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_979323_weight_decay_0.001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.5845308303833
Linear Weight Rank: 16
Intra Cos: 0.07988917827606201
Inter Cos: 0.001758486032485962
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: 8.63695240020752
Linear Weight Rank: 179
Intra Cos: 0.1736857146024704
Inter Cos: 0.004749658517539501
Norm Quadratic Average: 5.401309490203857
Nearest Class Center Accuracy: 0.944125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.007055282592773
Linear Weight Rank: 4
Intra Cos: 0.602100670337677
Inter Cos: 0.023049842566251755
Norm Quadratic Average: 6.783105373382568
Nearest Class Center Accuracy: 0.959375

Output Layer:
Intra Cos: 0.7776336669921875
Inter Cos: 0.03150397539138794
Norm Quadratic Average: 17.032962799072266
Nearest Class Center Accuracy: 0.9655

Test Set:
Average Loss: 0.08743920493125916
Accuracy: 0.9765
NC1 Within Class Collapse: 3.559227466583252
NC2 Equinorm: Features: 0.038275182247161865, Weights: 0.013704110868275166
NC2 Equiangle: Features: 0.43253127733866376, Weights: 0.38968706130981445
NC3 Self-Duality: 0.05669946223497391
NC4 NCC Mismatch: 0.04349999999999998

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.5845308303833
Linear Weight Rank: 16
Intra Cos: 0.08033028244972229
Inter Cos: 0.003312898799777031
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: 8.63695240020752
Linear Weight Rank: 179
Intra Cos: 0.1714661419391632
Inter Cos: 0.0027457773685455322
Norm Quadratic Average: 5.402510643005371
Nearest Class Center Accuracy: 0.949

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.007055282592773
Linear Weight Rank: 4
Intra Cos: 0.5888355374336243
Inter Cos: 0.013804536312818527
Norm Quadratic Average: 6.8269124031066895
Nearest Class Center Accuracy: 0.955

Output Layer:
Intra Cos: 0.7581361532211304
Inter Cos: 0.010211431421339512
Norm Quadratic Average: 17.140235900878906
Nearest Class Center Accuracy: 0.957

