Width and Height of the images

AruniRC / detectron-self-train

A PyTorch Detectron codebase for domain adaptation of object detectors.

MIT License

118 stars 21 forks source link

Closed tqvinhcs closed 5 years ago

tqvinhcs commented 5 years ago

Hi,

I am a little bit confused about your json data converting.

bdd100k image['width'] = 720 image['height'] = 1280

Wider image['width'] = im.height image['height'] = im.width

It seems that you have swapped the height and width of the image. What does it mean here? Does it affect the training and testing of the model?

AruniRC commented 5 years ago

It should not affect the performance you report on BDD pedestrians. The face detection (WIDER/CS6) code had this bugfixed.