diff options
Diffstat (limited to 'megapixels/commands')
| -rw-r--r-- | megapixels/commands/cv/face_attributes.py | 136 | ||||
| -rw-r--r-- | megapixels/commands/cv/face_landmark_2d_68.py | 4 | ||||
| -rw-r--r-- | megapixels/commands/cv/face_pose.py | 11 | ||||
| -rw-r--r-- | megapixels/commands/cv/face_roi.py | 67 | ||||
| -rw-r--r-- | megapixels/commands/cv/face_vector.py | 46 | ||||
| -rw-r--r-- | megapixels/commands/cv/resize.py | 13 | ||||
| -rw-r--r-- | megapixels/commands/cv/resize_dataset.py | 149 | ||||
| -rw-r--r-- | megapixels/commands/datasets/file_record.py | 40 | ||||
| -rw-r--r-- | megapixels/commands/demo/face_3ddfa.py | 85 | ||||
| -rw-r--r-- | megapixels/commands/demo/face_age_gender.py | 31 | ||||
| -rw-r--r-- | megapixels/commands/demo/face_beauty.py | 12 | ||||
| -rw-r--r-- | megapixels/commands/demo/face_detect.py (renamed from megapixels/commands/demo/face_detection.py) | 57 | ||||
| -rw-r--r-- | megapixels/commands/demo/face_landmarks_2d.py | 155 | ||||
| -rw-r--r-- | megapixels/commands/demo/face_landmarks_3d.py | 82 | ||||
| -rw-r--r-- | megapixels/commands/demo/face_pose.py | 25 | ||||
| -rw-r--r-- | megapixels/commands/demo/face_search.py | 49 | ||||
| -rw-r--r-- | megapixels/commands/demo/face_vector.py | 28 |
17 files changed, 559 insertions, 431 deletions
diff --git a/megapixels/commands/cv/face_attributes.py b/megapixels/commands/cv/face_attributes.py new file mode 100644 index 00000000..01fe3bd1 --- /dev/null +++ b/megapixels/commands/cv/face_attributes.py @@ -0,0 +1,136 @@ +""" + +""" + +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('--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='Processing size for detection') +@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): + """Creates 2D 68-point 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 cv2 as cv + import pandas as pd + + from app.utils import logger_utils, file_utils, im_utils, display_utils, draw_utils + from app.processors import face_age_gender + from app.models.data_store import DataStore + from app.models.bbox import BBox + + # ------------------------------------------------------------------------- + # init here + + log = logger_utils.Logger.getLogger() + # init face processors + age_estimator_apnt = face_age_gender.FaceAgeApparent() + age_estimator_real = face_age_gender.FaceAgeReal() + gender_estimator = face_age_gender.FaceGender() + + # init filepaths + data_store = DataStore(opt_data_store, opt_dataset) + # set file output path + metadata_type = types.Metadata.FACE_ATTRIBUTES + fp_out = data_store.metadata(metadata_type) 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 + + # ------------------------------------------------------------------------- + # load filepath 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') + # 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 landmarks in list + results = [] + + # ------------------------------------------------------------------------- + # iterate groups with file/record index as key + + for record_index, df_img_group in tqdm(df_img_groups): + + # access file_record DataSeries + file_record = df_record.iloc[record_index] + + # load image + fp_im = data_store.face(file_record.subdir, file_record.fn, file_record.ext) + im = cv.imread(fp_im) + im_resized = im_utils.resize(im, width=opt_size[0], height=opt_size[1]) + dim = im_resized.shape[:2][::-1] + + # iterate ROIs in this image + for roi_index, df_img in df_img_group.iterrows(): + + # find landmarks + bbox_norm = BBox.from_xywh(df_img.x, df_img.y, df_img.w, df_img.h) + bbox_dim = bbox_norm.to_dim(dim) + + age_apnt = age_estimator_apnt.predict(im_resized, bbox_norm) + age_real = age_estimator_real.predict(im_resized, bbox_norm) + gender = gender_estimator.predict(im_resized, bbox_norm) + + attr_obj = { + 'age_real':float(f'{age_real:.2f}'), + 'age_apparent': float(f'{age_apnt:.2f}'), + 'm': float(f'{gender["m"]:.4f}'), + 'f': float(f'{gender["f"]:.4f}'), + 'roi_index': roi_index + } + results.append(attr_obj) + + + # create DataFrame and save to CSV + file_utils.mkdirs(fp_out) + df = pd.DataFrame.from_dict(results) + df.index.name = 'index' + df.to_csv(fp_out) + + # save script + file_utils.write_text(' '.join(sys.argv), '{}.sh'.format(fp_out))
\ No newline at end of file diff --git a/megapixels/commands/cv/face_landmark_2d_68.py b/megapixels/commands/cv/face_landmark_2d_68.py index e24d4b60..c6978a40 100644 --- a/megapixels/commands/cv/face_landmark_2d_68.py +++ b/megapixels/commands/cv/face_landmark_2d_68.py @@ -126,7 +126,7 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_dir_media, opt_data_store, opt_dataset, bbox = BBox.from_xywh(x, y, w, h).to_dim(dim) points = landmark_detector.landmarks(im_resized, bbox) points_norm = landmark_detector.normalize(points, dim) - points_flat = landmark_detector.flatten(points_norm) + points_str = landmark_detector.to_str(points_norm) # display if optioned if opt_display: @@ -137,7 +137,7 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_dir_media, opt_data_store, opt_dataset, display_utils.handle_keyboard() # add to results for CSV - results.append(points_flat) + results.append({'vec': points_str, 'roi_index':roi_index}) # create DataFrame and save to CSV diff --git a/megapixels/commands/cv/face_pose.py b/megapixels/commands/cv/face_pose.py index 70ea1f30..cb7ec56c 100644 --- a/megapixels/commands/cv/face_pose.py +++ b/megapixels/commands/cv/face_pose.py @@ -92,7 +92,7 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_dir_media, opt_data_store, opt_dataset, # 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') # load ROI data fp_roi = data_store.metadata(types.Metadata.FACE_ROI) df_roi = pd.read_csv(fp_roi).set_index('index') @@ -125,10 +125,11 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_dir_media, opt_data_store, opt_dataset, x, y, w, h = df_img.x, df_img.y, df_img.w, df_img.h #dim = (file_record.width, file_record.height) dim = im_resized.shape[:2][::-1] - bbox = BBox.from_xywh(x, y, w, h).to_dim(dim) + bbox_norm = BBox.from_xywh(x, y, w, h) + bbox_dim = bbox_norm.to_dim(dim) # get pose - landmarks = face_landmarks.landmarks(im_resized, bbox) + landmarks = face_landmarks.landmarks(im_resized, bbox_norm) pose_data = face_pose.pose(landmarks, dim) #pose_degrees = pose_data['degrees'] # only keep the degrees data #pose_degrees['points_nose'] = pose_data @@ -143,8 +144,8 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_dir_media, opt_data_store, opt_dataset, # add image index and append to result CSV data pose_data['roi_index'] = roi_index for k, v in pose_data['points'].items(): - pose_data[f'point_{k}_x'] = v[0][0] / dim[0] - pose_data[f'point_{k}_y'] = v[0][1] / dim[1] + pose_data[f'point_{k}_x'] = v[0] / dim[0] + pose_data[f'point_{k}_y'] = v[1] / dim[1] # rearrange data structure for DataFrame pose_data.pop('points') diff --git a/megapixels/commands/cv/face_roi.py b/megapixels/commands/cv/face_roi.py index 70fff401..e83b0f61 