xiaozhi2015 comments

Results 16 comments of


                                            xiaozhi2015

Conv Details

After fixing this bug, have you obtained the result same as the original author's [https://github.com/sniklaus/sepconv-slomo](url) ? I just got the blur result in this project.

when complier the sepcon，occur the following error？

@chenwu-mc Have you solved the blur problem finally?

Does it currently support upsample_bilinear?

How did you convert it successfully? By replacing upsample_bilinear with ConvTranspose2d? @Brave731

can't download data

Have you found any other way to download MSR-VTT? @wu-shuqi

How to convert other imgs through the parameters we get from one img inferring?

How to match the value of parameters from user_study_ui to "tif_debug.pkl" file? @yuanming-hu Looking forward to a reply.

Unable to run dvector_create.py, file does not start with RIFF id

Make a transformation using SPHFile

IndexError occurs when generation

@ZJUhjx How did you turn Chinese dataset to the format same as wikibio. And did you successfully apply this project to Chinese dataset?

DeepSORT ONLY

Have you solved it bro ? @EddieEduardo

DeepSORT ONLY

I had solved it, bro. @EddieEduardo Replace bbox_xywh with your own bbox.

i change detector ,use FCOS instead of YOlO, The effect of pedestrian detection is good, i want to Detect a frame to track 10 frames,it seem some trouble,can you show your code for real time processing

You can set interval with para "frame_interval" in yolo3_deepsort.py. @Zzzcg About "Detecting a frame to track 10 frames", if you detect every frame, then why do we need to track,...