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_979323_weight_decay_0.003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.822346210479736
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222443655133247
Norm Quadratic Average: 3.9938876628875732
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 7.7705841064453125
Linear Weight Rank: 179
Intra Cos: 0.031465012580156326
Inter Cos: -0.005144278984516859
Norm Quadratic Average: 4.727357387542725
Nearest Class Center Accuracy: 0.61325

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.4188783168792725
Linear Weight Rank: 4
Intra Cos: 0.14397796988487244
Inter Cos: -0.024543099105358124
Norm Quadratic Average: 2.7049050331115723
Nearest Class Center Accuracy: 0.73225

Output Layer:
Intra Cos: 0.36466512084007263
Inter Cos: -0.06957007199525833
Norm Quadratic Average: 3.415501356124878
Nearest Class Center Accuracy: 0.7485

Test Set:
Average Loss: 0.6733365459442139
Accuracy: 0.727
NC1 Within Class Collapse: 5.455915451049805
NC2 Equinorm: Features: 0.1281324028968811, Weights: 0.055531054735183716
NC2 Equiangle: Features: 0.18115580081939697, Weights: 0.025836532314618427
NC3 Self-Duality: 0.18497967720031738
NC4 NCC Mismatch: 0.10150000000000003

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.822346210479736
Linear Weight Rank: 16
Intra Cos: 0.030431468039751053
Inter Cos: -0.004549722652882338
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: 7.7705841064453125
Linear Weight Rank: 179
Intra Cos: 0.02899354137480259
Inter Cos: -0.0033340146765112877
Norm Quadratic Average: 4.718195915222168
Nearest Class Center Accuracy: 0.6095

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.4188783168792725
Linear Weight Rank: 4
Intra Cos: 0.126071497797966
Inter Cos: -0.008002771064639091
Norm Quadratic Average: 2.687185525894165
Nearest Class Center Accuracy: 0.7085

Output Layer:
Intra Cos: 0.33727002143859863
Inter Cos: -0.045837219804525375
Norm Quadratic Average: 3.385859727859497
Nearest Class Center Accuracy: 0.724

