diff options
Diffstat (limited to 'megapixels/commands/cv/gen_face_vec.py')
| -rw-r--r-- | megapixels/commands/cv/gen_face_vec.py | 123 |
1 files changed, 123 insertions, 0 deletions
diff --git a/megapixels/commands/cv/gen_face_vec.py b/megapixels/commands/cv/gen_face_vec.py new file mode 100644 index 00000000..83e1460d --- /dev/null +++ b/megapixels/commands/cv/gen_face_vec.py @@ -0,0 +1,123 @@ +""" +Converts ROIs to face vector +""" + +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('--data_store', 'opt_data_store', + type=cfg.DataStoreVar, + default=click_utils.get_default(types.DataStore.SSD), + 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=(300, 300), + help='Output image size') +@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') +@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_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_recognition + + + # ------------------------------------------------- + # 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 + facerec = face_recognition.RecognitionDLIB() + + # load data + df_file = pd.read_csv(data_store.metadata(types.Metadata.FILEPATH)).set_index('index') + df_roi = pd.read_csv(data_store.metadata(types.Metadata.FACE_ROI)).set_index('index') + + if opt_slice: + df_roi = df_roi[opt_slice[0]:opt_slice[1]] + + # ------------------------------------------------- + # process here + df_img_groups = df_roi.groupby('image_index') + log.debug('processing {:,} groups'.format(len(df_img_groups))) + + vecs = [] + + for image_index, df_img_group in tqdm(df_img_groups): + # make fp + roi_index = df_img_group.index.values[0] + log.debug(f'roi_index: {roi_index}, image_index: {image_index}') + ds_file = df_file.loc[roi_index] # locate image meta + #ds_file = df_file.loc['index', image_index] # locate image meta + + fp_im = data_store.face_image(str(ds_file.subdir), str(ds_file.fn), str(ds_file.ext)) + im = cv.imread(fp_im) + # get bbox + x = df_img_group.x.values[0] + y = df_img_group.y.values[0] + w = df_img_group.w.values[0] + h = df_img_group.h.values[0] + imw = df_img_group.image_width.values[0] + imh = df_img_group.image_height.values[0] + dim = im.shape[:2][::-1] + # get face vector + dim = (imw, imh) + bbox_dim = BBox.from_xywh(x, y, w, h).to_dim(dim) # convert to int real dimensions + # compute vec + # padding=opt_padding not yet implemented in 19.16 but merged in master + vec = facerec.vec(im, bbox_dim, jitters=opt_jitters) + vec_str = ','.join([repr(x) for x in vec]) # convert to string for CSV + vecs.append( {'roi_index': roi_index, 'image_index': image_index, 'vec': vec_str}) + + + # save date + df = pd.DataFrame.from_dict(vecs) + df.index.name = 'index' + #file_utils.mkdirs(fp_out) + #df.to_csv(fp_out)
\ No newline at end of file |