Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_mlp3_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_314159_weight_decay_0.003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.106893539428711
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222445517778397
Norm Quadratic Average: 3.9938883781433105
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 7.169410228729248
Linear Weight Rank: 179
Intra Cos: 0.02734002284705639
Inter Cos: -0.0043776133097708225
Norm Quadratic Average: 12.214470863342285
Nearest Class Center Accuracy: 0.59

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.6371653079986572
Linear Weight Rank: 4
Intra Cos: 0.04790862649679184
Inter Cos: -0.009475057944655418
Norm Quadratic Average: 12.660677909851074
Nearest Class Center Accuracy: 0.828375

Output Layer:
Intra Cos: 0.5764306783676147
Inter Cos: -0.0999358743429184
Norm Quadratic Average: 7.092560291290283
Nearest Class Center Accuracy: 0.978375

Test Set:
Average Loss: 0.6094838008880615
Accuracy: 0.768
NC1 Within Class Collapse: 5.027318477630615
NC2 Equinorm: Features: 0.1375013142824173, Weights: 0.049929067492485046
NC2 Equiangle: Features: 0.14073247710863748, Weights: 0.029867462813854218
NC3 Self-Duality: 0.5151792168617249
NC4 NCC Mismatch: 0.22250000000000003

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.106893539428711
Linear Weight Rank: 16
Intra Cos: 0.030431468039751053
Inter Cos: -0.0045497240498661995
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: 7.169410228729248
Linear Weight Rank: 179
Intra Cos: 0.026307953521609306
Inter Cos: -0.003801181446760893
Norm Quadratic Average: 12.264047622680664
Nearest Class Center Accuracy: 0.583

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.6371653079986572
Linear Weight Rank: 4
Intra Cos: 0.035843368619680405
Inter Cos: -0.0034343991428613663
Norm Quadratic Average: 12.697948455810547
Nearest Class Center Accuracy: 0.702

Output Layer:
Intra Cos: 0.37829649448394775
Inter Cos: -0.04205251485109329
Norm Quadratic Average: 6.951051235198975
Nearest Class Center Accuracy: 0.7605

