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_0.0001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.270018577575684
Linear Weight Rank: 16
Intra Cos: 0.03299568220973015
Inter Cos: -0.006222443655133247
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: 8.222947120666504
Linear Weight Rank: 180
Intra Cos: 0.030019614845514297
Inter Cos: -0.004101425874978304
Norm Quadratic Average: 14.063628196716309
Nearest Class Center Accuracy: 0.597

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.7967259883880615
Linear Weight Rank: 4
Intra Cos: 0.04227614775300026
Inter Cos: -0.009587612934410572
Norm Quadratic Average: 14.45197582244873
Nearest Class Center Accuracy: 0.812375

Output Layer:
Intra Cos: 0.5646358728408813
Inter Cos: -0.13501550257205963
Norm Quadratic Average: 7.709492206573486
Nearest Class Center Accuracy: 0.981375

Test Set:
Average Loss: 0.6271339797973633
Accuracy: 0.767
NC1 Within Class Collapse: 5.233366012573242
NC2 Equinorm: Features: 0.11336629092693329, Weights: 0.04090263694524765
NC2 Equiangle: Features: 0.11461462577184041, Weights: 0.033297901352246605
NC3 Self-Duality: 0.5524771809577942
NC4 NCC Mismatch: 0.21899999999999997

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.270018577575684
Linear Weight Rank: 16
Intra Cos: 0.030431468039751053
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: 8.222947120666504
Linear Weight Rank: 180
Intra Cos: 0.02683998830616474
Inter Cos: -0.004083611536771059
Norm Quadratic Average: 14.070320129394531
Nearest Class Center Accuracy: 0.5995

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.7967259883880615
Linear Weight Rank: 4
Intra Cos: 0.03221656009554863
Inter Cos: -0.0059836083091795444
Norm Quadratic Average: 14.466164588928223
Nearest Class Center Accuracy: 0.714

Output Layer:
Intra Cos: 0.3649662733078003
Inter Cos: -0.06786499917507172
Norm Quadratic Average: 7.56550931930542
Nearest Class Center Accuracy: 0.76