100644 --- a/megapixels/commands/cv/face_roi.py +++ b/megapixels/commands/cv/face_roi.py @@ -33,7 +33,7 @@ color_filters = {'color': 1, 'gray': 2, 'all': 3} help='Output image size') @click.option('-d', '--detector', 'opt_detector_type', type=cfg.FaceDetectNetVar, - default=click_utils.get_default(types.FaceDetectNet.DLIB_CNN), + default=click_utils.get_default(types.FaceDetectNet.CVDNN), help=click_utils.show_help(types.FaceDetectNet)) @click.option('-g', '--gpu', 'opt_gpu', default=0, help='GPU index') @@ -97,31 +97,37 @@ def cli(ctx, opt_fp_in, opt_dir_media, opt_fp_out, opt_data_store, opt_dataset, detector = face_detector.DetectorDLIBCNN(gpu=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(gpu=opt_gpu) + elif opt_detector_type == types.FaceDetectNet.MTCNN_TF: + detector = face_detector.DetectorMTCNN_TF(gpu=opt_gpu) 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') + fp_record = data_store.metadata(types.Metadata.FILE_RECORD) if opt_fp_in is None else opt_fp_in + df_record = pd.read_csv(fp_record, dtype=cfg.FILE_RECORD_DTYPES).set_index('index') if opt_slice: - df_records = df_records[opt_slice[0]:opt_slice[1]] - log.debug('processing {:,} files'.format(len(df_records))) + df_record = df_record[opt_slice[0]:opt_slice[1]] + log.debug('processing {:,} files'.format(len(df_record))) # filter out grayscale color_filter = color_filters[opt_color_filter] # set largest flag, to keep all or only largest - opt_largest = opt_largest == 'largest' + opt_largest = (opt_largest == 'largest') data = [] + skipped_files = [] + processed_files = [] - for df_record in tqdm(df_records.itertuples(), total=len(df_records)): + for df_record in tqdm(df_record.itertuples(), total=len(df_record)): fp_im = data_store.face(str(df_record.subdir), str(df_record.fn), str(df_record.ext)) - im = cv.imread(fp_im) - im_resized = im_utils.resize(im, width=opt_size[0], height=opt_size[1]) + try: + im = cv.imread(fp_im) + im_resized = im_utils.resize(im, width=opt_size[0], height=opt_size[1]) + except Exception as e: + log.debug(f'could not read: {fp_im}') + return # filter out color or grayscale iamges if color_filter != color_filters['all']: try: @@ -134,31 +140,38 @@ def cli(ctx, opt_fp_in, opt_dir_media, opt_fp_out, opt_data_store, opt_dataset, continue try: - bboxes = detector.detect(im_resized, pyramids=opt_pyramids, largest=opt_largest, + bboxes_norm = detector.detect(im_resized, pyramids=opt_pyramids, largest=opt_largest, zone=opt_zone, conf_thresh=opt_conf_thresh) 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 - } - data.append(roi) - if len(bboxes) == 0: + if len(bboxes_norm) == 0: + skipped_files.append(fp_im) log.warn(f'no faces in: {fp_im}') - + log.warn(f'skipped: {len(skipped_files)}. found:{len(processed_files)} files') + else: + processed_files.append(fp_im) + for bbox in bboxes_norm: + roi = { + 'record_index': int(df_record.Index), + 'x': bbox.x, + 'y': bbox.y, + 'w': bbox.w, + 'h': bbox.h + } + data.append(roi) + # if display optined - if opt_display and len(bboxes): + if opt_display and len(bboxes_norm): # draw each box - for bbox in bboxes: - bbox_dim = bbox.to_dim(im_resized.shape[:2][::-1]) - draw_utils.draw_bbox(im_resized, bbox_dim) + for bbox_norm in bboxes_norm: + dim = im_resized.shape[:2][::-1] + bbox_dim = bbox.to_dim(dim) + if dim[0] > 1000: + im_resized = im_utils.resize(im_resized, width=1000) + im_resized = draw_utils.draw_bbox(im_resized, bbox_norm) # display and wait cv.imshow('', im_resized) 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) diff --git a/megapixels/commands/cv/resize.py b/megapixels/commands/cv/resize.py index dcd621b3..7409ee6f 100644 --- a/megapixels/commands/cv/resize.py +++ b/megapixels/commands/cv/resize.py @@ -49,7 +49,7 @@ centerings = { help='File glob ext') @click.option('--size', 'opt_size', type=(int, int), default=(256, 256), - help='Output image size (square)') + help='Max output size') @click.option('--method', 'opt_scale_method', type=click.Choice(methods.keys()), default='lanczos', @@ -88,7 +88,7 @@ def cli(ctx, opt_dir_in, opt_dir_out, opt_glob_ext, opt_size, opt_scale_method, # ------------------------------------------------- # process here - def pool_resize(fp_im, opt_size, scale_method, centering): + def pool_resize(fp_im, opt_size, scale_method): # Threaded image resize function try: pbar.update(1) @@ -100,7 +100,7 @@ def cli(ctx, opt_dir_in, opt_dir_out, opt_glob_ext, opt_size, opt_scale_method, log.error(e) return False - im = ImageOps.fit(im, opt_size, method=scale_method, centering=centering) + #im = ImageOps.fit(im, opt_size, method=scale_method, centering=centering) if opt_equalize: im_np = im_utils.pil2np(im) @@ -117,8 +117,8 @@ def cli(ctx, opt_dir_in, opt_dir_out, opt_glob_ext, opt_size, opt_scale_method, except: return False - centering = centerings[opt_center] - scale_method = methods[opt_scale_method] + #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))) @@ -132,7 +132,8 @@ def cli(ctx, opt_dir_in, opt_dir_out, opt_glob_ext, opt_size, opt_scale_method, # setup multithreading pbar = tqdm(total=len(fp_ims)) - pool_resize = partial(pool_resize, opt_size=opt_size, scale_method=scale_method, centering=centering) + #pool_resize = partial(pool_resize, opt_size=opt_size, scale_method=scale_method, centering=centering) + pool_resize = partial(pool_resize, opt_size=opt_size) #result_list = pool.map(prod_x, data_list) pool = ThreadPool(opt_threads) with tqdm(total=len(fp_ims)) as pbar: diff --git a/megapixels/commands/cv/resize_dataset.py b/megapixels/commands/cv/resize_dataset.py new file mode 100644 index 00000000..3a6ec15f --- /dev/null +++ b/megapixels/commands/cv/resize_dataset.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 + +cv_resize_algos = { + 'area': cv.INTER_AREA, + 'lanco': cv.INTER_LANCZOS4, + 'linear': cv.INTER_LINEAR, + 'linear_exact': cv.INTER_LINEAR_EXACT, + 'nearest': cv.INTER_NEAREST +} +""" +Filter Q-Down Q-Up Speed +NEAREST ⭐⭐⭐⭐⭐ +BOX ⭐ ⭐⭐⭐⭐ +BILINEAR ⭐ ⭐ ⭐⭐⭐ +HAMMING ⭐⭐ ⭐⭐⭐ +BICUBIC ⭐⭐⭐ ⭐⭐⭐ ⭐⭐ +LANCZOS ⭐⭐⭐⭐ ⭐⭐⭐⭐ ⭐ +""" +pil_resize_algos = { + 'antialias': Image.ANTIALIAS, + 'lanczos': Image.LANCZOS, + 'bicubic': Image.BICUBIC, + 'hamming': Image.HAMMING, + 'bileaner': Image.BILINEAR, + 'box': Image.BOX, + 'nearest': Image.NEAREST + } + +@click.command() +@click.option('--dataset', 'opt_dataset', + type=cfg.DatasetVar, + required=True, + show_default=True, + help=click_utils.show_help(types.Dataset)) +@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('-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 max (w,h)') +@click.option('--interp', 'opt_interp_algo', + type=click.Choice(pil_resize_algos.keys()), + default='bicubic', + help='Interpolation resizing algorithms') +@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.option('--recursive/--no-recursive', 'opt_recursive', is_flag=True, default=False, + help='Use glob recursion (slower)') +@click.pass_context +def