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_0.0005.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.76058578491211
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: 8.66248607635498
Linear Weight Rank: 179
Intra Cos: 0.03252260014414787
Inter Cos: -0.0029132564086467028
Norm Quadratic Average: 5.188472270965576
Nearest Class Center Accuracy: 0.616125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.5727105140686035
Linear Weight Rank: 4
Intra Cos: 0.12399228662252426
Inter Cos: -0.02316730096936226
Norm Quadratic Average: 3.1452341079711914
Nearest Class Center Accuracy: 0.73325

Output Layer:
Intra Cos: 0.3223663568496704
Inter Cos: -0.06975406408309937
Norm Quadratic Average: 3.8329126834869385
Nearest Class Center Accuracy: 0.753875

Test Set:
Average Loss: 0.6530868587493897
Accuracy: 0.725
NC1 Within Class Collapse: 5.5010881423950195
NC2 Equinorm: Features: 0.12850753962993622, Weights: 0.04591565206646919
NC2 Equiangle: Features: 0.18832528591156006, Weights: 0.037647709250450134
NC3 Self-Duality: 0.21386462450027466
NC4 NCC Mismatch: 0.10999999999999999

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.76058578491211
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: 8.66248607635498
Linear Weight Rank: 179
Intra Cos: 0.028850479051470757
Inter Cos: -0.0029130391776561737
Norm Quadratic Average: 5.18798303604126
Nearest Class Center Accuracy: 0.614

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.5727105140686035
Linear Weight Rank: 4
Intra Cos: 0.11040311306715012
Inter Cos: -0.012261432595551014
Norm Quadratic Average: 3.137535333633423
Nearest Class Center Accuracy: 0.711

Output Layer:
Intra Cos: 0.29249680042266846
Inter Cos: -0.04762586951255798
Norm Quadratic Average: 3.8176376819610596
Nearest Class Center Accuracy: 0.723

