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_265358_weight_decay_0.03.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.085188388824463
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: 2.2014000415802
Linear Weight Rank: 177
Intra Cos: 0.03284359723329544
Inter Cos: -0.004662688821554184
Norm Quadratic Average: 3.3670949935913086
Nearest Class Center Accuracy: 0.613375

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.724757194519043
Linear Weight Rank: 4
Intra Cos: 0.2003171443939209
Inter Cos: -0.049595315009355545
Norm Quadratic Average: 4.135234832763672
Nearest Class Center Accuracy: 0.94075

Output Layer:
Intra Cos: 0.6834070682525635
Inter Cos: -0.17750005424022675
Norm Quadratic Average: 3.6701512336730957
Nearest Class Center Accuracy: 0.958625

Test Set:
Average Loss: 0.5637823638916015
Accuracy: 0.7755
NC1 Within Class Collapse: 3.0900113582611084
NC2 Equinorm: Features: 0.11083102971315384, Weights: 0.036120783537626266
NC2 Equiangle: Features: 0.11419714490572612, Weights: 0.02345617612202962
NC3 Self-Duality: 0.16797083616256714
NC4 NCC Mismatch: 0.055499999999999994

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.085188388824463
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: 2.2014000415802
Linear Weight Rank: 177
Intra Cos: 0.02886742725968361
Inter Cos: -0.0044568367302417755
Norm Quadratic Average: 3.368055820465088
Nearest Class Center Accuracy: 0.611

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.724757194519043
Linear Weight Rank: 4
Intra Cos: 0.13787004351615906
Inter Cos: -0.014937367290258408
Norm Quadratic Average: 4.133500576019287
Nearest Class Center Accuracy: 0.7715

Output Layer:
Intra Cos: 0.44853678345680237
Inter Cos: -0.06021880730986595
Norm Quadratic Average: 3.6172561645507812
Nearest Class Center Accuracy: 0.7745

