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_0.01.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.8450398445129395
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: 5.932653427124023
Linear Weight Rank: 179
Intra Cos: 0.24724221229553223
Inter Cos: 0.005231102462857962
Norm Quadratic Average: 3.741238832473755
Nearest Class Center Accuracy: 0.969125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.4550344944000244
Linear Weight Rank: 4
Intra Cos: 0.6833640933036804
Inter Cos: 0.0290328711271286
Norm Quadratic Average: 4.521317481994629
Nearest Class Center Accuracy: 0.982125

Output Layer:
Intra Cos: 0.8201022148132324
Inter Cos: 0.02410288341343403
Norm Quadratic Average: 10.072271347045898
Nearest Class Center Accuracy: 0.98375

Test Set:
Average Loss: 0.1338289098739624
Accuracy: 0.9775
NC1 Within Class Collapse: 2.619032382965088
NC2 Equinorm: Features: 0.02945089153945446, Weights: 0.02116134949028492
NC2 Equiangle: Features: 0.43151211738586426, Weights: 0.39842971165974933
NC3 Self-Duality: 0.0320444330573082
NC4 NCC Mismatch: 0.02949999999999997

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.8450398445129395
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: 5.932653427124023
Linear Weight Rank: 179
Intra Cos: 0.244145467877388
Inter Cos: 0.008661923930048943
Norm Quadratic Average: 3.750222682952881
Nearest Class Center Accuracy: 0.968

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.4550344944000244
Linear Weight Rank: 4
Intra Cos: 0.6808097958564758
Inter Cos: 0.03688923642039299
Norm Quadratic Average: 4.561976909637451
Nearest Class Center Accuracy: 0.968

Output Layer:
Intra Cos: 0.8105185627937317
Inter Cos: 0.03777867555618286
Norm Quadratic Average: 10.148771286010742
Nearest Class Center Accuracy: 0.974

