unable to detect objects
patricxu opened this issue · comments
patricxu commented
I use the following code to do segmentation but all it output is a "bottle"
import pixellib
from pixellib.torchbackend.instance import instanceSegmentation
ins = instanceSegmentation()
ins.load_model("pointrend_resnet50.pkl")
target_classes = ins.select_target_classes(person = True)
ins.segmentImage("image.jpg", show_bboxes=True, segment_target_classes = target_classes, output_image_name="output_image.jpg")
I got the model from PointRend
even no objects got segmented on some input images.
The following message is the output from my terminal
ayoolaolafenwa commented
@patricxu Are you sure that this is the output image it produced? I tested the same image and I got the desired result. What pytorch version are you using?
patricxu commented
thanks! I upgraded torch to 1.9 then fix the issue