merge

4 files changed, 388 insertions, 0 deletions

diff --git a/megapixels/datasets/commands/crop.py b/megapixels/datasets/commands/crop.py
new file mode 100644
index 00000000..778be0c4
--- /dev/null
+++ b/megapixels/datasets/commands/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/datasets/commands/extract.py b/megapixels/datasets/commands/extract.py
new file mode 100644
index 00000000..4e77a978
--- /dev/null
+++ b/megapixels/datasets/commands/extract.py
@@ -0,0 +1,86 @@
+"""
+Crop images to prepare for training
+"""
+
+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('--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('--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('--padding', 'opt_padding', default=0,
+  help='Facial padding')
+@click.option('--ext', 'opt_ext_out', default='jpg', type=click.Choice(['jpg', 'png']),
+  help='Output image type')
+@click.pass_context
+def cli(ctx, opt_fp_in, opt_dir_media, opt_dir_out, opt_size, opt_slice, 
+  opt_padding, opt_ext_out):
+  """Extrace 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)
+  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
+
+  for group in groups:
+    
+    # get image
+    group_rows = df_rois_grouped.get_group(group)
+
+    row = group_rows.iloc[0]
+    fp_im = join(opt_dir_media, '{fn}{ext}'.format(**row))  #TODO change to ext
+    im = Image.open(fp_im)
+
+    
+    for idx, roi in group_rows.iterrows():
+      log.info('{}'.format(roi['fn']))
+      # 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
+      bbox_dim_exp = bbox_dim.expand_dim(opt_padding, dim)
+      # crop
+      x1y2 = bbox_dim_exp.pt_tl + bbox_dim_exp.pt_br
+      im_crop = im.crop(box=x1y2)
+      # save
+      idx_zpad = file_utils.zpad(idx, zeros=3)
+      fp_im_out = join(opt_dir_out, '{}_{}.{}'.format(roi['fn'], idx_zpad, opt_ext_out))
+      im_crop.save(fp_im_out)
+
diff --git a/megapixels/datasets/commands/face.py b/megapixels/datasets/commands/face.py
new file mode 100644
index 00000000..6b7b18b7
--- /dev/null
+++ b/megapixels/datasets/commands/face.py
@@ -0,0 +1,117 @@
+"""
+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_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('--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.pass_context
+def cli(ctx, opt_dir_in, opt_fp_out, opt_ext, opt_size, opt_detector_type, 
+  opt_gpu, opt_conf_thresh, opt_pyramids, opt_slice, opt_display):
+  """Extrace face"""
+  
+  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 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.HAAR:
+    log.error('{} not yet implemented'.format(opt_detector_type.name))
+    return
+
+  
+  # -------------------------------------------------
+  # process here
+  
+  # get list of files to process
+  fp_ims = glob(join(opt_dir_in, '*.{}'.format(opt_ext)))
+  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)
+    bboxes = detector.detect(im, opt_size=opt_size, opt_pyramids=opt_pyramids)
+    fpp_im = Path(fp_im)
+    for bbox in bboxes:
+      roi = {
+        'fn': fpp_im.stem, 
+        'ext': fpp_im.suffix, 
+        'x': bbox.x, 
+        'y': bbox.y, 
+        'w': bbox.w, 
+        'h': bbox.h}
+      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=opt_size[0])
+      for bbox in bboxes:
+        dim = bbox.to_dim(im_md.shape[:2][::-1])
+        cv.rectangle(im_md, dim.pt_tl, 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
+  df = pd.DataFrame.from_dict(data)
+  df.to_csv(opt_fp_out)
\ No newline at end of file
diff --git a/megapixels/datasets/commands/resize.py b/megapixels/datasets/commands/resize.py
new file mode 100644
index 00000000..5e2d31aa
--- /dev/null
+++ b/megapixels/datasets/commands/resize.py
@@ -0,0 +1,81 @@
+"""
+Crop images to prepare for training
+"""
+
+import click
+
+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   ⭐⭐⭐⭐  ⭐⭐⭐⭐  ⭐
+"""
+
+@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='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 (square)')
+@click.option('--method', 'opt_scale_method', 
+  type=click.Choice(['LANCZOS', 'BICUBIC', 'HAMMING', 'BILINEAR', 'BOX', 'NEAREST']),
+  default='LANCZOS',
+  help='Scaling method to use')
+@click.pass_context
+def cli(ctx, opt_dir_in, opt_dir_out, opt_glob_ext, opt_size, opt_scale_method):
+  """Crop, mirror images"""
+  
+  import os
+  from os.path import join
+  from pathlib import Path
+  from glob import glob
+  from tqdm import tqdm
+  from PIL import Image, ImageOps, ImageFilter
+  from app.utils import logger_utils, file_utils, im_utils
+  
+  # -------------------------------------------------
+  # init
+
+  log = logger_utils.Logger.getLogger()
+  
+  methods = {
+    'LANCZOS': Image.LANCZOS,
+    'BICUBIC': Image.BICUBIC,
+    'HAMMING': Image.HAMMING,
+    'BILINEAR': Image.BILINEAR,
+    'BOX': Image.BOX,
+    'NEAREST': Image.NEAREST
+    }
+
+  # -------------------------------------------------
+  # process here
+
+  # get list of files to process
+  fp_ims = glob(join(opt_dir_in, '*.{}'.format(opt_glob_ext)))
+  log.info('processing {:,} files'.format(len(fp_ims)))
+  
+  # set scale method
+  scale_method = methods[opt_scale_method]
+
+  # 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)
+    im = ImageOps.fit(im, opt_size, method=scale_method, centering=(0.5, 0.5))
+    fp_out = join(opt_dir_out, Path(fp_im).name)
+    im.save(fp_out)
+