Detectron2快速开始

图像分割任务

demo.py

# Copyright (c) Facebook, Inc. and its affiliates.
import argparse
import glob
import multiprocessing as mp
import numpy as np
import os
import tempfile
import time
import warnings
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()
    # To use demo for Panoptic-DeepLab, please uncomment the following two lines.
    # from detectron2.projects.panoptic_deeplab import add_panoptic_deeplab_config  # noqa
    # add_panoptic_deeplab_config(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 configs")
    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


def test_opencv_video_format(codec, file_ext):
    with tempfile.TemporaryDirectory(prefix="video_format_test") as dir:
        filename = os.path.join(dir, "test_file" + file_ext)
        writer = cv2.VideoWriter(
            filename=filename,
            fourcc=cv2.VideoWriter_fourcc(*codec),
            fps=float(30),
            frameSize=(10, 10),
            isColor=True,
        )
        [writer.write(np.zeros((10, 10, 3), np.uint8)) for _ in range(30)]
        writer.release()
        if os.path.isfile(filename):
            return True
        return False
from PIL import Image
def readimage(file):
    try:
        data = np.fromfile(file, dtype=np.uint8)  #先用numpy把图片文件存入内存：data，把图片数据看做是纯字节数据
        image = cv2.imdecode(data, cv2.IMREAD_COLOR) [:,:,::-1] #从内存数据读入图片
    except:
        image = np.array(Image.open(file))#读取数据
    return image
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")
            img=readimage(path)
            start_time = time.time()
            predictions, visualized_output = demo.run_on_image(img)
            # import torch
            # .to(torch.device('cpu'))sem_seg
            # print(predictions['panoptic_seg'])
            # print(predictions['sem_seg'][0].cpu().numpy())
            # print(predictions["sem_seg"].shape)
            # data=predictions["sem_seg"].argmax(dim=0).cpu().numpy()
            # print(data)
            import matplotlib.pyplot as plt
            import numpy as np
            # data=np.load(r"E:\work\空间舒适度分析\五大新城街道品质\outfile\image\perdictfile\奉贤新城_luwangsample_hebing\121.451603354069_30.91853061151274.npy")
            # plt.imshow(data,'jet',alpha=0.5)
            # plt.show()
            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
    elif args.webcam:
        assert args.input is None, "Cannot have both --input and --webcam!"
        assert args.output is None, "output not yet supported with --webcam!"
        cam = cv2.VideoCapture(0)
        for vis in tqdm.tqdm(demo.run_on_video(cam)):
            cv2.namedWindow(WINDOW_NAME, cv2.WINDOW_NORMAL)
            cv2.imshow(WINDOW_NAME, vis)
            if cv2.waitKey(1) == 27:
                break  # esc to quit
        cam.release()
        cv2.destroyAllWindows()
    elif args.video_input:
        video = cv2.VideoCapture(args.video_input)
        width = int(video.get(cv2.CAP_PROP_FRAME_WIDTH))
        height = int(video.get(cv2.CAP_PROP_FRAME_HEIGHT))
        frames_per_second = video.get(cv2.CAP_PROP_FPS)
        num_frames = int(video.get(cv2.CAP_PROP_FRAME_COUNT))
        basename = os.path.basename(args.video_input)
        codec, file_ext = (
            ("x264", ".mkv") if test_opencv_video_format("x264", ".mkv") else ("mp4v", ".mp4")
        )
        if codec == ".mp4v":
            warnings.warn("x264 codec not available, switching to mp4v")
        if args.output:
            if os.path.isdir(args.output):
                output_fname = os.path.join(args.output, basename)
                output_fname = os.path.splitext(output_fname)[0] + file_ext
            else:
                output_fname = args.output
            assert not os.path.isfile(output_fname), output_fname
            output_file = cv2.VideoWriter(
                filename=output_fname,
                # some installation of opencv may not support x264 (due to its license),
                # you can try other format (e.g. MPEG)
                fourcc=cv2.VideoWriter_fourcc(*codec),
                fps=float(frames_per_second),
                frameSize=(width, height),
                isColor=True,
            )
        assert os.path.isfile(args.video_input)
        for vis_frame in tqdm.tqdm(demo.run_on_video(video), total=num_frames):
            if args.output:
                output_file.write(vis_frame)
            else:
                cv2.namedWindow(basename, cv2.WINDOW_NORMAL)
                cv2.imshow(basename, vis_frame)
                if cv2.waitKey(1) == 27:
                    break  # esc to quit
        video.release()
        if args.output:
            output_file.release()
        else:
            cv2.destroyAllWindows()

import torch

print(torch.cuda.is_available(),torch.__version__)

import detectron2
# Some basic setup:
# Setup detectron2 logger
import detectron2
from detectron2.utils.logger import setup_logger
setup_logger()

# import some common libraries
import numpy as np
import os, json, cv2, random
# from google.colab.patches import cv2_imshow

# import some common detectron2 utilities
from detectron2 import model_zoo
from detectron2.engine import DefaultPredictor
from detectron2.config import get_cfg
from detectron2.utils.visualizer import Visualizer
from detectron2.data import MetadataCatalog, DatasetCatalog

import os
basedir=''

inputfile1=f"images/*.png"
outfile1=r"out/"
cmd1=f'cd {basedir}\detectron2-main\demo'
cmd3=f"python demo.py --config-file {configfile} --input {inputfile1}  --confidence-threshold 0.6 --output {outfile1} --opts MODEL.WEIGHTS detectron2://COCO-PanopticSegmentation/panoptic_fpn_R_101_3x/139514519/model_final_cafdb1.pkl"
os.system(cmd1+'&'+cmd3)