Oliver

icon indicating an email [email protected]

icon location Espoo, Finland icon location PhD in Robotics and Machine Learning. CTO @ Coachless.

Results 2 issues of Oliver

Hard coded resolution in video.py and detect.py lead to wrong bounding boxes

Hi, first of all thanks for the great tutorial! I think in video.py, line 134 and detect.py, lin 164: ` scaling_factor = torch.min(416/im_dim,1)[0].view(-1,1)` is using a hard coded value for...

Style Transfer Model Returns Wrong Dimensions when a (1920x1080x3) form a full HD webcam is passed through it.

When using a full HD webcam in the style transfer demo, the program crashes when filling the returned image into frame_style. Frame style is 1920x1080 (same resolution as the webcam...