diff options
Diffstat (limited to 'megapixels/commands/cv')
| -rw-r--r-- | megapixels/commands/cv/_old_files_to_face_rois.py | 168 | ||||
| -rw-r--r-- | megapixels/commands/cv/cluster.py | 47 | ||||
| -rw-r--r-- | megapixels/commands/cv/crop.py | 104 | ||||
| -rw-r--r-- | megapixels/commands/cv/csv_to_faces.py | 105 | ||||
| -rw-r--r-- | megapixels/commands/cv/csv_to_faces_mt.py | 105 | ||||
| -rw-r--r-- | megapixels/commands/cv/face_frames.py | 82 | ||||
| -rw-r--r-- | megapixels/commands/cv/face_landmarks_3d.py | 96 | ||||
| -rw-r--r-- | megapixels/commands/cv/face_pose.py | 140 | ||||
| -rw-r--r-- | megapixels/commands/cv/face_roi.py | 171 | ||||
| -rw-r--r-- | megapixels/commands/cv/face_vector.py | 125 | ||||
| -rw-r--r-- | megapixels/commands/cv/mirror.py | 57 | ||||
| -rw-r--r-- | megapixels/commands/cv/resize.py | 149 | ||||
| -rw-r--r-- | megapixels/commands/cv/videos_to_frames.py | 73 |
13 files changed, 1422 insertions, 0 deletions
diff --git a/megapixels/commands/cv/_old_files_to_face_rois.py b/megapixels/commands/cv/_old_files_to_face_rois.py new file mode 100644 index 00000000..d92cbd74 --- /dev/null +++ b/megapixels/commands/cv/_old_files_to_face_rois.py @@ -0,0 +1,168 @@ +""" +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 + +color_filters = {'color': 1, 'gray': 2, 'all': 3} + +@click.command() +@click.option('-i', '--input', 'opt_fp_files', required=True, + help='Input file meta CSV') +@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('-p', '--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.option('--recursive/--no-recursive', 'opt_recursive', is_flag=True, default=False, + help='Use glob recursion (slower)') +@click.option('-f', '--force', 'opt_force', is_flag=True, + help='Force overwrite file') +@click.option('--color', 'opt_color_filter', + type=click.Choice(color_filters.keys()), default='color', + help='Filter to keep color or grayscale images (color = keep color') +@click.pass_context +def cli(ctx, opt_dirs_in, opt_fp_out, opt_ext, opt_size, opt_detector_type, + opt_gpu, opt_conf_thresh, opt_pyramids, opt_slice, opt_display, opt_recursive, opt_force, opt_color_filter): + """Converts frames with faces to CSV of ROIs""" + + 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 not opt_force and Path(opt_fp_out).exists(): + log.error('File exists. Use "-f / --force" to overwite') + return + + 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.MTCNN: + detector = face_detector.DetectorMTCNN() + elif opt_detector_type == types.FaceDetectNet.HAAR: + log.error('{} not yet implemented'.format(opt_detector_type.name)) + return + + + # ------------------------------------------------- + # process here + color_filter = color_filters[opt_color_filter] + + # get list of files to process + fp_ims = [] + for opt_dir_in in opt_dirs_in: + if opt_recursive: + fp_glob = join(opt_dir_in, '**/*.{}'.format(opt_ext)) + fp_ims += glob(fp_glob, recursive=True) + else: + fp_glob = join(opt_dir_in, '*.{}'.format(opt_ext)) + fp_ims += glob(fp_glob) + log.debug(fp_glob) + + + 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) + + # filter out color or grayscale iamges + if color_filter != color_filters['all']: + try: + is_gray = im_utils.is_grayscale(im) + if is_gray and color_filter != color_filters['gray']: + log.debug('Skipping grayscale image: {}'.format(fp_im)) + continue + except Exception as e: + log.error('Could not check grayscale: {}'.format(fp_im)) + continue + + try: + bboxes = detector.detect(im, opt_size=opt_size, opt_pyramids=opt_pyramids) + except Exception as e: + log.error('could not detect: {}'.format(fp_im)) + log.error('{}'.format(e)) + fpp_im = Path(fp_im) + subdir = str(fpp_im.parent.relative_to(opt_dir_in)) + + for bbox in bboxes: + # log.debug('is square: {}'.format(bbox.w == bbox.h)) + nw,nh = int(bbox.w * im.shape[1]), int(bbox.h * im.shape[0]) + roi = { + 'fn': fpp_im.stem, + 'ext': fpp_im.suffix.replace('.',''), + 'x': bbox.x, + 'y': bbox.y, + 'w': bbox.w, + 'h': bbox.h, + 'image_height': im.shape[0], + 'image_width': im.shape[1], + 'subdir': subdir} + bbox_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=min(1200, opt_size[0])) + for bbox in bboxes: + bbox_dim = bbox.to_dim(im_md.shape[:2][::-1]) + cv.rectangle(im_md, bbox_dim.pt_tl, bbox_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 + file_utils.mkdirs(opt_fp_out) + df = pd.DataFrame.from_dict(data) + df.to_csv(opt_fp_out, index=False)
