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_0.01.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.492076873779297
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: 5.441858291625977
Linear Weight Rank: 179
Intra Cos: 0.0168736781924963
Inter Cos: 0.005322387907654047
Norm Quadratic Average: 3.256218433380127
Nearest Class Center Accuracy: 0.4775

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.1663262844085693
Linear Weight Rank: 4
Intra Cos: 0.07659313827753067
Inter Cos: 0.031340938061475754
Norm Quadratic Average: 1.4049686193466187
Nearest Class Center Accuracy: 0.51875

Output Layer:
Intra Cos: 0.14983579516410828
Inter Cos: 0.08022059500217438
Norm Quadratic Average: 1.2996110916137695
Nearest Class Center Accuracy: 0.5145

Test Set:
Average Loss: 1.149930233001709
Accuracy: 0.5045
NC1 Within Class Collapse: 18.424896240234375
NC2 Equinorm: Features: 0.07425174117088318, Weights: 0.037071388214826584
NC2 Equiangle: Features: 0.44796236356099445, Weights: 0.1296768585840861
NC3 Self-Duality: 0.18530559539794922
NC4 NCC Mismatch: 0.10699999999999998

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.492076873779297
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: 5.441858291625977
Linear Weight Rank: 179
Intra Cos: 0.017743032425642014
Inter Cos: 0.005602617282420397
Norm Quadratic Average: 3.2487502098083496
Nearest Class Center Accuracy: 0.4905

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.1663262844085693
Linear Weight Rank: 4
Intra Cos: 0.07690951228141785
Inter Cos: 0.03100539930164814
Norm Quadratic Average: 1.3930726051330566
Nearest Class Center Accuracy: 0.5025

Output Layer:
Intra Cos: 0.1349441260099411
Inter Cos: 0.0723736435174942
Norm Quadratic Average: 1.2843550443649292
Nearest Class Center Accuracy: 0.4975

