Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_mlp3_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_314159_weight_decay_0.007.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.8730549812316895
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222445517778397
Norm Quadratic Average: 3.9938883781433105
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 5.937814235687256
Linear Weight Rank: 179
Intra Cos: 0.027624979615211487
Inter Cos: -0.004443490877747536
Norm Quadratic Average: 10.072504043579102
Nearest Class Center Accuracy: 0.59125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.439582586288452
Linear Weight Rank: 4
Intra Cos: 0.057116854935884476
Inter Cos: -0.012300264090299606
Norm Quadratic Average: 10.568670272827148
Nearest Class Center Accuracy: 0.870125

Output Layer:
Intra Cos: 0.5964425802230835
Inter Cos: -0.11428820341825485
Norm Quadratic Average: 6.3194899559021
Nearest Class Center Accuracy: 0.980875

Test Set:
Average Loss: 0.5892860889434814
Accuracy: 0.7645
NC1 Within Class Collapse: 4.48555326461792
NC2 Equinorm: Features: 0.13137571513652802, Weights: 0.04925760254263878
NC2 Equiangle: Features: 0.1404897173245748, Weights: 0.023928758998711903
NC3 Self-Duality: 0.41983649134635925
NC4 NCC Mismatch: 0.17000000000000004

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.8730549812316895
Linear Weight Rank: 16
Intra Cos: 0.030431468039751053
Inter Cos: -0.0045497240498661995
Norm Quadratic Average: 3.9951601028442383
Nearest Class Center Accuracy: 0.583

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 5.937814235687256
Linear Weight Rank: 179
Intra Cos: 0.026674004271626472
Inter Cos: -0.0038640168495476246
Norm Quadratic Average: 10.111961364746094
Nearest Class Center Accuracy: 0.582

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.439582586288452
Linear Weight Rank: 4
Intra Cos: 0.04290539026260376
Inter Cos: -0.003942683804780245
Norm Quadratic Average: 10.602425575256348
Nearest Class Center Accuracy: 0.7295

Output Layer:
Intra Cos: 0.38508111238479614
Inter Cos: -0.04251052439212799
Norm Quadratic Average: 6.188669204711914
Nearest Class Center Accuracy: 0.7595