\ No newline at end of file diff --git a/megapixels/commands/cv/cluster.py b/megapixels/commands/cv/cluster.py new file mode 100644 index 00000000..419091a0 --- /dev/null +++ b/megapixels/commands/cv/cluster.py @@ -0,0 +1,47 @@ +import click + +from app.settings import types +from app.utils import click_utils +from app.settings import app_cfg as cfg +from app.utils.logger_utils import Logger + +@click.command() +@click.option('--data_store', 'opt_data_store', + type=cfg.DataStoreVar, + default=click_utils.get_default(types.DataStore.NAS), + 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('--metadata', 'opt_metadata', required=True, + type=cfg.MetadataVar, + show_default=True, + help=click_utils.show_help(types.Metadata)) +@click.pass_context +def cli(ctx, opt_data_store, opt_dataset, opt_metadata): + """Display image info""" + + # cluster the embeddings + print("[INFO] clustering...") + clt = DBSCAN(metric="euclidean", n_jobs=args["jobs"]) + clt.fit(encodings) + + # determine the total number of unique faces found in the dataset + labelIDs = np.unique(clt.labels_) + numUniqueFaces = len(np.where(labelIDs > -1)[0]) + print("[INFO] # unique faces: {}".format(numUniqueFaces)) + # load and display image + im = cv.imread(fp_im) + cv.imshow('', im) + + 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
\ No newline at end of file diff --git a/megapixels/commands/cv/crop.py b/megapixels/commands/cv/crop.py new file mode 100644 index 00000000..778be0c4 --- /dev/null +++ b/megapixels/commands/cv/crop.py @@ -0,0 +1,104 @@ +""" +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_dir_out', required=True, + help='Output directory') +@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=(256, 256), + help='Output image size') +@click.option('-t', '--crop-type', 'opt_crop_type', + default='center', type=click.Choice(['center', 'mirror', 'face', 'person', 'none']), + help='Force fit image center location') +@click.pass_context +def cli(ctx, opt_dir_in, opt_dir_out, opt_ext, opt_size, opt_crop_type): + """Crop, mirror images""" + + import os + from os.path import join + from pathlib import Path + from glob import glob + from tqdm import tqdm + + + from app.utils import logger_utils, file_utils, im_utils + + # ------------------------------------------------- + # process here + + log = logger_utils.Logger.getLogger() + log.info('crop images') + + # get list of files to process + fp_ims = glob(join(opt_dir_in, '*.{}'.format(opt_ext))) + log.debug('files: {}'.format(len(fp_ims))) + + # ensure output dir exists + file_utils.mkdirs(opt_dir_out) + + for fp_im in tqdm(fp_ims): + im = process_crop(fp_im, opt_size, opt_crop_type) + fp_out = join(opt_dir_out, Path(fp_im).name) + im.save(fp_out) + + +def process_crop(fp_im, opt_size, crop_type): + im = Image.open(fp_im) + if crop_type == 'center': + im = crop_square_fit(im, opt_size) + elif crop_type == 'mirror': + im = mirror_crop_square(im, opt_size) + return im + +def crop_square_fit(im, size, center=(0.5, 0.5)): + return ImageOps.fit(im, size, method=Image.BICUBIC, centering=center) + +def mirror_crop_square(im, size): + # force to even dims + if im.size[0] % 2 or im.size[1] % 2: + im = ImageOps.fit(im, ((im.size[0] // 2) * 2, (im.size[1] // 2) * 2)) + + # create new square image + min_size, max_size = (min(im.size), max(im.size)) + orig_w, orig_h = im.size + margin = (max_size - min_size) // 2 + w, h = (max_size, max_size) + im_new = Image.new('RGB', (w, h), color=(0, 0, 0)) + + #crop (l, t, r, b) + if orig_w > orig_h: + # landscape, mirror expand T/B + im_top = ImageOps.mirror(im.crop((0, 0, margin, w))) + im_bot = ImageOps.mirror(im.crop((orig_h - margin, 0, orig_h, w))) + im_new.paste(im_top, (0, 0)) + im_new.paste(im, (margin, 0, orig_h + margin, w)) + im_new.paste(im_bot, (h - margin, 0)) + elif orig_h > orig_w: + # portrait, mirror expand L/R + im_left = ImageOps.mirror(im.crop((0, 0, margin, h))) + im_right = ImageOps.mirror(im.crop((orig_w - margin, 0, orig_w, h))) + im_new.paste(im_left, (0, 0)) + im_new.paste(im, (margin, 0, orig_w + margin, h)) + im_new.paste(im_right, (w - margin, 0)) + + return im_new.resize(size) + + +def center_crop_face(): + pass + +def center_crop_person(): + pass
