Merge branch 'master' of github.com:adamhrv/megapixels_dev

7 files changed, 369 insertions, 57 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