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_979323_weight_decay_0.01.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.875327110290527
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222443655133247
Norm Quadratic Average: 3.9938876628875732
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 5.848161697387695
Linear Weight Rank: 179
Intra Cos: 0.03596818819642067
Inter Cos: -0.005037122871726751
Norm Quadratic Average: 3.5773422718048096
Nearest Class Center Accuracy: 0.623625

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.066765546798706
Linear Weight Rank: 4
Intra Cos: 0.195114403963089
Inter Cos: -0.03172152861952782
Norm Quadratic Average: 1.9666657447814941
Nearest Class Center Accuracy: 0.71425

Output Layer:
Intra Cos: 0.3487236797809601
Inter Cos: -0.049873851239681244
Norm Quadratic Average: 2.7717740535736084
Nearest Class Center Accuracy: 0.717125

Test Set:
Average Loss: 0.7325006923675537
Accuracy: 0.709
NC1 Within Class Collapse: 5.621434211730957
NC2 Equinorm: Features: 0.14297181367874146, Weights: 0.04923732578754425
NC2 Equiangle: Features: 0.19477562109629312, Weights: 0.03182211518287659
NC3 Self-Duality: 0.11663158237934113
NC4 NCC Mismatch: 0.08299999999999996

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.875327110290527
Linear Weight Rank: 16
Intra Cos: 0.030431468039751053
Inter Cos: -0.004549722652882338
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: 5.848161697387695
Linear Weight Rank: 179
Intra Cos: 0.032995469868183136
Inter Cos: -0.002569178817793727
Norm Quadratic Average: 3.5699832439422607
Nearest Class Center Accuracy: 0.6175

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.066765546798706
Linear Weight Rank: 4
Intra Cos: 0.17108313739299774
Inter Cos: -0.008561795577406883
Norm Quadratic Average: 1.9518393278121948
Nearest Class Center Accuracy: 0.6915

Output Layer:
Intra Cos: 0.30178388953208923
Inter Cos: -0.0319579541683197
Norm Quadratic Average: 2.750030517578125
Nearest Class Center Accuracy: 0.697