\ No newline at end of file diff --git a/megapixels/commands/cv/csv_to_faces.py b/megapixels/commands/cv/csv_to_faces.py new file mode 100644 index 00000000..64c8b965 --- /dev/null +++ b/megapixels/commands/cv/csv_to_faces.py @@ -0,0 +1,105 @@ +""" +Reads in CSV of ROIs and extracts facial regions with padding +""" + +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('-i', '--input', 'opt_fp_in', required=True, + help='Input CSV') +@click.option('-m', '--media', 'opt_dir_media', required=True, + help='Input image/video directory') +@click.option('-o', '--output', 'opt_dir_out', required=True, + help='Output directory for extracted ROI images') +@click.option('--slice', 'opt_slice', type=(int, int), default=(None, None), + help='Slice list of files') +@click.option('--padding', 'opt_padding', default=0.25, + help='Facial padding as percentage of face width') +@click.option('--ext', 'opt_ext_out', default='png', type=click.Choice(['jpg', 'png']), + help='Output image type') +@click.option('--min', 'opt_min', default=(60, 60), + help='Minimum original face size') +@click.pass_context +def cli(ctx, opt_fp_in, opt_dir_media, opt_dir_out, opt_slice, + opt_padding, opt_ext_out, opt_min): + """Converts ROIs to images""" + + import os + from os.path import join + from pathlib import Path + from glob import glob + + from tqdm import tqdm + import numpy as np + from PIL import Image, ImageOps, ImageFilter, ImageDraw + import cv2 as cv + import pandas as pd + + from app.utils import logger_utils, file_utils, im_utils + from app.models.bbox import BBox + + # ------------------------------------------------- + # process here + log = logger_utils.Logger.getLogger() + + df_rois = pd.read_csv(opt_fp_in, dtype={'subdir': str, 'fn': str}) + if opt_slice: + df_rois = df_rois[opt_slice[0]:opt_slice[1]] + + log.info('Processing {:,} rows'.format(len(df_rois))) + + file_utils.mkdirs(opt_dir_out) + + df_rois_grouped = df_rois.groupby(['fn']) # group by fn/filename + groups = df_rois_grouped.groups + skipped = [] + + for group in tqdm(groups): + # get image + group_rows = df_rois_grouped.get_group(group) + + row = group_rows.iloc[0] + fp_im = join(opt_dir_media, str(row['subdir']), '{fn}.{ext}'.format(**row)) # TODO change to ext + try: + im = Image.open(fp_im).convert('RGB') + im.verify() + except Exception as e: + log.warn('Could not open: {}'.format(fp_im)) + log.error(e) + continue + + for idx, roi in group_rows.iterrows(): + # get bbox to im dimensions + xywh = [roi['x'], roi['y'], roi['w'] , roi['h']] + bbox = BBox.from_xywh(*xywh) + dim = im.size + bbox_dim = bbox.to_dim(dim) + # expand + opt_padding_px = int(opt_padding * bbox_dim.width) + bbox_dim_exp = bbox_dim.expand_dim(opt_padding_px, dim) + # crop + x1y2 = bbox_dim_exp.pt_tl + bbox_dim_exp.pt_br + im_crop = im.crop(box=x1y2) + + # strip exif, create new image and paste data + im_crop_data = list(im_crop.getdata()) + im_crop_no_exif = Image.new(im_crop.mode, im_crop.size) + im_crop_no_exif.putdata(im_crop_data) + + # save + idx_zpad = file_utils.zpad(idx, zeros=3) + subdir = '' if roi['subdir'] == '.' else '{}_'.format(roi['subdir']) + subdir = subdir.replace('/', '_') + fp_im_out = join(opt_dir_out, '{}{}{}.{}'.format(subdir, roi['fn'], idx_zpad, opt_ext_out)) + # threshold size and save + if im_crop_no_exif.size[0] < opt_min[0] or im_crop_no_exif.size[1] < opt_min[1]: + skipped.append(fp_im_out) + log.info('Face too small: {}, idx: {}'.format(fp_im, idx)) + else: + im_crop_no_exif.save(fp_im_out) + + log.info('Skipped {:,} images'.format(len(skipped))) diff --git a/megapixels/commands/cv/csv_to_faces_mt.py b/megapixels/commands/cv/csv_to_faces_mt.py new file mode 100644 index 00000000..64c8b965 --- /dev/null +++ b/megapixels/commands/cv/csv_to_faces_mt.py @@ -0,0 +1,105 @@ +""" +Reads in CSV of ROIs and extracts facial regions with padding +""" + +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('-i', '--input', 'opt_fp_in', required=True, + help='Input CSV') +@click.option('-m', '--media', 'opt_dir_media', required=True, + help='Input image/video directory') +@click.option('-o', '--output', 'opt_dir_out', required=True, + help='Output directory for extracted ROI images') +@click.option('--slice', 'opt_slice', type=(int, int), default=(None, None), + help='Slice list of files') +@click.option('--padding', 'opt_padding', default=0.25, + help='Facial padding as percentage of face width') +@click.option('--ext', 'opt_ext_out', default='png', type=click.Choice(['jpg', 'png']), + help='Output image type') +@click.option('--min', 'opt_min', default=(60, 60), + help='Minimum original face size') +@click.pass_context +def cli(ctx, opt_fp_in, opt_dir_media, opt_dir_out, opt_slice, + opt_padding, opt_ext_out, opt_min): + """Converts ROIs to images""" + + import os + from os.path import join + from pathlib import Path + from glob import glob + + from tqdm import tqdm + import numpy as np + from PIL