cli(ctx, opt_dataset, opt_data_store, opt_dir_out, opt_glob_ext, opt_size, opt_interp_algo, + opt_slice, opt_threads, opt_recursive): + """Resize dataset 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 + import pandas as pd + import numpy as np + + from app.utils import logger_utils, file_utils, im_utils + from app.models.data_store import DataStore + + # ------------------------------------------------- + # init + + log = logger_utils.Logger.getLogger() + + + # ------------------------------------------------- + # process here + + def pool_resize(fp_in, dir_in, dir_out, im_size, interp_algo): + # Threaded image resize function + pbar.update(1) + try: + im = Image.open(fp_in).convert('RGB') + im.verify() # throws error if image is corrupt + im.thumbnail(im_size, interp_algo) + fp_out = fp_in.replace(dir_in, dir_out) + file_utils.mkdirs(fp_out) + im.save(fp_out, quality=100) + except Exception as e: + log.warn(f'Could not open: {fp_in}, Error: {e}') + return False + return True + + + data_store = DataStore(opt_data_store, opt_dataset) + fp_records = data_store.metadata(types.Metadata.FILE_RECORD) + df_records = pd.read_csv(fp_records, dtype=cfg.FILE_RECORD_DTYPES).set_index('index') + dir_in = data_store.media_images_original() + + # get list of files to process + #fp_ims = file_utils.glob_multi(opt_dir_in, ['jpg', 'png'], recursive=opt_recursive) + fp_ims = [] + for ds_record in df_records.itertuples(): + fp_im = data_store.face(ds_record.subdir, ds_record.fn, ds_record.ext) + fp_ims.append(fp_im) + + if opt_slice: + fp_ims = fp_ims[opt_slice[0]:opt_slice[1]] + if not fp_ims: + log.error('No images. Try with "--recursive"') + return + log.info(f'processing {len(fp_ims):,} images') + + # algorithm to use for resizing + interp_algo = pil_resize_algos[opt_interp_algo] + log.info(f'using {interp_algo} for interpoloation') + + # ensure output dir exists + file_utils.mkdirs(opt_dir_out) + + # setup multithreading + pbar = tqdm(total=len(fp_ims)) + # fixed arguments for pool function + map_pool_resize = partial(pool_resize, dir_in=dir_in, dir_out=opt_dir_out, im_size=opt_size, interp_algo=interp_algo) + #result_list = pool.map(prod_x, data_list) # simple + pool = ThreadPool(opt_threads) + # start multithreading + with tqdm(total=len(fp_ims)) as pbar: + results = pool.map(map_pool_resize, fp_ims) + # end multithreading + pbar.close() + + log.info(f'Resized: {results.count(True)} / {len(fp_ims)} images')
\ No newline at end of file diff --git a/megapixels/commands/datasets/file_record.py b/megapixels/commands/datasets/file_record.py index d3f790d4..41a5df28 100644 --- a/megapixels/commands/datasets/file_record.py +++ b/megapixels/commands/datasets/file_record.py @@ -45,9 +45,11 @@ identity_sources = ['subdir', 'numeric'] help='Identity source key') @click.option('--recursive/--no-recursive', 'opt_recursive', is_flag=True, default=False, help='Use glob recursion (slower)') +@click.option('--max-depth', 'opt_max_depth', default=None, type=int, + help='Max number of images per subdirectory') @click.pass_context def cli(ctx, opt_fp_in, opt_fp_out, opt_dataset, opt_data_store, opt_dir_media, opt_slice, opt_threads, - opt_identity, opt_force, opt_recursive): + opt_identity, opt_force, opt_recursive, opt_max_depth): """Generates sha256, uuid, and identity index CSV file""" import sys, os @@ -59,6 +61,7 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_dataset, opt_data_store, opt_dir_media, import random import uuid + from PIL import Image import cv2 as cv import pandas as pd from tqdm import tqdm @@ -84,6 +87,26 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_dataset, opt_data_store, opt_dir_media, fp_in = opt_fp_in if opt_fp_in is not None else data_store.media_images_original() log.info(f'Globbing {fp_in}') fp_ims = file_utils.glob_multi(fp_in, ['jpg', 'png'], recursive=opt_recursive) + + log.info('Found {:,} images'.format(len(fp_ims))) + subdir_groups = {} + if opt_max_depth: + log.debug(f'using max depth: {opt_max_depth}') + for fp_im in fp_ims: + fpp_im = Path(fp_im) + + subdir = fp_im.split('/')[-2] + if not subdir in subdir_groups.keys(): + subdir_groups[subdir] = [] + else: + subdir_groups[subdir].append(fp_im) + # for each subgroup, limit number of files + fp_ims = [] + for subdir_name, items in subdir_groups.items(): + ims = items[0:opt_max_depth] + fp_ims += ims + + log.debug(f'num subdirs: {len(subdir_groups.keys())}') # fail if none if not fp_ims: log.error('No images. Try with "--recursive"') @@ -93,7 +116,6 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_dataset, opt_data_store, opt_dir_media, fp_ims = fp_ims[opt_slice[0]:opt_slice[1]] log.info('Found {:,} images'.format(len(fp_ims))) - # ---------------------------------------------------------------- # multithread process into SHA256 @@ -101,7 +123,14 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_dataset, opt_data_store, opt_dir_media, def pool_mapper(fp_im): pbar.update(1) - sha256 = file_utils.sha256(fp_im) + try: + sha256 = file_utils.sha256(fp_im) + im = Image.open(fp_im) + im.verify() # throws error if bad file + assert(im.size[0] > 60 and im.size[1] > 60) + except Exception as e: + log.warn(f'skipping file: {fp_im}') + return None im = cv.imread(fp_im) w, h = im.shape[:2][::-1] file_size_kb = os.stat(fp_im).st_size // 1000 @@ -128,10 +157,11 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_dataset, opt_data_store, opt_dir_media, data = [] indentity_count = 0 for pool_map, fp_im in zip(pool_maps, fp_ims): + if pool_map is None: + log.warn(f'skipping file: {fp_im}') + continue # skip error files fpp_im = Path(fp_im) subdir = str(fpp_im.parent.relative_to(fp_in)) - #subdir = '' if subdir is '.' else subdir - log.debug(subdir) if opt_identity: subdirs = subdir.split('/') diff --git a/megapixels/commands/demo/face_3ddfa.py b/megapixels/commands/demo/face_3ddfa.py index 6182aeb6..90359159 100644 --- a/megapixels/commands/demo/face_3ddfa.py +++ b/megapixels/commands/demo/face_3ddfa.py @@ -1,7 +1,7 @@ ''' Combines 3D face mode + rendering -https://github.com/cleardusk/3DDFA -https://github.com/YadiraF/face3d +https://github.com/cleardusk/3DDFA --> 3d landmarks +https://github.com/YadiraF/face3d --> render 3D with lighting as 2.5d image ''' import click @@ -13,8 +13,8 @@ from app.settings import app_cfg as cfg @click.command() @click.option('-i', '--input', 'opt_fp_in', default=None, required=True, help='Image filepath') -@click.option('-o', '--output', 'opt_fp_out', default=None, - help='GIF output path') +@click.option('-o', '--output', 'opt_dir_out', default=None, + help='Directory for output files') @click.option('--size', 'opt_size', type=(int, int), default=(300, 300), help='Output image size') @@ -27,11 +27,13 @@ from app.settings import app_cfg as cfg @click.option('--size', 'opt_render_dim', type=(int, int), default=(512, 512), help='2.5D render image size') -@click.option('--display/--no-display', 'opt_display', is_flag=True, default=False, +@click.option('--display/--no-display', 