Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_mlp3_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_265358_weight_decay_0.02.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 3.2321083545684814
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: 3.2903671264648438
Linear Weight Rank: 178
Intra Cos: 0.03142065182328224
Inter Cos: -0.004323868080973625
Norm Quadratic Average: 5.400875568389893
Nearest Class Center Accuracy: 0.60925

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.983571767807007
Linear Weight Rank: 4
Intra Cos: 0.11571953445672989
Inter Cos: -0.026343191042542458
Norm Quadratic Average: 6.074008464813232
Nearest Class Center Accuracy: 0.9485

Output Layer:
Intra Cos: 0.673906683921814
Inter Cos: -0.16832482814788818
Norm Quadratic Average: 4.469085693359375
Nearest Class Center Accuracy: 0.9785

Test Set:
Average Loss: 0.5523147335052491
Accuracy: 0.77
NC1 Within Class Collapse: 3.3045976161956787
NC2 Equinorm: Features: 0.12248905748128891, Weights: 0.03785068169236183
NC2 Equiangle: Features: 0.11508952577908833, Weights: 0.023821587363878887
NC3 Self-Duality: 0.2408684343099594
NC4 NCC Mismatch: 0.07399999999999995

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 3.2321083545684814
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: 3.2903671264648438
Linear Weight Rank: 178
Intra Cos: 0.027692006900906563
Inter Cos: -0.004208162892609835
Norm Quadratic Average: 5.400033473968506
Nearest Class Center Accuracy: 0.61

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.983571767807007
Linear Weight Rank: 4
Intra Cos: 0.08130554109811783
Inter Cos: -0.008386123925447464
Norm Quadratic Average: 6.088249206542969
Nearest Class Center Accuracy: 0.7815

Output Layer:
Intra Cos: 0.44191303849220276
Inter Cos: -0.06506907939910889
Norm Quadratic Average: 4.403329849243164
Nearest Class Center Accuracy: 0.7765

