RicoSuave

icon company Berry AI icon location Taipei icon location AI Engineer, Active Researcher, Data & Theory Enthusiast. MD in High Energy Phenomenology Physics. Experienced in Astrostatistics.

Results 2 comments of RicoSuave

Mionr bug: There is no `r_model_path` in `create_mtcnn_net()`

Also in line `bboxes = create_mtcnn_net(image, 50, device, p_model_path=weight_path, o_model_path=None)` should change to `bboxes = create_mtcnn_net(image, [50,50], device, p_model_path=weight_path, o_model_path=None)`. Since `min_lp_size` in `detect_pnet(pnet, image, min_lp_size, device)` should either tuple...

Customizing your dataset

Maybe I type the comment too quickly, the "input format" [0,38,75] actually is the **unique pixel value** of annotation file. You can find out the labelme annotation by the following...