'opt_display', is_flag=True, default=True, help='Display detections to debug') +@click.option('--save/--no-save', 'opt_save', is_flag=True, default=True, + help='Save output images/files') @click.pass_context -def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_bbox_init, - opt_size, opt_render_dim, opt_force, opt_display): +def cli(ctx, opt_fp_in, opt_dir_out, opt_gpu, opt_bbox_init, + opt_size, opt_render_dim, opt_force, opt_display, opt_save): """3D face demo""" import sys @@ -58,6 +60,7 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_bbox_init, import scipy.io as sio sys.path.append(join(Path.cwd().parent, '3rdparty')) + # git clone https://github.com/cleardusk/3DDFA 3rdparty/d3ddfa # change name of 3DDFA to d3DDFA because can't start with number from d3DDFA import mobilenet_v1 from d3DDFA.utils.ddfa import ToTensorGjz, NormalizeGjz, str2bool @@ -70,7 +73,7 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_bbox_init, from d3DDFA.utils.render import get_depths_image, cget_depths_image, cpncc from d3DDFA.utils import paf as d3dfa_paf_utils - # https://github.com/YadiraF/face3d + # git clone https://github.com/YadiraF/face3d 3rdparty/face3d # compile cython module in face3d/mesh/cython/ python setup.py build_ext -i from face3d.face3d import mesh as face3d_mesh @@ -82,13 +85,11 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_bbox_init, fpp_in = Path(opt_fp_in) im = cv.imread(opt_fp_in) - #im = im_utils.resize(im_orig, width=opt_size[0], height=opt_size[1]) - # im = im_orig.copy() # ---------------------------------------------------------------------------- # detect face - face_detector = face_detector.DetectorDLIBCNN(gpu=opt_gpu) # -1 for CPU + face_detector = face_detector.DetectorCVDNN() # -1 for CPU bboxes = face_detector.detect(im, largest=True) bbox = bboxes[0] dim = im.shape[:2][::-1] @@ -165,7 +166,6 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_bbox_init, # dense face 3d vertices vertices = d3dfa_utils.predict_dense(param, roi_box) vertices_lst.append(vertices) - log.info(f'generated 3d data in: {(time.time() - st):.2f}s') # filepath helper function @@ -183,28 +183,20 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_bbox_init, sio.savemat(fp_mat_3df, {'vertices': vertices, 'colors': colors, 'triangles': triangles}) # save PAF - #fp_paf = to_fp(fpp_in, 'jpg', suffix='paf') - #opt_paf_size = 3 # PAF feature kernel size - #im_paf = d3dfa_paf_utils.gen_img_paf(img_crop=im_crop, param=param, kernel_size=opt_paf_size) - #cv.imwrite(fp_paf, im_paf) + im_paf = d3dfa_paf_utils.gen_img_paf(img_crop=im_crop, param=param, kernel_size=3) # save pose image # P, pose = parse_pose(param) # Camera matrix (without scale), and pose (yaw, pitch, roll, to verify) - img_pose = draw_utils.plot_pose_box(im, Ps, pts_res) - fp_pose = to_fp(fpp_in, 'jpg', suffix='pose') - cv.imwrite(fp_pose, img_pose) + im_pose = draw_utils.plot_pose_box(im, Ps, pts_res) # save depth image - fp_depth = to_fp(fpp_in, 'png', suffix='depth') # depths_img = get_depths_image(im, vertices_lst, tri-1) # python version im_depth = cget_depths_image(im, vertices_lst, triangles - 1) # cython version - cv.imwrite(fp_depth, im_depth) # save pncc image - fp_pose = to_fp(fpp_in, 'png', suffix='pncc') pncc_feature = cpncc(im, vertices_lst, triangles - 1) # cython version - cv.imwrite(fp_pose, pncc_feature[:, :, ::-1]) # cv.imwrite will swap RGB -> BGR + im_pncc = pncc_feature[:, :, ::-1] # swap BGR # save .ply #fp_ply = to_fp(fpp_in, 'ply') @@ -228,8 +220,6 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_bbox_init, # save obj colors = d3dfa_utils.get_colors(im, vertices_orig) - fp_obj = to_fp(fpp_in, 'obj') - write_obj_with_colors(fp_obj, vertices_orig, triangles, colors) #fp_landmarks = to_fp(fpp_in, 'jpg', suffix='3DDFA') # show_flg? @@ -276,30 +266,39 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_bbox_init, vertices_proj = face3d_mesh.transform.orthographic_project(vertices_cam) # ------------------------------------------------------------------------- - # render 2D image + # render 2D images w = h = max(opt_render_dim) vertices_im = face3d_mesh.transform.to_image(vertices_proj, h, w) - rendering = face3d_mesh.render.render_colors(vertices_im, triangles, colors_lit, h, w) - - cv.imshow('', rendering) - display_utils.handle_keyboard() + im_render = face3d_mesh.render.render_colors(vertices_im, triangles, colors_lit, h, w) + im_render = (255* im_render).astype(np.uint8) + im_pncc = im_pncc.astype(np.uint8) + im_depth = im_depth.astype(np.uint8) + im_paf = im_paf.astype(np.uint8) # ---------------------------------------------------------------------------- # save - if opt_fp_out: - # save pose only - fpp_out = Path(opt_fp_out) + if opt_save: + fpp_out = Path(opt_dir_out) if opt_dir_out is not None else Path(opt_fp_in).parent + fpp_in = Path(opt_fp_in) + fp_out = join(fpp_out, f'{fpp_in.stem}_render.png') + cv.imwrite(fp_out, im_render) + + fp_out = join(fpp_out, f'{fpp_in.stem}_pose.png') + cv.imwrite(fp_out, im_pose) - fp_out = join(fpp_out.parent, f'{fpp_out.stem}_real{fpp_out.suffix}') - cv.imwrite(fp_out, im_age_real) + fp_out = join(fpp_out, f'{fpp_in.stem}_depth.png') + cv.imwrite(fp_out, im_depth) + + fp_out = join(fpp_out, f'{fpp_in.stem}_pncc.png') + cv.imwrite(fp_out, im_pncc) - fp_out = join(fpp_out.parent, f'{fpp_out.stem}_apparent{fpp_out.suffix}') - cv.imwrite(fp_out, im_age_apparent) + fp_out = join(fpp_out, f'{fpp_in.stem}_paf.png') + cv.imwrite(fp_out, im_paf) - fp_out = join(fpp_out.parent, f'{fpp_out.stem}_gender{fpp_out.suffix}') - cv.imwrite(fp_out, im_age_apparent) + fp_out = join(fpp_out, f'{fpp_in.stem}.obj') + write_obj_with_colors(fp_out, vertices_orig, triangles, colors) # ---------------------------------------------------------------------------- @@ -307,8 +306,10 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_bbox_init, if opt_display: # show all images here - cv.imshow('real', im_age_real) - cv.imshow('apparent', im_age_apparent) - cv.imshow('gender', im_gender) + cv.imshow('3d', im_render) + cv.imshow('depth', im_depth) + cv.imshow('pncc', im_pncc) + cv.imshow('pose', im_pose) + cv.imshow('paf', im_paf) display_utils.handle_keyboard() diff --git a/megapixels/commands/demo/face_age_gender.py b/megapixels/commands/demo/face_age_gender.py index c74f1e45..c4f09c13 100644 --- a/megapixels/commands/demo/face_age_gender.py +++ b/megapixels/commands/demo/face_age_gender.py @@ -17,7 +17,7 @@ from app.settings import app_cfg as cfg help='GPU index') @click.option('-f', '--force', 'opt_force', is_flag=True, help='Force overwrite file') -@click.option('--display/--no-display', 'opt_display', is_flag=True, default=False, +@click.option('--display/--no-display', 'opt_display', is_flag=True, default=True, help='Display detections to debug') @click.pass_context def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_size, opt_force, opt_display): @@ -52,12 +52,12 