Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_mlp3_epochs_200_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: 8.855006217956543
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222447380423546
Norm Quadratic Average: 3.9938881397247314
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.864516258239746
Linear Weight Rank: 179
Intra Cos: 0.030616916716098785
Inter Cos: -0.005657619331032038
Norm Quadratic Average: 5.320298671722412
Nearest Class Center Accuracy: 0.610875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.7008860111236572
Linear Weight Rank: 4
Intra Cos: 0.12393976747989655
Inter Cos: -0.021688446402549744
Norm Quadratic Average: 3.2056844234466553
Nearest Class Center Accuracy: 0.739625

Output Layer:
Intra Cos: 0.35348841547966003
Inter Cos: -0.07482434809207916
Norm Quadratic Average: 3.975229263305664
Nearest Class Center Accuracy: 0.761

Test Set:
Average Loss: 0.6392701187133789
Accuracy: 0.7355
NC1 Within Class Collapse: 5.400135040283203
NC2 Equinorm: Features: 0.1414634883403778, Weights: 0.048441268503665924
NC2 Equiangle: Features: 0.1829784313837687, Weights: 0.03315966824690501
NC3 Self-Duality: 0.23019523918628693
NC4 NCC Mismatch: 0.11099999999999999

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.855006217956543
Linear Weight Rank: 16
Intra Cos: 0.030431464314460754
Inter Cos: -0.004549724981188774
Norm Quadratic Average: 3.995159864425659
Nearest Class Center Accuracy: 0.583

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.864516258239746
Linear Weight Rank: 179
Intra Cos: 0.029138682410120964
Inter Cos: -0.0044857896864414215
Norm Quadratic Average: 5.329483509063721
Nearest Class Center Accuracy: 0.6055

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.7008860111236572
Linear Weight Rank: 4
Intra Cos: 0.10957509279251099
Inter Cos: -0.00940999947488308
Norm Quadratic Average: 3.191070079803467
Nearest Class Center Accuracy: 0.709

Output Layer:
Intra Cos: 0.329373300075531
Inter Cos: -0.0555470809340477
Norm Quadratic Average: 3.9195661544799805
Nearest Class Center Accuracy: 0.7265

