1 files changed, 86 insertions, 0 deletions
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)
+