search

facebookresearch / deepcluster

Deep Clustering for Unsupervised Learning of Visual Features
Other
1.69k stars 325 forks source link

Does the dimension of PCA dimensionality reduction after extracting features have an effect on the results? #50

Closed junjianli106 closed 5 years ago

junjianli106 commented 5 years ago

Does the dimension of PCA dimensionality reduction after extracting features have an effect on the results?

mathildecaron31 commented 5 years ago

Hi, you can explore this by running deepcluster training with different dimension for the features. My intuition is that it doesn't have a big impact as long as you use enough dimension to retain most of the variance.

junjianli106 commented 5 years ago

Hi, you can explore this by running deepcluster training with different dimension for the features. My intuition is that it doesn't have a big impact as long as you use enough dimension to retain most of the variance.

Thank you for your reply