Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_conic_epochs_200_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_265358_weight_decay_0.05.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.2730464935302734
Linear Weight Rank: 16
Intra Cos: 0.07988916337490082
Inter Cos: 0.0017584804445505142
Norm Quadratic Average: 4.001680374145508
Nearest Class Center Accuracy: 0.948875

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 2.575058937072754
Linear Weight Rank: 174
Intra Cos: 0.6674988865852356
Inter Cos: 0.016072943806648254
Norm Quadratic Average: 1.7129586935043335
Nearest Class Center Accuracy: 0.98075

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.561349630355835
Linear Weight Rank: 4
Intra Cos: 0.7581690549850464
Inter Cos: 0.020597614347934723
Norm Quadratic Average: 2.270015239715576
Nearest Class Center Accuracy: 0.984875

Output Layer:
Intra Cos: 0.8355851173400879
Inter Cos: 0.019697491079568863
Norm Quadratic Average: 3.9064927101135254
Nearest Class Center Accuracy: 0.98575

Test Set:
Average Loss: 0.3140553932189941
Accuracy: 0.9865
NC1 Within Class Collapse: 4.021710395812988
NC2 Equinorm: Features: 0.03671108931303024, Weights: 0.013435066677629948
NC2 Equiangle: Features: 0.4383179346720378, Weights: 0.4228557348251343
NC3 Self-Duality: 0.007255923002958298
NC4 NCC Mismatch: 0.029000000000000026

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.2730464935302734
Linear Weight Rank: 16
Intra Cos: 0.0803302749991417
Inter Cos: 0.0033129025250673294
Norm Quadratic Average: 3.9883358478546143
Nearest Class Center Accuracy: 0.9165

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 2.575058937072754
Linear Weight Rank: 174
Intra Cos: 0.6743372678756714
Inter Cos: 0.03990573436021805
Norm Quadratic Average: 1.7277265787124634
Nearest Class Center Accuracy: 0.9745

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.561349630355835
Linear Weight Rank: 4
Intra Cos: 0.7572357058525085
Inter Cos: 0.045508913695812225
Norm Quadratic Average: 2.288180351257324
Nearest Class Center Accuracy: 0.9765

Output Layer:
Intra Cos: 0.838323175907135
Inter Cos: 0.04577963799238205
Norm Quadratic Average: 3.932173013687134
Nearest Class Center Accuracy: 0.9815