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_size, opt_force, opt_display): # ---------------------------------------------------------------------------- # detect face - face_detector = face_detector.DetectorDLIBCNN(gpu=opt_gpu) # -1 for CPU + face_detector = face_detector.DetectorCVDNN() bboxes = face_detector.detect(im_resized, largest=True) - bbox = bboxes[0] + bbox_norm = bboxes[0] dim = im_resized.shape[:2][::-1] - bbox_dim = bbox.to_dim(dim) - if not bbox: + bbox_dim = bbox_norm.to_dim(dim) + if not bbox_norm: log.error('no face detected') return else: @@ -70,21 +70,24 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_size, opt_force, opt_display): # real age_real_predictor = face_age_gender.FaceAgeReal() st = time.time() - age_real = age_real_predictor.predict(im_resized, bbox_dim) + age_real = age_real_predictor.predict(im_resized, bbox_norm) log.info(f'age real took: {(time.time()-st)/1000:.5f}s') # apparent age_apparent_predictor = face_age_gender.FaceAgeApparent() st = time.time() - age_apparent = age_apparent_predictor.predict(im_resized, bbox_dim) + age_apparent = age_apparent_predictor.predict(im_resized, bbox_norm) log.info(f'age apparent took: {(time.time()-st)/1000:.5f}s') # gender gender_predictor = face_age_gender.FaceGender() st = time.time() - gender = gender_predictor.predict(im_resized, bbox_dim) + gender = gender_predictor.predict(im_resized, bbox_norm) log.info(f'gender took: {(time.time()-st)/1000:.5f}s') + # ethnicity + # TODO + # ---------------------------------------------------------------------------- # output @@ -99,21 +102,21 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_size, opt_force, opt_display): # draw real age im_age_real = im_resized.copy() - draw_utils.draw_bbox(im_age_real, bbox_dim) + im_age_real = draw_utils.draw_bbox(im_age_real, bbox_norm) txt = f'{(age_real):.2f}' - draw_utils.draw_text(im_age_real, bbox_dim.pt_tl, txt) + im_age_real = draw_utils.draw_text(im_age_real, bbox_norm.pt_tl, txt) # apparent age im_age_apparent = im_resized.copy() - draw_utils.draw_bbox(im_age_apparent, bbox_dim) + im_age_apparent = draw_utils.draw_bbox(im_age_apparent, bbox_norm) txt = f'{(age_apparent):.2f}' - draw_utils.draw_text(im_age_apparent, bbox_dim.pt_tl, txt) + im_age_apparent = draw_utils.draw_text(im_age_apparent, bbox_norm.pt_tl, txt) # gender im_gender = im_resized.copy() - draw_utils.draw_bbox(im_age_apparent, bbox_dim) + im_gender = draw_utils.draw_bbox(im_gender, bbox_norm) txt = f"M: {gender['m']:.2f}, F: {gender['f']:.2f}" - draw_utils.draw_text(im_gender, (10, dim[1]-20), txt) + im_gender = draw_utils.draw_text(im_gender, (.1, .9), txt) # ---------------------------------------------------------------------------- diff --git a/megapixels/commands/demo/face_beauty.py b/megapixels/commands/demo/face_beauty.py index d31c5cee..45643c61 100644 --- a/megapixels/commands/demo/face_beauty.py +++ b/megapixels/commands/demo/face_beauty.py @@ -66,10 +66,10 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_size, opt_force, opt_display): face_detector = face_detector.DetectorDLIBCNN(gpu=opt_gpu) # -1 for CPU bboxes = face_detector.detect(im_resized, largest=True) - bbox = bboxes[0] + bbox_norm = bboxes[0] dim = im_resized.shape[:2][::-1] - bbox_dim = bbox.to_dim(dim) - if not bbox: + bbox_dim = bbox_norm.to_dim(dim) + if not bbox_norm: log.error('no face detected') return else: @@ -78,7 +78,7 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_size, opt_force, opt_display): # ---------------------------------------------------------------------------- # beauty - beauty_score = beauty_predictor.beauty(im_resized, bbox_dim) + beauty_score = beauty_predictor.beauty(im_resized, bbox_norm) # ---------------------------------------------------------------------------- @@ -93,9 +93,9 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_size, opt_force, opt_display): # draw 2d landmarks im_beauty = im_resized.copy() - draw_utils.draw_bbox(im_beauty, bbox_dim) + im_beauty = draw_utils.draw_bbox(im_beauty, bbox_dim) txt = f'Beauty score: {(100*beauty_score):.2f}' - draw_utils.draw_text(im_beauty, bbox_dim.pt_tl, txt) + im_beauty = draw_utils.draw_text(im_beauty, bbox_dim.pt_tl, txt) # ---------------------------------------------------------------------------- diff --git a/megapixels/commands/demo/face_detection.py b/megapixels/commands/demo/face_detect.py index 488cc80d..b92db7cb 100644 --- a/megapixels/commands/demo/face_detection.py +++ b/megapixels/commands/demo/face_detect.py @@ -59,68 +59,27 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_size, opt_force, opt_display): # ---------------------------------------------------------------------------- # detect face - face_detector = face_detector.DetectorDLIBCNN(gpu=opt_gpu) # -1 for CPU + face_detector = face_detector.DetectorCVDNN() bboxes = face_detector.detect(im_resized, largest=True) - bbox = bboxes[0] - dim = im_resized.shape[:2][::-1] - bbox_dim = bbox.to_dim(dim) - if not bbox: + if not bboxes: log.error('no face detected') return - - - # ---------------------------------------------------------------------------- - # generate 68 point landmarks using dlib - - from app.processors import face_landmarks - landmark_detector_2d_68 = face_landmarks.Dlib2D_68() - points_2d_68 = landmark_detector_2d_68.landmarks(im_resized, bbox_dim) - - - # ---------------------------------------------------------------------------- - # generate pose from 68 point 2D landmarks - - from app.processors import face_pose - pose_detector = face_pose.FacePoseDLIB() - pose_data = pose_detector.pose(points_2d_68, dim) - - # ---------------------------------------------------------------------------- - # output - - log.info(f'Face coords: {bbox_dim} face') - log.info(f'pitch: {pose_data["pitch"]}, roll: {pose_data["roll"]}, yaw: {pose_data["yaw"]}') + bbox_norm = bboxes[0] + dim = im_resized.shape[:2][::-1] + bbox_dim = bbox_norm.to_dim(dim) # ---------------------------------------------------------------------------- # draw - # draw 2d landmarks - im_landmarks_2d_68 = im_resized.copy() - draw_utils.draw_landmarks2D(im_landmarks_2d_68, points_2d_68) - draw_utils.draw_bbox(im_landmarks_2d_68, bbox_dim) - - # draw pose - im_pose = im_resized.copy() - draw_utils.draw_pose(im_pose, pose_data['point_nose'], pose_data['points']) - draw_utils.draw_degrees(im_pose, pose_data) - - - # ---------------------------------------------------------------------------- - # save - - if opt_fp_out: - # save pose only - cv.imwrite(opt_fp_out, im_pose) - + im_face = im_resized.copy() + im_face = draw_utils.draw_bbox(im_face, bbox_norm) # ---------------------------------------------------------------------------- # display if opt_display: - # show all images here - cv.imshow('Original', im_resized) - cv.imshow('2D 68PT Landmarks', im_landmarks_2d_68) - cv.imshow('Pose', im_pose) + cv.imshow('Face', im_face) display_utils.handle_keyboard()
