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_0.0007.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.772448539733887
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: 8.78485107421875
Linear Weight Rank: 179
Intra Cos: 0.17700053751468658
Inter Cos: 0.006990102119743824
Norm Quadratic Average: 5.43374490737915
Nearest Class Center Accuracy: 0.956125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.054575443267822
Linear Weight Rank: 4
Intra Cos: 0.6276074647903442
Inter Cos: 0.03373289853334427
Norm Quadratic Average: 6.884685039520264
Nearest Class Center Accuracy: 0.9805

Output Layer:
Intra Cos: 0.810458242893219
Inter Cos: 0.03281775116920471
Norm Quadratic Average: 17.435197830200195
Nearest Class Center Accuracy: 0.98225

Test Set:
Average Loss: 0.089223388671875
Accuracy: 0.9755
NC1 Within Class Collapse: 2.730346918106079
NC2 Equinorm: Features: 0.02674071304500103, Weights: 0.023339835926890373
NC2 Equiangle: Features: 0.43200989564259845, Weights: 0.3878515958786011
NC3 Self-Duality: 0.05396542698144913
NC4 NCC Mismatch: 0.023499999999999965

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.772448539733887
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: 8.78485107421875
Linear Weight Rank: 179
Intra Cos: 0.17915254831314087
Inter Cos: 0.003564688144251704
Norm Quadratic Average: 5.439719200134277
Nearest Class Center Accuracy: 0.9555

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.054575443267822
Linear Weight Rank: 4
Intra Cos: 0.62502521276474
Inter Cos: 0.028895486146211624
Norm Quadratic Average: 6.946125507354736
Nearest Class Center Accuracy: 0.965

Output Layer:
Intra Cos: 0.7975566983222961
Inter Cos: 0.03482115641236305
Norm Quadratic Average: 17.57825469970703
Nearest Class Center Accuracy: 0.969

