我正在关注detectron2 入门教程，以使用他们的机器学习模型之一检测图像中的对象。我正在使用 AWS 机器学习 AMI 和 jupyter 笔记本来执行此操作。该模型成功检测到图像中的对象，但 openCV 似乎无法正常工作，因为我没有在控制台中获得输出。我得到的错误是无法连接到 X 服务器。
Reading a file from 'Detectron2 Model Zoo'
[07/12 20:03:32 detectron2]: input1.jpg: detected 1 instances in 0.45s :
cannot connect to X server /home/ubuntu/anaconda3/lib/python3.7/multiprocessing/semaphore_tracker.py:144: UserWarning: semaphore_tracker: There appear to be 1 leaked semaphores to clean up at shutdown len(cache)) ubuntu@ip-10-0-0-225:~/detectron2/detectron2/demo$
这是我用来运行模型的命令：
python demo.py --config-file ../configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml \
--input input1.jpg input2.jpg \
--opts MODEL.WEIGHTS detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl
这是 demo.py 文件：
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
import argparse
import glob
import multiprocessing as mp
import os
import time
import cv2
import tqdm
from detectron2.config import get_cfg
from detectron2.data.detection_utils import read_image
from detectron2.utils.logger import setup_logger
from predictor import VisualizationDemo
# constants
WINDOW_NAME = "COCO detections"
def setup_cfg(args):
# load config from file and command-line arguments
cfg = get_cfg()
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
# Set score_threshold for builtin models
cfg.MODEL.RETINANET.SCORE_THRESH_TEST = args.confidence_threshold
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = args.confidence_threshold
cfg.MODEL.PANOPTIC_FPN.COMBINE.INSTANCES_CONFIDENCE_THRESH = args.confidence_threshold
cfg.freeze()
return cfg
def get_parser():
parser = argparse.ArgumentParser(description="Detectron2 demo for builtin models")
parser.add_argument(
"--config-file",
default="configs/quick_schedules/mask_rcnn_R_50_FPN_inference_acc_test.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument("--webcam", action="store_true", help="Take inputs from webcam.")
parser.add_argument("--video-input", help="Path to video file.")
parser.add_argument(
"--input",
nargs="+",
help="A list of space separated input images; "
"or a single glob pattern such as 'directory/*.jpg'",
)
parser.add_argument(
"--output",
help="A file or directory to save output visualizations. "
"If not given, will show output in an OpenCV window.",
)
parser.add_argument(
"--confidence-threshold",
type=float,
default=0.5,
help="Minimum score for instance predictions to be shown",
)
parser.add_argument(
"--opts",
help="Modify config options using the command-line 'KEY VALUE' pairs",
default=[],
nargs=argparse.REMAINDER,
)
return parser
if __name__ == "__main__":
mp.set_start_method("spawn", force=True)
args = get_parser().parse_args()
setup_logger(name="fvcore")
logger = setup_logger()
logger.info("Arguments: " + str(args))
cfg = setup_cfg(args)
demo = VisualizationDemo(cfg)
if args.input:
if len(args.input) == 1:
args.input = glob.glob(os.path.expanduser(args.input[0]))
assert args.input, "The input path(s) was not found"
for path in tqdm.tqdm(args.input, disable=not args.output):
# use PIL, to be consistent with evaluation
img = read_image(path, format="BGR")
start_time = time.time()
predictions, visualized_output = demo.run_on_image(img)
logger.info(
"{}: {} in {:.2f}s".format(
path,
"detected {} instances".format(len(predictions["instances"]))
if "instances" in predictions
else "finished",
time.time() - start_time,
)
)
if args.output:
if os.path.isdir(args.output):
assert os.path.isdir(args.output), args.output
out_filename = os.path.join(args.output, os.path.basename(path))
else:
assert len(args.input) == 1, "Please specify a directory with args.output"
out_filename = args.output
visualized_output.save(out_filename)
else:
cv2.namedWindow(WINDOW_NAME, cv2.WINDOW_NORMAL)
cv2.imshow(WINDOW_NAME, visualized_output.get_image()[:, :, ::-1])
if cv2.waitKey(0) == 27:
break # esc to quit