\ No newline at end of file diff --git a/megapixels/commands/demo/face_landmarks_2d.py b/megapixels/commands/demo/face_landmarks_2d.py index 22e09297..145a12a6 100644 --- a/megapixels/commands/demo/face_landmarks_2d.py +++ b/megapixels/commands/demo/face_landmarks_2d.py @@ -3,7 +3,6 @@ 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 @@ -13,26 +12,14 @@ from app.settings import app_cfg as cfg @click.command() @click.option('-i', '--input', 'opt_fp_in', default=None, required=True, help='Image filepath') -@click.option('-o', '--output', 'opt_fp_out', default=None, - help='GIF output path') @click.option('--size', 'opt_size', type=(int, int), default=(300, 300), help='Output image size') -@click.option('--gif-size', 'opt_gif_size', - type=(int, int), default=(480, 480), - help='GIF output size') -@click.option('--gif-frames', 'opt_gif_frames', default=15, - help='GIF frames') -@click.option('-g', '--gpu', 'opt_gpu', default=0, - help='GPU index') -@click.option('-f', '--force', 'opt_force', is_flag=True, - help='Force overwrite file') -@click.option('--display/--no-display', 'opt_display', is_flag=True, default=False, +@click.option('--display/--no-display', 'opt_display', is_flag=True, default=True, help='Display detections to debug') @click.pass_context -def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_gif_frames, - opt_size, opt_gif_size, opt_force, opt_display): - """Generates 3D landmark animations from CSV files""" +def cli(ctx, opt_fp_in, opt_size, opt_display): + """2D 68-point landmarks""" import sys import os @@ -52,12 +39,6 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_gif_frames, from app.utils import plot_utils from app.processors import face_detector, face_landmarks from app.models.data_store import DataStore - - # TOOD add selective testing - opt_run_pose = True - opt_run_2d_68 = True - opt_run_3d_68 = True - opt_run_3d_68 = True # ------------------------------------------------- @@ -66,7 +47,6 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_gif_frames, log = logger_utils.Logger.getLogger() - # load image im = cv.imread(opt_fp_in) im_resized = im_utils.resize(im, width=opt_size[0], height=opt_size[1]) @@ -74,146 +54,41 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_gif_frames, # ---------------------------------------------------------------------------- # detect face - face_detector = face_detector.DetectorDLIBCNN(gpu=opt_gpu) # -1 for CPU + face_detector = face_detector.DetectorCVDNN() log.info('detecting face...') st = time.time() bboxes = face_detector.detect(im_resized, largest=True) - bbox = bboxes[0] + bbox_norm = bboxes[0] dim = im_resized.shape[:2][::-1] - bbox_dim = bbox.to_dim(dim) - if not bbox: + bbox_dim = bbox_norm.to_dim(dim) + if not bbox_norm: log.error('no face detected') return else: log.info(f'Detected face in {(time.time() - st):.2f}s') - log.info('') - - - # ---------------------------------------------------------------------------- - # detect 3D landmarks - - log.info('loading 3D landmark generator files...') - landmark_detector_3d_68 = face_landmarks.FaceAlignment3D_68(gpu=opt_gpu) # -1 for CPU - log.info('generating 3D landmarks...') - st = time.time() - points_3d_68 = landmark_detector_3d_68.landmarks(im_resized, bbox_dim.to_xyxy()) - log.info(f'generated 3D landmarks in {(time.time() - st):.2f}s') - log.info('') - - - # ---------------------------------------------------------------------------- - # generate 3D GIF animation - log.info('generating 3D animation...') - if not opt_fp_out: - fpp_im = Path(opt_fp_in) - fp_out = join(fpp_im.parent, f'{fpp_im.stem}_anim.gif') - else: - fp_out = opt_fp_out - st = time.time() - plot_utils.generate_3d_landmark_anim(np.array(points_3d_68), fp_out, - size=opt_gif_size, num_frames=opt_gif_frames) - log.info(f'Generated animation in {(time.time() - st):.2f}s') - log.info(f'Saved to: {fp_out}') - log.info('') - - - # ---------------------------------------------------------------------------- - # generate face vectors, only to test if feature extraction works - - log.info('initialize face recognition model...') - from app.processors import face_recognition - face_rec = face_recognition.RecognitionDLIB() - st = time.time() - log.info('generating face vector...') - vec = face_rec.vec(im_resized, bbox_dim) - log.info(f'generated face vector in {(time.time() - st):.2f}s') - log.info('') - # ---------------------------------------------------------------------------- # generate 68 point landmarks using dlib log.info('initializing face landmarks 68 dlib...') - from app.processors import face_landmarks landmark_detector_2d_68 = face_landmarks.Dlib2D_68() log.info('generating 2D 68PT landmarks...') st = time.time() - points_2d_68 = landmark_detector_2d_68.landmarks(im_resized, bbox_dim) + points_norm = landmark_detector_2d_68.landmarks(im_resized, bbox_norm) log.info(f'generated 2D 68PT face landmarks in {(time.time() - st):.2f}s') - log.info('') # ---------------------------------------------------------------------------- - # generate pose from 68 point 2D landmarks - - if opt_run_pose: - log.info('initialize pose...') - from app.processors import face_pose - pose_detector = face_pose.FacePoseDLIB() - log.info('generating pose...') - st = time.time() - pose_data = pose_detector.pose(points_2d_68, dim) - log.info(f'generated pose {(time.time() - st):.2f}s') - log.info('') - - - # x - - - # display + if opt_display: - - # draw bbox - - # draw 3d landmarks - im_landmarks_3d_68 = im_resized.copy() - draw_utils.draw_landmarks3D(im_landmarks_3d_68, points_3d_68) - draw_utils.draw_bbox(im_landmarks_3d_68, bbox_dim) # draw 2d landmarks - im_landmarks_2d_68 = im_resized.copy() - draw_utils.draw_landmarks2D(im_landmarks_2d_68, points_2d_68) - draw_utils.draw_bbox(im_landmarks_2d_68, bbox_dim) - - # draw pose - if opt_run_pose: - im_pose = im_resized.copy() - draw_utils.draw_pose(im_pose, pose_data['point_nose'], pose_data['points']) - draw_utils.draw_degrees(im_pose, pose_data) - - # draw animated GIF - im = Image.open(opt_fp_out) - im_frames = [] - duration = im.info['duration'] - try: - while True: - im.seek(len(im_frames)) - mypalette = im.getpalette() - im.putpalette(mypalette) - im_jpg = Image.new("RGB", im.size) - im_jpg.paste(im) - im_np = im_utils.pil2np(im_jpg.copy()) - im_frames.append(im_np) - except EOFError: - pass # end of GIF sequence - - n_frames = len(im_frames) - frame_number = 0 + im_lmarks = im_resized.copy() + im_lmarks = draw_utils.draw_bbox(im_lmarks, bbox_norm) + im_lmarks = draw_utils.draw_landmarks2D(im_lmarks, points_norm) - while True: - # show all images here - cv.imshow('Original', im_resized) - cv.imshow('2D 68PT Landmarks', im_landmarks_2d_68) - cv.imshow('3D 68PT Landmarks', im_landmarks_3d_68) - cv.imshow('Pose', im_pose) - cv.imshow('3D 68pt GIF', im_frames[frame_number]) - frame_number = (frame_number + 1) % n_frames - k = cv.waitKey(duration) & 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 + # show all images here + cv.imshow('2D 68PT Landmarks', im_lmarks) + display_utils.handle_keyboard()
