search

cfotache / pytorch_objectdetecttrack

Object detection in images, and tracking across video frames
483 stars 253 forks source link

Modifications for running yolov3-tiny #2

Open BibratRanjan opened 5 years ago

BibratRanjan commented 5 years ago

What kind of modifications are required in the code to run "tiny yolov3" for object detection, apart from using different config file and weights ?

I'am getting the following error

File "/pytorch_objectdetecttrack/models.py", line 129, in forward prediction = x.view(nB, nA, self.bbox_attrs, nG, nG).permute(0, 1, 3, 4, 2).contiguous()

RuntimeError: shape '[1, 3, 85, 12, 12]' is invalid for input of size 39780

Thanks

XABxab123 commented 5 years ago

me too

XABxab123 commented 5 years ago

@cfotache

ngingihy commented 5 years ago

Me as well @cfotache

kd4293accio commented 5 years ago

@XAB745220zt @BibratRanjan @ngingihy has anyone solved this issue? please let me know

Chiaquan commented 5 years ago

@XAB745220zt @ngingihy @kd4293accio @cfotache has anyone solved this issue? please let me know

joelorentz commented 4 years ago

I had the same problem and found that it has been solved in newer versions of the Pytorch Yolo implementation used in this repo. To get this working you can simply clone this repo and add the missing files (e.g. objectracker.py, config/coco.names).

ajaykumaar commented 4 years ago

Hii @joelorentz , I used the weights and cfg of yolov3-tiny from the githup repo you have mentioned, yet i run into the same error. Has the issue been resolved?

ttaehyung commented 3 years ago

working on yolov4-tiny, has anyone can resolve this? please share