diff options
Diffstat (limited to 'megapixels/datasets/commands/face.py')
| -rw-r--r-- | megapixels/datasets/commands/face.py | 117 |
1 files changed, 117 insertions, 0 deletions
diff --git a/megapixels/datasets/commands/face.py b/megapixels/datasets/commands/face.py new file mode 100644 index 00000000..6b7b18b7 --- /dev/null +++ b/megapixels/datasets/commands/face.py @@ -0,0 +1,117 @@ +""" +Crop images to prepare for training +""" + +import click +# from PIL import Image, ImageOps, ImageFilter, ImageDraw + +from app.settings import types +from app.utils import click_utils +from app.settings import app_cfg as cfg + +@click.command() +@click.option('-i', '--input', 'opt_dir_in', required=True, + help='Input directory') +@click.option('-o', '--output', 'opt_fp_out', required=True, + help='Output CSV') +@click.option('-e', '--ext', 'opt_ext', + default='jpg', type=click.Choice(['jpg', 'png']), + help='File glob ext') +@click.option('--size', 'opt_size', + type=(int, int), default=(300, 300), + help='Output image size') +@click.option('-t', '--detector-type', 'opt_detector_type', + type=cfg.FaceDetectNetVar, + default=click_utils.get_default(types.FaceDetectNet.DLIB_CNN), + help=click_utils.show_help(types.FaceDetectNet)) +@click.option('-g', '--gpu', 'opt_gpu', default=0, + help='GPU index') +@click.option('--conf', 'opt_conf_thresh', default=0.85, type=click.FloatRange(0,1), + help='Confidence minimum threshold') +@click.option('--pyramids', 'opt_pyramids', default=0, type=click.IntRange(0,4), + help='Number pyramids to upscale for DLIB detectors') +@click.option('--slice', 'opt_slice', type=(int, int), default=(None, None), + help='Slice list of files') +@click.option('--display/--no-display', 'opt_display', is_flag=True, default=False, + help='Display detections to debug') +@click.pass_context +def cli(ctx, opt_dir_in, opt_fp_out, opt_ext, opt_size, opt_detector_type, + opt_gpu, opt_conf_thresh, opt_pyramids, opt_slice, opt_display): + """Extrace face""" + + import sys + import os + from os.path import join + from pathlib import Path + from glob import glob + from tqdm import tqdm + import numpy as np + import dlib # must keep a local reference for dlib + import cv2 as cv + import pandas as pd + + from app.utils import logger_utils, file_utils, im_utils + from app.processors import face_detector + + # ------------------------------------------------- + # init here + + log = logger_utils.Logger.getLogger() + + if opt_detector_type == types.FaceDetectNet.CVDNN: + detector = face_detector.DetectorCVDNN() + elif opt_detector_type == types.FaceDetectNet.DLIB_CNN: + detector = face_detector.DetectorDLIBCNN(opt_gpu) + elif opt_detector_type == types.FaceDetectNet.DLIB_HOG: + detector = face_detector.DetectorDLIBHOG() + elif opt_detector_type == types.FaceDetectNet.HAAR: + log.error('{} not yet implemented'.format(opt_detector_type.name)) + return + + + # ------------------------------------------------- + # process here + + # get list of files to process + fp_ims = glob(join(opt_dir_in, '*.{}'.format(opt_ext))) + if opt_slice: + fp_ims = fp_ims[opt_slice[0]:opt_slice[1]] + log.debug('processing {:,} files'.format(len(fp_ims))) + + + data = [] + + for fp_im in tqdm(fp_ims): + im = cv.imread(fp_im) + bboxes = detector.detect(im, opt_size=opt_size, opt_pyramids=opt_pyramids) + fpp_im = Path(fp_im) + for bbox in bboxes: + roi = { + 'fn': fpp_im.stem, + 'ext': fpp_im.suffix, + 'x': bbox.x, + 'y': bbox.y, + 'w': bbox.w, + 'h': bbox.h} + dim = bbox.to_dim(im.shape[:2][::-1]) # w,h + data.append(roi) + + # debug display + if opt_display and len(bboxes): + im_md = im_utils.resize(im, width=opt_size[0]) + for bbox in bboxes: + dim = bbox.to_dim(im_md.shape[:2][::-1]) + cv.rectangle(im_md, dim.pt_tl, dim.pt_br, (0,255,0), 3) + cv.imshow('', im_md) + while True: + k = cv.waitKey(1) & 0xFF + if k == 27 or k == ord('q'): # ESC + cv.destroyAllWindows() + sys.exit() + elif k != 255: + # any key to continue + break + + # save date + df = pd.DataFrame.from_dict(data) + df.to_csv(opt_fp_out)
\ No newline at end of file |