Model save path: ./New_Models/bn_True_dataset_CIFAR10_epochs_200_lr_0.01_model_type_vgg11_rand_seed_979323_test_samples_None_train_samples_None_weight_decay_0.001.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0198909230530262
Inter Cos: 0.10477276891469955
Norm Quadratic Average: 27.59718894958496
Nearest Class Center Accuracy: 0.26968

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018375974148511887
Inter Cos: 0.07262958586215973
Norm Quadratic Average: 15.142900466918945
Nearest Class Center Accuracy: 0.40376

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01992810145020485
Inter Cos: 0.05048411339521408
Norm Quadratic Average: 7.398589134216309
Nearest Class Center Accuracy: 0.53626

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0150452284142375
Inter Cos: 0.03800336271524429
Norm Quadratic Average: 5.92990255355835
Nearest Class Center Accuracy: 0.6205

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.020731600001454353
Inter Cos: 0.03422046825289726
Norm Quadratic Average: 3.909559726715088
Nearest Class Center Accuracy: 0.74846

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03478584066033363
Inter Cos: 0.0352901853621006
Norm Quadratic Average: 2.7395167350769043
Nearest Class Center Accuracy: 0.85702

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1473192423582077
Inter Cos: 0.08725952357053757
Norm Quadratic Average: 2.0345351696014404
Nearest Class Center Accuracy: 0.97058

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6453773975372314
Inter Cos: 0.09460116177797318
Norm Quadratic Average: 1.345527172088623
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 4.827770233154297
Linear Weight Rank: 4029
Intra Cos: 0.9296524524688721
Inter Cos: -0.0364002101123333
Norm Quadratic Average: 24.99822425842285
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 3.2873892784118652
Linear Weight Rank: 3636
Intra Cos: 0.9727930426597595
Inter Cos: -0.04649669677019119
Norm Quadratic Average: 18.90059471130371
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.6369152069091797
Linear Weight Rank: 9
Intra Cos: 0.968475341796875
Inter Cos: 0.05091112479567528
Norm Quadratic Average: 14.404006004333496
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9870221018791199
Inter Cos: 0.18630632758140564
Norm Quadratic Average: 12.26600170135498
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.5993814939498902
Accuracy: 0.8554
NC1 Within Class Collapse: 3.7787303924560547
NC2 Equinorm: Features: 0.1449647843837738, Weights: 0.01649085432291031
NC2 Equiangle: Features: 0.11253501044379341, Weights: 0.038451125886705184
NC3 Self-Duality: 0.09676948934793472
NC4 NCC Mismatch: 0.023900000000000032

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018526077270507812
Inter Cos: 0.1042705774307251
Norm Quadratic Average: 27.550140380859375
Nearest Class Center Accuracy: 0.284

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.017376722767949104
Inter Cos: 0.0742933377623558
Norm Quadratic Average: 15.131431579589844
Nearest Class Center Accuracy: 0.4233

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018680069595575333
Inter Cos: 0.05149229243397713
Norm Quadratic Average: 7.399735927581787
Nearest Class Center Accuracy: 0.5456

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.013860749080777168
Inter Cos: 0.03877171501517296
Norm Quadratic Average: 5.93643045425415
Nearest Class Center Accuracy: 0.6295

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.017742794007062912
Inter Cos: 0.03511201962828636
Norm Quadratic Average: 3.9116311073303223
Nearest Class Center Accuracy: 0.7108

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.026799025014042854
Inter Cos: 0.037240538746118546
Norm Quadratic Average: 2.7263896465301514
Nearest Class Center Accuracy: 0.7624

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10326407104730606
Inter Cos: 0.09657599776983261
Norm Quadratic Average: 1.9962058067321777
Nearest Class Center Accuracy: 0.8063

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3251274526119232
Inter Cos: 0.18493697047233582
Norm Quadratic Average: 1.2535860538482666
Nearest Class Center Accuracy: 0.8493

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 4.827770233154297
Linear Weight Rank: 4029
Intra Cos: 0.520126223564148
Inter Cos: 0.22613410651683807
Norm Quadratic Average: 22.256366729736328
Nearest Class Center Accuracy: 0.8466

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 3.2873892784118652
Linear Weight Rank: 3636
Intra Cos: 0.5333861708641052
Inter Cos: 0.22163599729537964
Norm Quadratic Average: 16.61862564086914
Nearest Class Center Accuracy: 0.8509

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.6369152069091797
Linear Weight Rank: 9
Intra Cos: 0.5337145924568176
Inter Cos: 0.24022048711776733
Norm Quadratic Average: 12.793527603149414
Nearest Class Center Accuracy: 0.8532

Output Layer:
Intra Cos: 0.5751137137413025
Inter Cos: 0.29851993918418884
Norm Quadratic Average: 10.874079704284668
Nearest Class Center Accuracy: 0.854

