Test the custom dataset trained weights ".pth" on the test video.

[VAIBHAVPATEL97]

Hello.
I am new to the detectron 2 and need some help. I have trained the Detectron 2 COCO object detection model and have saved the weights (.pth files) to the output folder. Now, I would like to use these saved weights to test some images. How can I do that?. I tried to edit the testing code but not working, Thanks.

Note: I have registered the dataset with only the train folder there is no validation folder.

import os, cv2
from detectron2.engine import DefaultPredictor
from detectron2.config import get_cfg
from detectron2.utils.visualizer import Visualizer
from detectron2.utils.visualizer import ColorMode
from detectron2.data import MetadataCatalog
os.environ['DISPLAY'] = ':0'

cfg = get_cfg()
cfg.merge_from_file("/home/uavproject/Desktop/detectron2/configs/COCO-Detection/faster_rcnn_R_101_FPN_3x.yaml")
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.5  # set threshold for this model
cfg.MODEL.WEIGHTS = ("/home/uavproject/Desktop/yolov5/datasets/compDataset/images/output/model_0294999.pth")

img_path="/home/uavproject/Desktop/cover.jpg"

im = cv2.imread(img_path)
predictor = DefaultPredictor(cfg)
outputs = predictor(im)

""" print(outputs["instances"].pred_classes)
print(outputs["instances"].pred_boxes)
print(outputs["instances"].pred_masks) """

v = Visualizer(im[:, :, ::-1], MetadataCatalog.get(cfg.DATASETS.TRAIN[0]), scale=0.2, instance_mode=ColorMode.IMAGE)
out = v.draw_instance_predictions(outputs["instances"].to("cpu"))

cv2.imshow('show solar', out.get_image()[:, :, ::-1])
cv2.waitKey(0)
cv2.imwrite('/home/uavproject/Desktop/cover.jpg', out.get_image()[:, :, ::-1])   
cv2.destroyAllWindows()```