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_265358_weight_decay_0.05.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 1.898618459701538
Linear Weight Rank: 16
Intra Cos: 0.03299568220973015
Inter Cos: -0.006222444586455822
Norm Quadratic Average: 3.9938879013061523
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 2.033435344696045
Linear Weight Rank: 176
Intra Cos: 0.11990570276975632
Inter Cos: -0.010720115154981613
Norm Quadratic Average: 1.3415660858154297
Nearest Class Center Accuracy: 0.595125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 1.9611644744873047
Linear Weight Rank: 4
Intra Cos: 0.18869543075561523
Inter Cos: 0.00027599770692177117
Norm Quadratic Average: 1.0846872329711914
Nearest Class Center Accuracy: 0.593125

Output Layer:
Intra Cos: 0.18904349207878113
Inter Cos: 0.014313433319330215
Norm Quadratic Average: 1.2495667934417725
Nearest Class Center Accuracy: 0.585125

Test Set:
Average Loss: 1.0118952751159669
Accuracy: 0.605
NC1 Within Class Collapse: 8.367826461791992
NC2 Equinorm: Features: 0.18727527558803558, Weights: 0.04869908094406128
NC2 Equiangle: Features: 0.27545690536499023, Weights: 0.13993866244951883
NC3 Self-Duality: 0.048843443393707275
NC4 NCC Mismatch: 0.09999999999999998

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 1.898618459701538
Linear Weight Rank: 16
Intra Cos: 0.030431464314460754
Inter Cos: -0.004549724515527487
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: 2.033435344696045
Linear Weight Rank: 176
Intra Cos: 0.10937294363975525
Inter Cos: -0.0007849302492104471
Norm Quadratic Average: 1.3378980159759521
Nearest Class Center Accuracy: 0.5955

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 1.9611644744873047
Linear Weight Rank: 4
Intra Cos: 0.16928735375404358
Inter Cos: 0.01843656785786152
Norm Quadratic Average: 1.0796544551849365
Nearest Class Center Accuracy: 0.5915

Output Layer:
Intra Cos: 0.1736336648464203
Inter Cos: 0.030805982649326324
Norm Quadratic Average: 1.242801547050476
Nearest Class Center Accuracy: 0.5835