import Image, ImageOps, ImageFilter, ImageDraw + import cv2 as cv + import pandas as pd + + from app.utils import logger_utils, file_utils, im_utils + from app.models.bbox import BBox + + # ------------------------------------------------- + # process here + log = logger_utils.Logger.getLogger() + + df_rois = pd.read_csv(opt_fp_in, dtype={'subdir': str, 'fn': str}) + if opt_slice: + df_rois = df_rois[opt_slice[0]:opt_slice[1]] + + log.info('Processing {:,} rows'.format(len(df_rois))) + + file_utils.mkdirs(opt_dir_out) + + df_rois_grouped = df_rois.groupby(['fn']) # group by fn/filename + groups = df_rois_grouped.groups + skipped = [] + + for group in tqdm(groups): + # get image + group_rows = df_rois_grouped.get_group(group) + + row = group_rows.iloc[0] + fp_im = join(opt_dir_media, str(row['subdir']), '{fn}.{ext}'.format(**row)) # TODO change to ext + try: + im = Image.open(fp_im).convert('RGB') + im.verify() + except Exception as e: + log.warn('Could not open: {}'.format(fp_im)) + log.error(e) + continue + + for idx, roi in group_rows.iterrows(): + # get bbox to im dimensions + xywh = [roi['x'], roi['y'], roi['w'] , roi['h']] + bbox = BBox.from_xywh(*xywh) + dim = im.size + bbox_dim = bbox.to_dim(dim) + # expand + opt_padding_px = int(opt_padding * bbox_dim.width) + bbox_dim_exp = bbox_dim.expand_dim(opt_padding_px, dim) + # crop + x1y2 = bbox_dim_exp.pt_tl + bbox_dim_exp.pt_br + im_crop = im.crop(box=x1y2) + + # strip exif, create new image and paste data + im_crop_data = list(im_crop.getdata()) + im_crop_no_exif = Image.new(im_crop.mode, im_crop.size) + im_crop_no_exif.putdata(im_crop_data) + + # save + idx_zpad = file_utils.zpad(idx, zeros=3) + subdir = '' if roi['subdir'] == '.' else '{}_'.format(roi['subdir']) + subdir = subdir.replace('/', '_') + fp_im_out = join(opt_dir_out, '{}{}{}.{}'.format(subdir, roi['fn'], idx_zpad, opt_ext_out)) + # threshold size and save + if im_crop_no_exif.size[0] < opt_min[0] or im_crop_no_exif.size[1] < opt_min[1]: + skipped.append(fp_im_out) + log.info('Face too small: {}, idx: {}'.format(fp_im, idx)) + else: + im_crop_no_exif.save(fp_im_out) + + log.info('Skipped {:,} images'.format(len(skipped))) diff --git a/megapixels/commands/cv/face_frames.py b/megapixels/commands/cv/face_frames.py new file mode 100644 index 00000000..76f23af1 --- /dev/null +++ b/megapixels/commands/cv/face_frames.py @@ -0,0 +1,82 @@ +from glob import glob +import os +from os.path import join +from pathlib import Path + +import click + + + + +@click.command() +@click.option('-i', '--input', 'opt_fp_in', required=True, + help='Input directory to glob') +@click.option('-o', '--output', 'opt_fp_out', required=True, + help='Output directory for face frames') +@click.option('--size', 'opt_size', + type=(int, int), default=(300, 300), + help='Output image size') +@click.option('--slice', 'opt_slice', type=(int, int), default=(None, None), + help='Slice list of files') +@click.pass_context +def cli(ctx, opt_fp_in, opt_fp_out, opt_size, opt_slice): + """Split video to face frames""" + + from tqdm import tqdm + import dlib + import pandas as pd + from PIL import Image, ImageOps, ImageFilter + import cv2 as cv + import numpy as np + + from app.processors import face_detector + from app.utils import logger_utils, file_utils, im_utils + from app.settings import types + from app.utils import click_utils + from app.settings import app_cfg as cfg + from app.models.bbox import BBox + + log = logger_utils.Logger.getLogger() + + # ------------------------------------------------- + # process + + detector = face_detector.DetectorDLIBCNN() + + # get file list + fp_videos = glob(join(opt_fp_in, '*.mp4')) + fp_videos += glob(join(opt_fp_in, '*.webm')) + fp_videos += glob(join(opt_fp_in, '*.mkv')) + + min_distance_per = .025 # minimum distance percentage to save new face image + face_interval = 5 + frame_interval_count = 0 + frame_count = 0 + bbox_prev = BBox(0,0,0,0) + file_utils.mkdirs(opt_fp_out) + dnn_size = opt_size + max_dim = max(dnn_size) + px_thresh = int(max_dim * min_distance_per) + + for fp_video in tqdm(fp_videos): + # load video + video = cv.VideoCapture(fp_video) + # iterate through frames + while video.isOpened(): + res, frame = video.read() + if not res: + break + # increment frames, save frame if interval has passed + frame_count += 1 # for naming + frame_interval_count += 1 # for interval + bboxes = detector.detect(frame, opt_size=dnn_size, opt_pyramids=0) + if len(bboxes) > 0 and frame_interval_count >= face_interval: + dim = frame.shape[:2][::-1] + d = bboxes[0].to_dim(dim).distance(bbox_prev) + if d > px_thresh: + # save frame + zfc = file_utils.zpad(frame_count) + fp_frame = join(opt_fp_out, '{}_{}.jpg'.format(Path(fp_video).stem, zfc)) + cv.imwrite(fp_frame, frame) + frame_interval_count = 0 + bbox_prev = bboxes[0] diff --git a/megapixels/commands/cv/face_landmarks_3d.py b/megapixels/commands/cv/face_landmarks_3d.py new file mode 100644 index 00000000..03ef8fc2 --- /dev/null +++ b/megapixels/commands/cv/face_landmarks_3d.py @@ -0,0 +1,96 @@ +""" + +""" + +import click + +from app.settings import types +from app.utils import click_utils +from app.settings import app_cfg as cfg + +color_filters = {'color': 1, 'gray': 2, 'all': 3} + +@click.command() +@click.option('-i', '--input', 'opt_dirs_in', required=True, multiple=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('-g', '--gpu', 'opt_gpu', default=0, + help='GPU index') +@click.option('--slice', 'opt_slice', type=(int, int), default=(None, None), + help='Slice list of files') +@click.option('--recursive/--no-recursive', 'opt_recursive', is_flag=True, default=False, + help='Use glob recursion (slower)') +@click.option('-f', '--force', 'opt_force', is_flag=True, + help='Force overwrite file') +@click.pass_context +def cli(ctx, opt_dirs_in, opt_fp_out, opt_ext, opt_size, opt_gpu, opt_slice, + opt_recursive, opt_force): + """Converts face imges to 3D landmarks""" + + 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 face_alignment import FaceAlignment, LandmarksType + from skimage import io + + from app.utils import logger_utils, file_utils + from app.processors import face_detector + + # ------------------------------------------------- + # init here + + + log = logger_utils.Logger.getLogger() + + if not opt_force and Path(opt_fp_out).exists(): + log.error('File exists. Use "-f / --force" to overwite') + return + + device = 'cuda' if opt_gpu > -1 else 'cpu' + fa = FaceAlignment(LandmarksType._3D, flip_input=False, device=device) + + # get list of files to process + fp_ims = [] + for opt_dir_in in opt_dirs_in: + if opt_recursive: + fp_glob = join(opt_dir_in, '**/*.{}'.format(opt_ext)) + fp_ims += glob(fp_glob, recursive=True) + else: + fp_glob = join(opt_dir_in, '*.{}'.format(opt_ext)) + fp_ims += glob(fp_glob) + log.debug(fp_glob) + + + 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): + fpp_im = Path(fp_im) + im = io.imread(fp_im) + preds = fa.get_landmarks(im) + if preds and len(preds) > 0: + data[fpp_im.name] = preds[0].tolist() + + # save date + file_utils.mkdirs(opt_fp_out) + + file_utils.write_json(data, opt_fp_out, verbose=True)
\ No newline at end of file diff --git a/megapixels/commands/cv/face_pose.py b/megapixels/commands/cv/face_pose.py new file mode 100644 index 00000000..c37d006f --- /dev/null +++ b/megapixels/commands/cv/face_pose.py @@ -0,0 +1,140 @@ +""" +Converts ROIs to pose: yaw, roll, pitch +""" + +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('-i', '--input', 'opt_fp_in', default=None, + help='Override enum input filename CSV') +@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('--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('-d', '--display', 'opt_display', is_flag=True, + help='Display image for debugging') +@click.pass_context +def cli(ctx, opt_fp_in, opt_fp_out, opt_dir_media, opt_data_store, opt_dataset, opt_size, + opt_slice, opt_force, opt_display): + """Converts ROIs to pose: roll, yaw, pitch""" + + 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.utils import logger_utils, file_utils, im_utils + from app.processors.face_landmarks import LandmarksDLIB + from app.processors.face_pose import FacePoseDLIB + from app.models.data_store import DataStore + + # ------------------------------------------------- + # 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_POSE) 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 + face_pose = FacePoseDLIB() + face_landmarks = LandmarksDLIB() + + # load filepath data + fp_record = data_store.metadata(types.Metadata.FILE_RECORD) + df_record = pd.read_csv(fp_record).set_index('index') + # load ROI data + fp_roi = data_store.metadata(types.Metadata.FACE_ROI) + df_roi = pd.read_csv(fp_roi).set_index('index') + # slice if you want + if opt_slice: + df_roi = df_roi[opt_slice[0]:opt_slice[1]] + # group by image index (speedup if multiple faces per image) + df_img_groups = df_roi.groupby('record_index') + log.debug('processing {:,} groups'.format(len(df_img_groups))) + + # store poses and convert to DataFrame + poses = [] + + # iterate + 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) + # 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] + dim = im.shape[:2][::-1] + bbox = BBox.from_xywh(x, y, w, h).to_dim(dim) + # get pose + landmarks = face_landmarks.landmarks(im, bbox) + pose_data = face_pose.pose(landmarks, dim, project_points=opt_display) + pose_degrees = pose_data['degrees'] # only keep the degrees data + + # use the project point data if display flag set + if opt_display: + pts_im = pose_data['points_image'] + pts_model = pose_data['points_model'] + pt_nose = pose_data['point_nose'] + dst = im.copy() + face_pose.draw_pose(dst, pts_im, pts_model, pt_nose) + face_pose.draw_degrees(dst, pose_degrees) + # display to cv window + cv.imshow('', dst) + 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 + + # add image index and append to result CSV data + pose_degrees['record_index'] = record_index + poses.append(pose_degrees) + + + # save date + file_utils.mkdirs(fp_out) + df = pd.DataFrame.from_dict(poses) + df.index.name = 'index' + df.to_csv(fp_out)
\ No newline at end of file diff --git a/megapixels/commands/cv/face_roi.py b/megapixels/commands/cv/face_roi.py new file mode 100644 index 00000000..a08566a8 --- /dev/null +++ b/megapixels/commands/cv/face_roi.py @@ -0,0 +1,171 @@ +""" +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 + +color_filters = {'color': 1, 'gray': 2, 'all': 3} + +@click.command() +@click.option('-i', '--input', 'opt_fp_in', default=None, + help='Override enum input filename CSV') +@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('-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('-p', '--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.option('-f', '--force', 'opt_force', is_flag=True, + help='Force overwrite file') +@click.option('--color', 'opt_color_filter', + type=click.Choice(color_filters.keys()), default='all', + help='Filter to keep color or grayscale images (color = keep color') +@click.option('--largest/--all-faces', 'opt_largest', is_flag=True, default=True, + help='Only keep largest face') +@click.pass_context +def cli(ctx, opt_fp_in, opt_dir_media, opt_fp_out, opt_data_store, opt_dataset, opt_size, opt_detector_type, + opt_gpu, opt_conf_thresh, opt_pyramids, opt_slice, opt_display, opt_force, opt_color_filter, + opt_largest): + """Converts frames with faces to CSV of ROIs""" + + 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 + from app.models.data_store import DataStore + + # ------------------------------------------------- + # 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_ROI) 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 + + # set detector + 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.MTCNN: + detector = face_detector.DetectorMTCNN() + elif opt_detector_type == types.FaceDetectNet.HAAR: + log.error('{} not yet implemented'.format(opt_detector_type.name)) + return + + + # get list of files to process + fp_in = data_store.metadata(types.Metadata.FILE_RECORD) if opt_fp_in is None else opt_fp_in + df_records = pd.read_csv(fp_in).set_index('index') + if opt_slice: + df_records = df_records[opt_slice[0]:opt_slice[1]] + log.debug('processing {:,} files'.format(len(df_records))) + + # filter out grayscale + color_filter = color_filters[opt_color_filter] + + data = [] + + for df_record in tqdm(df_records.itertuples(), total=len(df_records)): + fp_im = data_store.face(str(df_record.subdir), str(df_record.fn), str(df_record.ext)) + im = cv.imread(fp_im) + + # filter out color or grayscale iamges + if color_filter != color_filters['all']: + try: + is_gray = im_utils.is_grayscale(im) + if is_gray and color_filter != color_filters['gray']: + log.debug('Skipping grayscale image: {}'.format(fp_im)) + continue + except Exception as e: + log.error('Could not check grayscale: {}'.format(fp_im)) + continue + + try: + bboxes = detector.detect(im, size=opt_size, pyramids=opt_pyramids, largest=opt_largest) + except Exception as e: + log.error('could not detect: {}'.format(fp_im)) + log.error('{}'.format(e)) + continue + + for bbox in bboxes: + roi = { + 'record_index': int(df_record.Index), + 'x': bbox.x, + 'y': bbox.y, + 'w': bbox.w, + 'h': bbox.h, + 'image_width': im.shape[1], + 'image_height': im.shape[0]} + data.append(roi) + + # debug display + if opt_display and len(bboxes): + im_md = im_utils.resize(im, width=min(1200, opt_size[0])) + for bbox in bboxes: + bbox_dim = bbox.to_dim(im_md.shape[:2][::-1]) + log.debug(f'bbox: {bbox_dim}') + cv.rectangle(im_md, bbox_dim.pt_tl, bbox_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 + file_utils.mkdirs(fp_out) + df = pd.DataFrame.from_dict(data) + df.index.name = 'index' + df.to_csv(fp_out)
