SuperK
SuperK
have a look with "Joint Cascade Face Detection and Alignment"
I change test_real_A from [1, 256,256 ,3] to [1,533,800,3] , which input image'size is 533*800.
https://www.dropbox.com/sh/vves0ghwvxzpmby/AAC9HqJL0cqBUcrtqLWchooya?dl=0 Here it is.
I have fix it up, It's my mistake. Because I have changed the ratio of the trained images data.
The eval command is almost same with the inference as I have tried it and get a return result like : INFO:tensorflow:epoch/eval number 266878 | Avg_Hit@1: 0.902 | Avg_PERR: 0.795...
I haven't met that problem , it's all right for me to inference or evaluate.
I want to use it in searching similarity videos.
Thank you for that! I will have a try.
@feiyun1265 @antoine77340 I have also met this question and solve it. I'm working on it , and now I have finished a complete function with a video as input and...
@feiyun1265 the shape is not matched ,just expand it to the recommend shape.