.10766175389289856
Norm Quadratic Average: 117.09303283691406
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.0075569152832
Linear Weight Rank: 3670
Intra Cos: 0.6191715002059937
Inter Cos: 0.13033658266067505
Norm Quadratic Average: 63.28895950317383
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2525815963745117
Linear Weight Rank: 10
Intra Cos: 0.7412979006767273
Inter Cos: 0.15322542190551758
Norm Quadratic Average: 40.3529167175293
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9022446870803833
Inter Cos: 0.2345949113368988
Norm Quadratic Average: 21.806259155273438
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.10387812942266464
Accuracy: 0.9745
NC1 Within Class Collapse: 1.7660233974456787
NC2 Equinorm: Features: 0.062345996499061584, Weights: 0.01211485918611288
NC2 Equiangle: Features: 0.20379795498318143, Weights: 0.09129740397135416
NC3 Self-Duality: 0.6339644193649292
NC4 NCC Mismatch: 0.006000000000000005

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
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: 0.12223074585199356
Inter Cos: 0.1259671300649643
Norm Quadratic Average: 83.59599304199219
Nearest Class Center Accuracy: 0.822

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15520867705345154
Inter Cos: 0.14200371503829956
Norm Quadratic Average: 51.45970916748047
Nearest Class Center Accuracy: 0.8405

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14501795172691345
Inter Cos: 0.12634249031543732
Norm Quadratic Average: 53.99574279785156
Nearest Class Center Accuracy: 0.8585

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15182974934577942
Inter Cos: 0.10799456387758255
Norm Quadratic Average: 33.77499771118164
Nearest Class Center Accuracy: 0.903

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15680521726608276
Inter Cos: 0.10539074242115021
Norm Quadratic Average: 35.49169921875
Nearest Class Center Accuracy: 0.923

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19098995625972748
Inter Cos: 0.0882623940706253
Norm Quadratic Average: 23.947542190551758
Nearest Class Center Accuracy: 0.9515

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23664093017578125
Inter Cos: 0.09521471709012985
Norm Quadratic Average: 18.732078552246094
Nearest Class Center Accuracy: 0.967

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.97700500488281
Linear Weight Rank: 4031
Intra Cos: 0.3864487409591675
Inter Cos: 0.11342418193817139
Norm Quadratic Average: 114.71207427978516
Nearest Class Center Accuracy: 0.974

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.0075569152832
Linear Weight Rank: 3670
Intra Cos: 0.5042684078216553
Inter Cos: 0.14162962138652802
Norm Quadratic Average: 61.66680908203125
Nearest Class Center Accuracy: 0.9745

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2525815963745117
Linear Weight Rank: 10
Intra Cos: 0.6207910180091858
Inter Cos: 0.17181473970413208
Norm Quadratic Average: 39.1512451171875
Nearest Class Center Accuracy: 0.9755

Output Layer:
Intra Cos: 0.7857087850570679
Inter Cos: 0.2453000545501709
Norm Quadratic Average: 21.063377380371094
Nearest Class Center Accuracy: 0.9755