\ No newline at end of file diff --git a/megapixels/commands/cv/face_vector.py b/megapixels/commands/cv/face_vector.py new file mode 100644 index 00000000..7200d73b --- /dev/null +++ b/megapixels/commands/cv/face_vector.py @@ -0,0 +1,125 @@ +""" +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 + fp_record = data_store.metadata(types.Metadata.FILE_RECORD) + df_record = pd.read_csv(fp_record).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 here + df_img_groups = df_roi.groupby('record_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_record.loc[roi_index] # locate image meta + #ds_file = df_record.loc['index', image_index] # locate image meta + + fp_im = data_store.face(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, 'record_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 diff --git a/megapixels/commands/cv/mirror.py b/megapixels/commands/cv/mirror.py new file mode 100644 index 00000000..9ca1cac7 --- /dev/null +++ b/megapixels/commands/cv/mirror.py @@ -0,0 +1,57 @@ +""" +Crop images to prepare for training +""" + +import click +import cv2 as cv +from PIL import Image, ImageOps, ImageFilter + +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_dir_out', required=True, + help='Output directory') +@click.option('--slice', 'opt_slice', type=(int, int), default=(None, None), + help='Slice the input list') +@click.pass_context +def cli(ctx, opt_dir_in, opt_dir_out, opt_slice): + """Mirror augment image directory""" + + import os + from os.path import join + from pathlib import Path + from glob import glob + from tqdm import tqdm + + from app.utils import logger_utils, file_utils, im_utils + + # ------------------------------------------------- + # init + + log = logger_utils.Logger.getLogger() + + # ------------------------------------------------- + # process here + + # get list of files to process + fp_ims = glob(join(opt_dir_in, '*.jpg')) + fp_ims += glob(join(opt_dir_in, '*.png')) + + if opt_slice: + fp_ims = fp_ims[opt_slice[0]:opt_slice[1]] + log.info('processing {:,} files'.format(len(fp_ims))) + + # ensure output dir exists + file_utils.mkdirs(opt_dir_out) + + # resize and save images + for fp_im in tqdm(fp_ims): + im = Image.open(fp_im) + fpp_im = Path(fp_im) + fp_out = join(opt_dir_out, '{}_mirror{}'.format(fpp_im.stem, fpp_im.suffix)) + im.save(fp_out)
\ No newline at end of file diff --git a/megapixels/commands/cv/resize.py b/megapixels/commands/cv/resize.py new file mode 100644 index 00000000..dcd621b3 --- /dev/null +++ b/megapixels/commands/cv/resize.py @@ -0,0 +1,149 @@ +""" +Crop images to prepare for training +""" + +import click +import cv2 as cv +from PIL import Image, ImageOps, ImageFilter + +from app.settings import types +from app.utils import click_utils +from app.settings import app_cfg as cfg + +""" +Filter Q-Down Q-Up Speed +NEAREST ⭐⭐⭐⭐⭐ +BOX ⭐ ⭐⭐⭐⭐ +BILINEAR ⭐ ⭐ ⭐⭐⭐ +HAMMING ⭐⭐ ⭐⭐⭐ +BICUBIC ⭐⭐⭐ ⭐⭐⭐ ⭐⭐ +LANCZOS ⭐⭐⭐⭐ ⭐⭐⭐⭐ ⭐ +""" +methods = { + 'lanczos': Image.LANCZOS, + 'bicubic': Image.BICUBIC, + 'hamming': Image.HAMMING, + 'bileaner': Image.BILINEAR, + 'box': Image.BOX, + 'nearest': Image.NEAREST + } +centerings = { + 'tl': (0.0, 0.0), + 'tc': (0.5, 0.0), + 'tr': (0.0, 0.0), + 'lc': (0.0, 0.5), + 'cc': (0.5, 0.5), + 'rc': (1.0, 0.5), + 'bl': (0.0, 1.0), + 'bc': (1.0, 0.5), + 'br': (1.0, 1.0) +} + +@click.command() +@click.option('-i', '--input', 'opt_dir_in', required=True, + help='Input directory') +@click.option('-o', '--output', 'opt_dir_out', required=True, + help='Output directory') +@click.option('-e', '--ext', 'opt_glob_ext', + default='png', type=click.Choice(['jpg', 'png']), + help='File glob ext') +@click.option('--size', 'opt_size', + type=(int, int), default=(256, 256), + help='Output image size (square)') +@click.option('--method', 'opt_scale_method', + type=click.Choice(methods.keys()), + default='lanczos', + help='Scaling method to use') +@click.option('--equalize', 'opt_equalize', is_flag=True, + help='Equalize historgram') +@click.option('--sharpen', 'opt_sharpen', is_flag=True, + help='Unsharp mask') +@click.option('--center', 'opt_center', default='cc', type=click.Choice(centerings.keys()), + help='Crop focal point') +@click.option('--slice', 'opt_slice', type=(int, int), default=(None, None), + help='Slice the input list') +@click.option('-t', '--threads', 'opt_threads', default=8, + help='Number