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_0.02.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 4.1127824783325195
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: 4.103278160095215
Linear Weight Rank: 178
Intra Cos: 0.04814302921295166
Inter Cos: -0.0062905545346438885
Norm Quadratic Average: 2.5277113914489746
Nearest Class Center Accuracy: 0.636875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.724915027618408
Linear Weight Rank: 4
Intra Cos: 0.23775619268417358
Inter Cos: -0.03573191910982132
Norm Quadratic Average: 1.5126014947891235
Nearest Class Center Accuracy: 0.678625

Output Layer:
Intra Cos: 0.2938687801361084
Inter Cos: -0.03508208692073822
Norm Quadratic Average: 2.2041213512420654
Nearest Class Center Accuracy: 0.67475

Test Set:
Average Loss: 0.8105607986450195
Accuracy: 0.671
NC1 Within Class Collapse: 6.029956817626953
NC2 Equinorm: Features: 0.14936867356300354, Weights: 0.031356725841760635
NC2 Equiangle: Features: 0.20702548821767172, Weights: 0.05192486445109049
NC3 Self-Duality: 0.06325939297676086
NC4 NCC Mismatch: 0.08950000000000002

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 4.1127824783325195
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: 4.103278160095215
Linear Weight Rank: 178
Intra Cos: 0.04334777593612671
Inter Cos: -0.005211174953728914
Norm Quadratic Average: 2.5226821899414062
Nearest Class Center Accuracy: 0.634

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.724915027618408
Linear Weight Rank: 4
Intra Cos: 0.2116926908493042
Inter Cos: -0.013063502497971058
Norm Quadratic Average: 1.5041053295135498
Nearest Class Center Accuracy: 0.661

Output Layer:
Intra Cos: 0.2636210322380066
Inter Cos: -0.020146718248724937
Norm Quadratic Average: 2.1935949325561523
Nearest Class Center Accuracy: 0.6565

