Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_mlp3_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_265358_weight_decay_0.007.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 6.6909403800964355
Linear Weight Rank: 16
Intra Cos: 0.03299568220973015
Inter Cos: -0.006222444586455822
Norm Quadratic Average: 3.9938879013061523
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 6.623363971710205
Linear Weight Rank: 179
Intra Cos: 0.03532325476408005
Inter Cos: -0.0034158658236265182
Norm Quadratic Average: 3.9876301288604736
Nearest Class Center Accuracy: 0.6265

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.2505879402160645
Linear Weight Rank: 4
Intra Cos: 0.1760398894548416
Inter Cos: -0.03184144198894501
Norm Quadratic Average: 2.240809440612793
Nearest Class Center Accuracy: 0.724125

Output Layer:
Intra Cos: 0.3153815269470215
Inter Cos: -0.06305520236492157
Norm Quadratic Average: 3.1200430393218994
Nearest Class Center Accuracy: 0.734

Test Set:
Average Loss: 0.6951143741607666
Accuracy: 0.7145
NC1 Within Class Collapse: 5.474797248840332
NC2 Equinorm: Features: 0.13601404428482056, Weights: 0.04620955511927605
NC2 Equiangle: Features: 0.1927619775136312, Weights: 0.03832040230433146
NC3 Self-Duality: 0.12845078110694885
NC4 NCC Mismatch: 0.09650000000000003

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 6.6909403800964355
Linear Weight Rank: 16
Intra Cos: 0.030431464314460754
Inter Cos: -0.004549724515527487
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: 6.623363971710205
Linear Weight Rank: 179
Intra Cos: 0.03134163096547127
Inter Cos: -0.0033980808220803738
Norm Quadratic Average: 3.984750509262085
Nearest Class Center Accuracy: 0.624

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.2505879402160645
Linear Weight Rank: 4
Intra Cos: 0.1580715924501419
Inter Cos: -0.014579460956156254
Norm Quadratic Average: 2.2313461303710938
Nearest Class Center Accuracy: 0.7025

Output Layer:
Intra Cos: 0.29440975189208984
Inter Cos: -0.043356046080589294
Norm Quadratic Average: 3.106074810028076
Nearest Class Center Accuracy: 0.703

