Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_mlp6_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_265358_weight_decay_0.0005.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.396106719970703
Linear Weight Rank: 16
Intra Cos: 0.014583894982933998
Inter Cos: 0.004829855635762215
Norm Quadratic Average: 3.9931397438049316
Nearest Class Center Accuracy: 0.447

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.309599876403809
Linear Weight Rank: 180
Intra Cos: 0.014000454917550087
Inter Cos: 0.0037886970676481724
Norm Quadratic Average: 4.940368175506592
Nearest Class Center Accuracy: 0.470875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.615271806716919
Linear Weight Rank: 4
Intra Cos: 0.04135860502719879
Inter Cos: 0.012323426082730293
Norm Quadratic Average: 2.4403858184814453
Nearest Class Center Accuracy: 0.536875

Output Layer:
Intra Cos: 0.1792001873254776
Inter Cos: 0.06178267300128937
Norm Quadratic Average: 1.6353739500045776
Nearest Class Center Accuracy: 0.552375

Test Set:
Average Loss: 1.1026362190246581
Accuracy: 0.5265
NC1 Within Class Collapse: 16.28394317626953
NC2 Equinorm: Features: 0.04414806887507439, Weights: 0.04980683699250221
NC2 Equiangle: Features: 0.3752439816792806, Weights: 0.09541002909342448
NC3 Self-Duality: 0.371969074010849
NC4 NCC Mismatch: 0.15800000000000003

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.396106719970703
Linear Weight Rank: 16
Intra Cos: 0.014108894392848015
Inter Cos: 0.005012288689613342
Norm Quadratic Average: 3.9761204719543457
Nearest Class Center Accuracy: 0.4485

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.309599876403809
Linear Weight Rank: 180
Intra Cos: 0.014633679762482643
Inter Cos: 0.004004367161542177
Norm Quadratic Average: 4.931631565093994
Nearest Class Center Accuracy: 0.4795

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.615271806716919
Linear Weight Rank: 4
Intra Cos: 0.03814862668514252
Inter Cos: 0.012054920196533203
Norm Quadratic Average: 2.4276959896087646
Nearest Class Center Accuracy: 0.5255

Output Layer:
Intra Cos: 0.14935094118118286
Inter Cos: 0.05457058176398277
Norm Quadratic Average: 1.6086236238479614
Nearest Class Center Accuracy: 0.52

