about MEAD data process

[Shirley-0708]

Thank you for this great work!

I downloaded a part of the dataset of mead and followed the data processing method of readme, modified the file path of input, and output, and set detect landmark to true in order, but I got this error.

I located VideoFaceDetectionDataset here, self.index_for_frame_map are all 0, resulting in detectionin frame_index always 0, so there is an error reading the next frame. But I don't know how to fix it. Is there something wrong with my steps？ More details are below.

[radekd91]

Not all of the stages can be run at the same time. I added a clarification and a more detailed manual to the README. Please give it a shot. :-)

https://github.com/radekd91/inferno/tree/master/inferno_apps/TalkingHead/data_processing

[juheon-hwang]

in inferno/inferno/datasets/VideoFaceDetectionDataset.py just change the variable named self.vid_read in line 48 to self.vid_read = vid_read or 'skvread'

[gpfworld]

Not all of the stages can be run at the same time. I added a clarification and a more detailed manual to the README. Please give it a shot. :-)

https://github.com/radekd91/inferno/tree/master/inferno_apps/TalkingHead/data_processing

The issue doesn't seem to lie with the execution order as I've strictly adhered to it. I've come across the exact same problem while working with the MEAD dataset. Could you please look into whether there's a flaw in the code logic, and advise on how to rectify it?

[gpfworld]

in inferno/inferno/datasets/VideoFaceDetectionDataset.py just change the variable named self.vid_read in line 48 to self.vid_read = vid_read or 'skvread'

From what I see, the current code follows this logic. The error seems to be thrown at line 115, not 86, so the issue might not be here.