\ No newline at end of file diff --git a/megapixels/commands/demo/face_landmarks_3d.py b/megapixels/commands/demo/face_landmarks_3d.py index 22e09297..ed5a00d5 100644 --- a/megapixels/commands/demo/face_landmarks_3d.py +++ b/megapixels/commands/demo/face_landmarks_3d.py @@ -3,7 +3,6 @@ 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 @@ -27,7 +26,7 @@ from app.settings import app_cfg as cfg help='GPU index') @click.option('-f', '--force', 'opt_force', is_flag=True, help='Force overwrite file') -@click.option('--display/--no-display', 'opt_display', is_flag=True, default=False, +@click.option('--display/--no-display', 'opt_display', is_flag=True, default=True, help='Display detections to debug') @click.pass_context def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_gif_frames, @@ -52,12 +51,6 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_gif_frames, from app.utils import plot_utils from app.processors import face_detector, face_landmarks from app.models.data_store import DataStore - - # TOOD add selective testing - opt_run_pose = True - opt_run_2d_68 = True - opt_run_3d_68 = True - opt_run_3d_68 = True # ------------------------------------------------- @@ -74,14 +67,14 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_gif_frames, # ---------------------------------------------------------------------------- # detect face - face_detector = face_detector.DetectorDLIBCNN(gpu=opt_gpu) # -1 for CPU + face_detector = face_detector.DetectorCVDNN() log.info('detecting face...') st = time.time() bboxes = face_detector.detect(im_resized, largest=True) - bbox = bboxes[0] + bbox_norm = bboxes[0] dim = im_resized.shape[:2][::-1] - bbox_dim = bbox.to_dim(dim) - if not bbox: + bbox_dim = bbox_norm.to_dim(dim) + if not bbox_norm: log.error('no face detected') return else: @@ -96,7 +89,7 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_gif_frames, landmark_detector_3d_68 = face_landmarks.FaceAlignment3D_68(gpu=opt_gpu) # -1 for CPU log.info('generating 3D landmarks...') st = time.time() - points_3d_68 = landmark_detector_3d_68.landmarks(im_resized, bbox_dim.to_xyxy()) + points_3d_68 = landmark_detector_3d_68.landmarks(im_resized, bbox_norm) log.info(f'generated 3D landmarks in {(time.time() - st):.2f}s') log.info('') @@ -119,19 +112,6 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_gif_frames, # ---------------------------------------------------------------------------- - # generate face vectors, only to test if feature extraction works - - log.info('initialize face recognition model...') - from app.processors import face_recognition - face_rec = face_recognition.RecognitionDLIB() - st = time.time() - log.info('generating face vector...') - vec = face_rec.vec(im_resized, bbox_dim) - log.info(f'generated face vector in {(time.time() - st):.2f}s') - log.info('') - - - # ---------------------------------------------------------------------------- # generate 68 point landmarks using dlib log.info('initializing face landmarks 68 dlib...') @@ -139,54 +119,25 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_gif_frames, landmark_detector_2d_68 = face_landmarks.Dlib2D_68() log.info('generating 2D 68PT landmarks...') st = time.time() - points_2d_68 = landmark_detector_2d_68.landmarks(im_resized, bbox_dim) + points_2d_68 = landmark_detector_2d_68.landmarks(im_resized, bbox_norm) log.info(f'generated 2D 68PT face landmarks in {(time.time() - st):.2f}s') log.info('') - # ---------------------------------------------------------------------------- - # generate pose from 68 point 2D landmarks - - if opt_run_pose: - log.info('initialize pose...') - from app.processors import face_pose - pose_detector = face_pose.FacePoseDLIB() - log.info('generating pose...') - st = time.time() - pose_data = pose_detector.pose(points_2d_68, dim) - log.info(f'generated pose {(time.time() - st):.2f}s') - log.info('') - - - # x - - - # display if opt_display: - # draw bbox - - # draw 3d landmarks - im_landmarks_3d_68 = im_resized.copy() - draw_utils.draw_landmarks3D(im_landmarks_3d_68, points_3d_68) - draw_utils.draw_bbox(im_landmarks_3d_68, bbox_dim) - - # draw 2d landmarks - im_landmarks_2d_68 = im_resized.copy() - draw_utils.draw_landmarks2D(im_landmarks_2d_68, points_2d_68) - draw_utils.draw_bbox(im_landmarks_2d_68, bbox_dim) - - # draw pose - if opt_run_pose: - im_pose = im_resized.copy() - draw_utils.draw_pose(im_pose, pose_data['point_nose'], pose_data['points']) - draw_utils.draw_degrees(im_pose, pose_data) + # draw landmarks + im_lmarks = im_resized.copy() + im_lmarks = draw_utils.draw_bbox(im_lmarks, bbox_norm) + im_lmarks = draw_utils.draw_landmarks2D(im_lmarks, points_2d_68, radius=1, color=(0,0,255)) + im_lmarks = draw_utils.draw_landmarks3D(im_lmarks, points_3d_68, radius=3, color=(0,255,0)) # draw animated GIF - im = Image.open(opt_fp_out) + im = Image.open(fp_out) im_frames = [] duration = im.info['duration'] + try: while True: im.seek(len(im_frames)) @@ -204,10 +155,7 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_gif_frames, while True: # show all images here - cv.imshow('Original', im_resized) - cv.imshow('2D 68PT Landmarks', im_landmarks_2d_68) - cv.imshow('3D 68PT Landmarks', im_landmarks_3d_68) - cv.imshow('Pose', im_pose) + cv.imshow('2D/3D 68PT Landmarks', im_lmarks) cv.imshow('3D 68pt GIF', im_frames[frame_number]) frame_number = (frame_number + 1) % n_frames k = cv.waitKey(duration) & 0xFF diff --git a/megapixels/commands/demo/face_pose.py b/megapixels/commands/demo/face_pose.py index 3918adac..48214e0d 100644 --- a/megapixels/commands/demo/face_pose.py +++ b/megapixels/commands/demo/face_pose.py @@ -22,7 +22,7 @@ from app.settings import app_cfg as cfg help='GPU index') @click.option('-f', '--force', 'opt_force', is_flag=True, help='Force overwrite file') -@click.option('--display/--no-display', 'opt_display', is_flag=True, default=False, +@click.option('--display/--no-display', 'opt_display', is_flag=True, default=True, help='Display detections to debug') @click.pass_context def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_size, opt_force, opt_display): @@ -61,12 +61,12 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_size, opt_force, opt_display): # ---------------------------------------------------------------------------- # detect face - face_detector = face_detector.DetectorDLIBCNN(gpu=opt_gpu) # -1 for CPU + face_detector = face_detector.DetectorCVDNN() bboxes = face_detector.detect(im_resized, largest=True) - bbox = bboxes[0] + bbox_norm = bboxes[0] dim = im_resized.shape[:2][::-1] - bbox_dim = bbox.to_dim(dim) - if not bbox: + bbox_dim = bbox_norm.to_dim(dim) + if not bbox_norm: log.error('no face detected') return @@ -76,7 +76,7 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_size, opt_force, opt_display): from app.processors import face_landmarks landmark_detector_2d_68 = face_landmarks.Dlib2D_68() - points_2d_68 = landmark_detector_2d_68.landmarks(im_resized, bbox_dim) + points_2d_68 = landmark_detector_2d_68.landmarks(im_resized, bbox_norm) # ---------------------------------------------------------------------------- @@ -97,14 +97,14 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_size, opt_force, opt_display): # draw # draw 2d landmarks - im_landmarks_2d_68 = im_resized.copy() - draw_utils.draw_landmarks2D(im_landmarks_2d_68, points_2d_68) - draw_utils.draw_bbox(im_landmarks_2d_68, bbox_dim) + im_landmarks = im_resized.copy() + im_landmarks = draw_utils.draw_landmarks2D(im_landmarks, points_2d_68) + im_landmarks = draw_utils.draw_bbox(im_landmarks, bbox_norm) # draw pose im_pose = im_resized.copy() - draw_utils.draw_pose(im_pose, pose_data['point_nose'], pose_data['points']) - draw_utils.draw_degrees(im_pose, pose_data) + im_pose = draw_utils.draw_pose(im_pose, pose_data['point_nose'], pose_data['points']) + im_pose = draw_utils.draw_degrees(im_pose, pose_data) # ---------------------------------------------------------------------------- @@ -120,9 +120,8 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_gpu, opt_size, opt_force, opt_display): if opt_display: - # show all images here cv.imshow('Original', im_resized) - cv.imshow('2D 68PT Landmarks', im_landmarks_2d_68) + cv.imshow('2D 68PT Landmarks', im_landmarks) cv.imshow('Pose', im_pose) display_utils.handle_keyboard()
\ No newline at end of file diff --git a/megapixels/commands/demo/face_search.py b/megapixels/commands/demo/face_search.py index ca0b8016..f551cafd 100644 --- a/megapixels/commands/demo/face_search.py +++ b/megapixels/commands/demo/face_search.py @@ -13,7 +13,7 @@ log = Logger.getLogger() help='File to lookup') @click.option('--data_store', 'opt_data_store', type=cfg.DataStoreVar, - default=click_utils.get_default(types.DataStore.SSD), + default=click_utils.get_default(types.DataStore.HDD), show_default=True, help=click_utils.show_help(types.DataStore)) @click.option('--dataset', 'opt_dataset', @@ -39,62 +39,65 @@ def cli(ctx, opt_fp_in, opt_data_store, opt_dataset, opt_results, opt_gpu): import cv2 as cv from tqdm import tqdm import imutils + from PIL import Image, ImageOps - from app.utils import file_utils, im_utils + from app.utils import file_utils, im_utils, display_utils, draw_utils from app.models.data_store import DataStore from app.processors import face_detector - from app.processors import face_recognition + from app.processors import face_extractor log = Logger.getLogger() + # init dataset dataset = Dataset(opt_data_store, opt_dataset) - dataset.load_face_vectors() - dataset.load_records() - dataset.load_identities() + dataset.load_metadata(types.Metadata.FILE_RECORD) + dataset.load_metadata(types.Metadata.FACE_VECTOR) + dataset.load_metadata(types.Metadata.FACE_ROI) + # dataset.load_metadata(types.Metadata.IDENTITY) # init face detection - detector = face_detector.DetectorDLIBHOG() + detector = face_detector.DetectorCVDNN() - # init face recognition - recognition = face_recognition.RecognitionDLIB(gpu=opt_gpu) + # init face extractor + extractor = face_extractor.ExtractorVGG() # load query image im_query = cv.imread(opt_fp_in) # get detection as BBox object bboxes = detector.detect(im_query, largest=True) - bbox = bboxes[0] + bbox_norm = bboxes[0] dim = im_query.shape[:2][::-1] - bbox = bbox.to_dim(dim) # convert back to real dimensions + bbox_dim = bbox_norm.to_dim(dim) # convert back to real dimensions - if not bbox: + if not bbox_norm: log.error('No face detected. Exiting') return # extract the face vectors - vec_query = recognition.vec(im_query, bbox) + vec_query = extractor.extract(im_query, bbox_norm) + log.debug(f'len query: {len(vec_query)}') # find matches image_records = dataset.find_matches(vec_query, n_results=opt_results) # summary + im_query = draw_utils.draw_bbox(im_query, bbox_norm, stroke_weight=8) ims_match = [im_query] for image_record in image_records: image_record.summarize() log.info(f'{image_record.filepath}') im_match = cv.imread(image_record.filepath) + + im_match_pil = Image.open(image_record.filepath).convert('RGB') + # bbox = ims_match.append(im_match) + # make montages of most similar faces montages = imutils.build_montages(ims_match, (256, 256), (3,2)) + # display for i, montage in enumerate(montages): - cv.imshow(f'{i}', montage) - # cv gui - 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 + cv.imshow(f'{opt_dataset.name.upper()}: page {i}', montage) + + display_utils.handle_keyboard() diff --git a/megapixels/commands/demo/face_vector.py b/megapixels/commands/demo/face_vector.py index 3ff68001..c7b5ef2e 100644 --- a/megapixels/commands/demo/face_vector.py +++ b/megapixels/commands/demo/face_vector.py @@ -1,9 +1,8 @@ """ -Crop images to prepare for training +Tests if the feature vector generator works """ import click -# from PIL import Image, ImageOps, ImageFilter, ImageDraw from app.settings import types from app.utils import click_utils @@ -14,11 +13,11 @@ from app.settings import app_cfg as cfg @click.option('-i', '--input', 'opt_fp_in', default=None, required=True, help='Image filepath') @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('-g', '--gpu', 'opt_gpu', default=0, help='GPU index') -@click.option('--display/--no-display', 'opt_display', is_flag=True, default=False, +@click.option('--display/--no-display', 'opt_display', is_flag=True, default=True, help='Display detections to debug') @click.pass_context def cli(ctx, opt_fp_in, opt_gpu, opt_size, opt_display): @@ -54,12 +53,12 @@ def cli(ctx, opt_fp_in, opt_gpu, opt_size, opt_display): # ---------------------------------------------------------------------------- # detect face - face_detector = face_detector.DetectorDLIBCNN(gpu=opt_gpu) # -1 for CPU + face_detector = face_detector.DetectorCVDNN() # -1 for CPU bboxes = face_detector.detect(im_resized, largest=True) - bbox = bboxes[0] + bbox_norm = bboxes[0] dim = im_resized.shape[:2][::-1] - bbox_dim = bbox.to_dim(dim) - if not bbox: + bbox_dim = bbox_norm.to_dim(dim) + if not bbox_norm: log.error('no face detected') return @@ -67,14 +66,13 @@ def cli(ctx, opt_fp_in, opt_gpu, opt_size, opt_display): # ---------------------------------------------------------------------------- # generate face vectors, only to test if feature extraction works - from app.processors import face_recognition - facerec = face_recognition.RecognitionDLIB() - vec = facerec.vec(im_resized, bbox_dim) - vec_flat = facerec.flatten(vec) - log.info(f'generated vector. showing vec[0:10]:') - log.info(f'\n{vec_flat}') + from app.processors import face_extractor + extractor = face_extractor.ExtractorVGG() + vec = extractor.extract(im_resized, bbox_norm) + vec_str = extractor.to_str(vec) + log.info(f'\n{vec_str}') if opt_display: - draw_utils.draw_bbox(im_resized, bbox_dim) + im_resized = draw_utils.draw_bbox(im_resized, bbox_dim) cv.imshow('Original', im_resized) display_utils.handle_keyboard()
\ No newline at end of file |