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_314159_weight_decay_0.02.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 4.049050331115723
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: 4.080970764160156
Linear Weight Rank: 178
Intra Cos: 0.05106304585933685
Inter Cos: -0.00841486919671297
Norm Quadratic Average: 2.519496202468872
Nearest Class Center Accuracy: 0.6325

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.6798627376556396
Linear Weight Rank: 4
Intra Cos: 0.22932694852352142
Inter Cos: -0.028247637674212456
Norm Quadratic Average: 1.513516902923584
Nearest Class Center Accuracy: 0.6745

Output Layer:
Intra Cos: 0.28463876247406006
Inter Cos: -0.021072600036859512
Norm Quadratic Average: 2.1837923526763916
Nearest Class Center Accuracy: 0.66825

Test Set:
Average Loss: 0.8233134689331054
Accuracy: 0.6635
NC1 Within Class Collapse: 6.366278171539307
NC2 Equinorm: Features: 0.15926116704940796, Weights: 0.020291589200496674
NC2 Equiangle: Features: 0.21716986099878946, Weights: 0.08438404401143391
NC3 Self-Duality: 0.06512737274169922
NC4 NCC Mismatch: 0.08350000000000002

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 4.049050331115723
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: 4.080970764160156
Linear Weight Rank: 178
Intra Cos: 0.04581913724541664
Inter Cos: -0.004531839396804571
Norm Quadratic Average: 2.5181479454040527
Nearest Class Center Accuracy: 0.6175

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.6798627376556396
Linear Weight Rank: 4
Intra Cos: 0.19968101382255554
Inter Cos: -0.009678765200078487
Norm Quadratic Average: 1.5024091005325317
Nearest Class Center Accuracy: 0.6535

Output Layer:
Intra Cos: 0.24262824654579163
Inter Cos: -0.011461722664535046
Norm Quadratic Average: 2.1654741764068604
Nearest Class Center Accuracy: 0.6445

