diff options
Diffstat (limited to 'megapixels/commands/cv/face_vector.py')
| -rw-r--r-- | megapixels/commands/cv/face_vector.py | 46 |
1 files changed, 29 insertions, 17 deletions
diff --git a/megapixels/commands/cv/face_vector.py b/megapixels/commands/cv/face_vector.py index 4df647f5..cb155d08 100644 --- a/megapixels/commands/cv/face_vector.py +++ b/megapixels/commands/cv/face_vector.py @@ -1,5 +1,8 @@ """ 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 @@ -24,12 +27,16 @@ from app.settings import app_cfg as cfg show_default=True, help=click_utils.show_help(types.Dataset)) @click.option('--size', 'opt_size', - type=(int, int), default=(300, 300), + 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') -@click.option('-p', '--padding', 'opt_padding', default=cfg.DLIB_FACEREC_PADDING, - help='Percentage padding') + 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, @@ -38,7 +45,7 @@ from app.settings import app_cfg as cfg help='GPU index') @click.pass_context def cli(ctx, opt_fp_out, opt_dir_media, opt_data_store, opt_dataset, opt_size, - opt_slice, opt_force, opt_gpu, opt_jitters, opt_padding): + opt_extractor, opt_slice, opt_force, opt_gpu, opt_jitters, opt_padding): """Converts face ROIs to vectors""" import sys @@ -56,7 +63,7 @@ def cli(ctx, opt_fp_out, opt_dir_media, opt_data_store, opt_dataset, opt_size, 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_recognition + from app.processors import face_extractor # ------------------------------------------------- @@ -73,11 +80,15 @@ def cli(ctx, opt_fp_out, opt_dir_media, opt_data_store, opt_dataset, opt_size, return # init face processors - facerec = face_recognition.RecognitionDLIB() + 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).set_index('index') + 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') @@ -85,7 +96,8 @@ def cli(ctx, opt_fp_out, opt_dir_media, opt_data_store, opt_dataset, opt_size, df_roi = df_roi[opt_slice[0]:opt_slice[1]] # ------------------------------------------------- - # process here + # process images + df_img_groups = df_roi.groupby('record_index') log.debug('processing {:,} groups'.format(len(df_img_groups))) @@ -95,21 +107,21 @@ def cli(ctx, opt_fp_out, opt_dir_media, opt_data_store, opt_dataset, opt_size, 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) - #dim = im.shape[:2][::-1] # get face vector - bbox_dim = BBox.from_xywh(x, y, w, h).to_dim(dim) # convert to int real dimensions + bbox = BBox.from_xywh(x, y, w, h) # norm # compute vec - # padding=opt_padding not yet implemented in dlib===19.16 but merged in master - vec = facerec.vec(im, bbox_dim, jitters=opt_jitters) - vec_flat = facerec.flatten(vec) - vec_flat['roi_index'] = roi_index - vec_flat['record_index'] = record_index - vecs.append(vec_flat) + 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) |