data_curation/build_vlpart.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

import sys
sys.path.append('.')
from VLPart.vlpart.config import add_vlpart_config

from VLPart.demo.predictor import VisualizationDemo


# constants
WINDOW_NAME = "image demo"


def setup_cfg(args):
    # load config from file and command-line arguments
    cfg = get_cfg()
    add_vlpart_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="VLPart/configs/joint/swinbase_cascade_lvis_paco_pascalpart_partimagenet.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="+",
        default='',
        help="A list of space separated input images; "
        "or a single glob pattern such as 'directory/*.jpg'",
    )
    parser.add_argument(
        "--output",
        default='',
        help="A file or directory to save output visualizations. "
        "If not given, will show output in an OpenCV window.",
    )
    parser.add_argument(
        "--vocabulary",
        default="custom",
        choices=['pascal_part', 'partimagenet', 'paco',
                 'voc', 'coco', 'lvis',
                 'pascal_part_voc', 'lvis_paco', 'custom'],
        help="",
    )
    parser.add_argument(
        "--custom_vocabulary",
        default="",
        help="",
    )
    parser.add_argument(
        "--confidence-threshold",
        type=float,
        default=0.7,
        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=['MODEL.WEIGHTS', "/data/VLPart/ckpts/swinbase_cascade_lvis_paco_pascalpart_partimagenet.pth", "VIS.BOX", False],
        nargs=argparse.REMAINDER,
    )
    return parser

def build_vlpart_model(custom_vocabulary):

    mp.set_start_method("spawn", force=True)
    args = get_parser().parse_args()
    args.custom_vocabulary = custom_vocabulary
    setup_logger(name="fvcore")
    logger = setup_logger()
    logger.info("Arguments: " + str(args))

    cfg = setup_cfg(args)
    model = VisualizationDemo(cfg, args)

    return model