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_265358_weight_decay_0.0001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.91087818145752
Linear Weight Rank: 16
Intra Cos: 0.03299568220973015
Inter Cos: -0.006222444586455822
Norm Quadratic Average: 3.9938879013061523
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.810834884643555
Linear Weight Rank: 179
Intra Cos: 0.03239777311682701
Inter Cos: -0.00289746792986989
Norm Quadratic Average: 5.276116847991943
Nearest Class Center Accuracy: 0.615875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.5937838554382324
Linear Weight Rank: 4
Intra Cos: 0.12110185623168945
Inter Cos: -0.022624680772423744
Norm Quadratic Average: 3.2222421169281006
Nearest Class Center Accuracy: 0.73375

Output Layer:
Intra Cos: 0.3225986361503601
Inter Cos: -0.06996899843215942
Norm Quadratic Average: 3.8859574794769287
Nearest Class Center Accuracy: 0.7555

Test Set:
Average Loss: 0.6511293201446533
Accuracy: 0.729
NC1 Within Class Collapse: 5.510374546051025
NC2 Equinorm: Features: 0.12810589373111725, Weights: 0.04563603177666664
NC2 Equiangle: Features: 0.18829554319381714, Weights: 0.0375988706946373
NC3 Self-Duality: 0.22114306688308716
NC4 NCC Mismatch: 0.11150000000000004

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.91087818145752
Linear Weight Rank: 16
Intra Cos: 0.030431464314460754
Inter Cos: -0.004549724515527487
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: 8.810834884643555
Linear Weight Rank: 179
Intra Cos: 0.028742078691720963
Inter Cos: -0.002894491422921419
Norm Quadratic Average: 5.275757789611816
Nearest Class Center Accuracy: 0.613

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.5937838554382324
Linear Weight Rank: 4
Intra Cos: 0.10779114067554474
Inter Cos: -0.012145759537816048
Norm Quadratic Average: 3.214764356613159
Nearest Class Center Accuracy: 0.71

Output Layer:
Intra Cos: 0.292333722114563
Inter Cos: -0.047780055552721024
Norm Quadratic Average: 3.8706390857696533
Nearest Class Center Accuracy: 0.724

