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_0.0005.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.659568786621094
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: 8.669573783874512
Linear Weight Rank: 179
Intra Cos: 0.03076902963221073
Inter Cos: -0.005662290845066309
Norm Quadratic Average: 5.203141212463379
Nearest Class Center Accuracy: 0.609

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.5603721141815186
Linear Weight Rank: 4
Intra Cos: 0.12606681883335114
Inter Cos: -0.020727137103676796
Norm Quadratic Average: 3.0833654403686523
Nearest Class Center Accuracy: 0.73275

Output Layer:
Intra Cos: 0.34867897629737854
Inter Cos: -0.0688682347536087
Norm Quadratic Average: 3.7447988986968994
Nearest Class Center Accuracy: 0.75125

Test Set:
Average Loss: 0.6542211418151855
Accuracy: 0.7285
NC1 Within Class Collapse: 5.489495277404785
NC2 Equinorm: Features: 0.14501550793647766, Weights: 0.04879717156291008
NC2 Equiangle: Features: 0.18564748764038086, Weights: 0.034278651078542076
NC3 Self-Duality: 0.22515763342380524
NC4 NCC Mismatch: 0.10499999999999998

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.659568786621094
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: 8.669573783874512
Linear Weight Rank: 179
Intra Cos: 0.02931695431470871
Inter Cos: -0.00447523407638073
Norm Quadratic Average: 5.21221923828125
Nearest Class Center Accuracy: 0.6045

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.5603721141815186
Linear Weight Rank: 4
Intra Cos: 0.10998191684484482
Inter Cos: -0.009101375937461853
Norm Quadratic Average: 3.0683534145355225
Nearest Class Center Accuracy: 0.7045

Output Layer:
Intra Cos: 0.32726070284843445
Inter Cos: -0.05329493060708046
Norm Quadratic Average: 3.690756320953369
Nearest Class Center Accuracy: 0.721

