diff options
Diffstat (limited to 'megapixels/commands/processor/face_vector.py')
| -rw-r--r-- | megapixels/commands/processor/face_vector.py | 133 |
1 files changed, 133 insertions, 0 deletions
diff --git a/megapixels/commands/processor/face_vector.py b/megapixels/commands/processor/face_vector.py new file mode 100644 index 00000000..cb155d08 --- /dev/null +++ b/megapixels/commands/processor/face_vector.py @@ -0,0 +1,133 @@ +""" +Converts ROIs to face vector +NB: the VGG Face2 extractor should be used with MTCNN ROIs (not square) + the DLIB face extractor should be used with DLIB ROIs (square) +see https://github.com/ox-vgg/vgg_face2 for TAR@FAR +""" + +import click + +from app.settings import types +from app.utils import click_utils +from app.settings import app_cfg as cfg + +@click.command() +@click.option('-o', '--output', 'opt_fp_out', default=None, + help='Override enum output filename CSV') +@click.option('-m', '--media', 'opt_dir_media', default=None, + help='Override enum media directory') +@click.option('--store', 'opt_data_store', + type=cfg.DataStoreVar, + default=click_utils.get_default(types.DataStore.HDD), + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('--dataset', 'opt_dataset', + type=cfg.DatasetVar, + required=True, + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('--size', 'opt_size', + type=(int, int), default=cfg.DEFAULT_SIZE_FACE_DETECT, + help='Output image size') +@click.option('-e', '--extractor', 'opt_extractor', + default=click_utils.get_default(types.FaceExtractor.VGG), + type=cfg.FaceExtractorVar, + help='Type of extractor framework/network to use') +@click.option('-j', '--jitters', 'opt_jitters', default=cfg.DLIB_FACEREC_JITTERS, + help='Number of jitters (only for dlib') +@click.option('-p', '--padding', 'opt_padding', default=cfg.FACEREC_PADDING, + help='Percentage ROI padding') +@click.option('--slice', 'opt_slice', type=(int, int), default=(None, None), + help='Slice list of files') +@click.option('-f', '--force', 'opt_force', is_flag=True, + help='Force overwrite file') +@click.option('-g', '--gpu', 'opt_gpu', default=0, + help='GPU index') +@click.pass_context +def cli(ctx, opt_fp_out, opt_dir_media, opt_data_store, opt_dataset, opt_size, + opt_extractor, opt_slice, opt_force, opt_gpu, opt_jitters, opt_padding): + """Converts face ROIs to vectors""" + + 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.models.bbox import BBox + from app.models.data_store import DataStore + from app.utils import logger_utils, file_utils, im_utils + from app.processors import face_extractor + + + # ------------------------------------------------- + # init here + + log = logger_utils.Logger.getLogger() + # set data_store + data_store = DataStore(opt_data_store, opt_dataset) + + # get filepath out + fp_out = data_store.metadata(types.Metadata.FACE_VECTOR) if opt_fp_out is None else opt_fp_out + if not opt_force and Path(fp_out).exists(): + log.error('File exists. Use "-f / --force" to overwite') + return + + # init face processors + if opt_extractor == types.FaceExtractor.DLIB: + log.debug('set dlib') + extractor = face_extractor.ExtractorDLIB(gpu=opt_gpu, jitters=opt_jitters) + elif opt_extractor == types.FaceExtractor.VGG: + extractor = face_extractor.ExtractorVGG() + + # load data + fp_record = data_store.metadata(types.Metadata.FILE_RECORD) + df_record = pd.read_csv(fp_record, dtype=cfg.FILE_RECORD_DTYPES).set_index('index') + fp_roi = data_store.metadata(types.Metadata.FACE_ROI) + df_roi = pd.read_csv(fp_roi).set_index('index') + + if opt_slice: + df_roi = df_roi[opt_slice[0]:opt_slice[1]] + + # ------------------------------------------------- + # process images + + df_img_groups = df_roi.groupby('record_index') + log.debug('processing {:,} groups'.format(len(df_img_groups))) + + vecs = [] + for record_index, df_img_group in tqdm(df_img_groups): + # make fp + ds_record = df_record.iloc[record_index] + fp_im = data_store.face(ds_record.subdir, ds_record.fn, ds_record.ext) + im = cv.imread(fp_im) + im = im_utils.resize(im, width=opt_size[0], height=opt_size[1]) + for roi_index, df_img in df_img_group.iterrows(): + # get bbox + x, y, w, h = df_img.x, df_img.y, df_img.w, df_img.h + dim = (ds_record.width, ds_record.height) + # get face vector + bbox = BBox.from_xywh(x, y, w, h) # norm + # compute vec + vec = extractor.extract(im, bbox) # use normalized BBox + vec_str = extractor.to_str(vec) + vec_obj = {'vec':vec_str, 'roi_index': roi_index, 'record_index':record_index} + vecs.append(vec_obj) + + # ------------------------------------------------- + # save data + + # create DataFrame and save to CSV + df = pd.DataFrame.from_dict(vecs) + df.index.name = 'index' + file_utils.mkdirs(fp_out) + df.to_csv(fp_out) + + # save script + file_utils.write_text(' '.join(sys.argv), '{}.sh'.format(fp_out))
\ No newline at end of file |