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_979323_weight_decay_0.001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.152764320373535
Linear Weight Rank: 16
Intra Cos: 0.014583897776901722
Inter Cos: 0.004829857032746077
Norm Quadratic Average: 3.9931399822235107
Nearest Class Center Accuracy: 0.447

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.088242530822754
Linear Weight Rank: 179
Intra Cos: 0.014610277488827705
Inter Cos: 0.006582512520253658
Norm Quadratic Average: 4.894679546356201
Nearest Class Center Accuracy: 0.4675

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.535013198852539
Linear Weight Rank: 4
Intra Cos: 0.04309242591261864
Inter Cos: 0.019273897632956505
Norm Quadratic Average: 2.3719890117645264
Nearest Class Center Accuracy: 0.524625

Output Layer:
Intra Cos: 0.17574161291122437
Inter Cos: 0.0821177065372467
Norm Quadratic Average: 1.5644402503967285
Nearest Class Center Accuracy: 0.5445

Test Set:
Average Loss: 1.1169740829467774
Accuracy: 0.5185
NC1 Within Class Collapse: 17.016279220581055
NC2 Equinorm: Features: 0.11041060090065002, Weights: 0.024497538805007935
NC2 Equiangle: Features: 0.3887906074523926, Weights: 0.10338306427001953
NC3 Self-Duality: 0.38387393951416016
NC4 NCC Mismatch: 0.15349999999999997

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.152764320373535
Linear Weight Rank: 16
Intra Cos: 0.014108890667557716
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: 8.088242530822754
Linear Weight Rank: 179
Intra Cos: 0.013994037173688412
Inter Cos: 0.006216066889464855
Norm Quadratic Average: 4.869888782501221
Nearest Class Center Accuracy: 0.4705

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.535013198852539
Linear Weight Rank: 4
Intra Cos: 0.03729822114109993
Inter Cos: 0.0194869227707386
Norm Quadratic Average: 2.353783369064331
Nearest Class Center Accuracy: 0.5075

Output Layer:
Intra Cos: 0.14668631553649902
Inter Cos: 0.08080869913101196
Norm Quadratic Average: 1.5494824647903442
Nearest Class Center Accuracy: 0.51

