Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_mlp6_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_314159_weight_decay_0.0001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.143864631652832
Linear Weight Rank: 16
Intra Cos: 0.014583898708224297
Inter Cos: 0.004829856567084789
Norm Quadratic Average: 3.993140459060669
Nearest Class Center Accuracy: 0.447

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.301541328430176
Linear Weight Rank: 179
Intra Cos: 0.012544728815555573
Inter Cos: 0.004451993852853775
Norm Quadratic Average: 14.117392539978027
Nearest Class Center Accuracy: 0.464

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.8794937133789062
Linear Weight Rank: 4
Intra Cos: 0.014687682501971722
Inter Cos: -0.0005309288389980793
Norm Quadratic Average: 14.556954383850098
Nearest Class Center Accuracy: 0.6185

Output Layer:
Intra Cos: 0.5454676151275635
Inter Cos: -0.031368523836135864
Norm Quadratic Average: 4.372894287109375
Nearest Class Center Accuracy: 0.9335

Test Set:
Average Loss: 1.221265323638916
Accuracy: 0.5325
NC1 Within Class Collapse: 16.072031021118164
NC2 Equinorm: Features: 0.0463685542345047, Weights: 0.02882111817598343
NC2 Equiangle: Features: 0.20018176237742105, Weights: 0.03809206187725067
NC3 Self-Duality: 0.9997038841247559
NC4 NCC Mismatch: 0.43200000000000005

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.143864631652832
Linear Weight Rank: 16
Intra Cos: 0.014108894392848015
Inter Cos: 0.005012289620935917
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: 8.301541328430176
Linear Weight Rank: 179
Intra Cos: 0.01369209960103035
Inter Cos: 0.004361850209534168
Norm Quadratic Average: 14.060698509216309
Nearest Class Center Accuracy: 0.464

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.8794937133789062
Linear Weight Rank: 4
Intra Cos: 0.008849644102156162
Inter Cos: 0.0004856876330450177
Norm Quadratic Average: 14.572394371032715
Nearest Class Center Accuracy: 0.519

Output Layer:
Intra Cos: 0.15642768144607544
Inter Cos: 0.025120623409748077
Norm Quadratic Average: 4.199712753295898
Nearest Class Center Accuracy: 0.535