of threads') +@click.pass_context +def cli(ctx, opt_dir_in, opt_dir_out, opt_glob_ext, opt_size, opt_scale_method, + opt_equalize, opt_sharpen, opt_center, opt_slice, opt_threads): + """Crop, mirror images""" + + import os + from os.path import join + from pathlib import Path + from glob import glob + from tqdm import tqdm + from multiprocessing.dummy import Pool as ThreadPool + from functools import partial + + from app.utils import logger_utils, file_utils, im_utils + + # ------------------------------------------------- + # init + + log = logger_utils.Logger.getLogger() + + + # ------------------------------------------------- + # process here + + def pool_resize(fp_im, opt_size, scale_method, centering): + # Threaded image resize function + try: + pbar.update(1) + try: + im = Image.open(fp_im).convert('RGB') + im.verify() + except Exception as e: + log.warn('Could not open: {}'.format(fp_im)) + log.error(e) + return False + + im = ImageOps.fit(im, opt_size, method=scale_method, centering=centering) + + if opt_equalize: + im_np = im_utils.pil2np(im) + im_np_eq = eq_hist_yuv(im_np) + im_np = cv.addWeighted(im_np_eq, 0.35, im_np, 0.65, 0) + im = im_utils.np2pil(im_np) + + if opt_sharpen: + im = im.filter(ImageFilter.UnsharpMask) + + fp_out = join(opt_dir_out, Path(fp_im).name) + im.save(fp_out) + return True + except: + return False + + centering = centerings[opt_center] + scale_method = methods[opt_scale_method] + + # get list of files to process + fp_ims = glob(join(opt_dir_in, '*.{}'.format(opt_glob_ext))) + if opt_slice: + fp_ims = fp_ims[opt_slice[0]:opt_slice[1]] + log.info('processing {:,} files'.format(len(fp_ims))) + + + # ensure output dir exists + file_utils.mkdirs(opt_dir_out) + + # setup multithreading + pbar = tqdm(total=len(fp_ims)) + pool_resize = partial(pool_resize, opt_size=opt_size, scale_method=scale_method, centering=centering) + #result_list = pool.map(prod_x, data_list) + pool = ThreadPool(opt_threads) + with tqdm(total=len(fp_ims)) as pbar: + results = pool.map(pool_resize, fp_ims) + pbar.close() + + log.info('Resized: {} / {} images'.format(results.count(True), len(fp_ims))) + + + +def eq_hist_yuv(im): + im_yuv = cv.cvtColor(im, cv.COLOR_BGR2YUV) + im_yuv[:,:,0] = cv.equalizeHist(im_yuv[:,:,0]) + return cv.cvtColor(im_yuv, cv.COLOR_YUV2BGR) diff --git a/megapixels/commands/cv/videos_to_frames.py b/megapixels/commands/cv/videos_to_frames.py new file mode 100644 index 00000000..0b56c46a --- /dev/null +++ b/megapixels/commands/cv/videos_to_frames.py @@ -0,0 +1,73 @@ +from glob import glob +import os +from os.path import join +from pathlib import Path + +import click + +from app.settings import types +from app.utils import click_utils +from app.settings import app_cfg as cfg +from app.utils import logger_utils + +import dlib +import pandas as pd +from PIL import Image, ImageOps, ImageFilter +from app.utils import file_utils, im_utils + + +log = logger_utils.Logger.getLogger() + +@click.command() +@click.option('-i', '--input', 'opt_fp_in', required=True, + help='Input directory') +@click.option('-o', '--output', 'opt_fp_out', required=True, + help='Output directory') +@click.option('--size', 'opt_size', default=(320, 240), + help='Inference size for face detection' ) +@click.option('--interval', 'opt_frame_interval', default=20, + help='Number of frames before saving next face') +@click.pass_context +def cli(ctx, opt_fp_in, opt_fp_out, opt_size, opt_frame_interval): + """Converts videos to frames with faces""" + + # ------------------------------------------------- + # process + + from tqdm import tqdm + import cv2 as cv + from tqdm import tqdm + from app.processors import face_detector + + detector = face_detector.DetectorDLIBCNN() + + # get file list + fp_videos = glob(join(opt_fp_in, '*.mp4')) + fp_videos += glob(join(opt_fp_in, '*.webm')) + fp_videos += glob(join(opt_fp_in, '*.mkv')) + + frame_interval_count = 0 + frame_count = 0 + + file_utils.mkdirs(opt_fp_out) + + for fp_video in tqdm(fp_videos): + + video = cv.VideoCapture(fp_video) + + while video.isOpened(): + res, frame = video.read() + if not res: + break + + frame_count += 1 # for naming + frame_interval_count += 1 # for interval + + bboxes = detector.detect(frame, opt_size=opt_size, opt_pyramids=0) + if len(bboxes) > 0 and frame_interval_count >= opt_frame_interval: + # save frame + fname = file_utils.zpad(frame_count) + fp_frame = join(opt_fp_out, '{}_{}.jpg'.format(Path(fp_video).stem, fname)) + cv.imwrite(fp_frame, frame) + frame_interval_count = 0 + |