I have a need: to determine whether the profile file uploaded by a user is a face photo. At present, I intend to do this: collect hundreds of face photos as one category, and hundreds of any pictures as another category, and then predict_proba returns the estimated value. If the probability of face exceeds 0.8, it passes, otherwise it fails. Excuse me, is this feasible? Is there a better way?
Previous: How to ReFactor the Design and improve the Extensibility of the Code
Next: Centos7,svn can access remote access locally and report an error
the source of the problem: now both in the book and online are to divide a bunch of data sets with known prediction results into test sets and training sets, and then look at the accuracy between the prediction results and the real value, and report wha...