1 files changed, 100 insertions, 0 deletions
diff --git a/megapixels/commands/cv/embeddings.py b/megapixels/commands/cv/embeddings.py
new file mode 100644
index 00000000..9cb26ae7
--- /dev/null
+++ b/megapixels/commands/cv/embeddings.py
@@ -0,0 +1,100 @@
+"""
+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 directory')
+@click.option('-r', '--records', 'opt_fp_records', required=True,
+  help='Input directory')
+@click.option('-m', '--media', 'opt_fp_media', required=True,
+  help='Image directory')
+@click.option('-o', '--output', 'opt_fp_out', required=True,
+  help='Output CSV')
+@click.option('--size', 'opt_size', 
+  type=(int, int), default=(300, 300),
+  help='Output image size')
+@click.option('-g', '--gpu', 'opt_gpu', default=0,
+  help='GPU index')
+@click.option('--slice', 'opt_slice', type=(int, int), default=(None, None),
+  help='Slice list of files')
+@click.option('-f', '--force', 'opt_force', is_flag=True,
+  help='Force overwrite file')
+@click.option('-j', '--jitters', 'opt_jitters', default=cfg.DLIB_FACEREC_JITTERS,
+  help='Number of jitters')
+@click.option('-p', '--padding', 'opt_padding', default=cfg.DLIB_FACEREC_PADDING,
+  help='Percentage padding')
+@click.pass_context
+def cli(ctx, opt_fp_in, opt_fp_records, opt_fp_out, opt_fp_media, opt_size, opt_gpu,
+  opt_slice, opt_jitters, opt_padding, opt_force):
+  """Converts frames with faces to CSV of rows"""
+  
+  import sys
+  import os
+  from os.path import join
+  from pathlib import Path
+  
+  from tqdm import tqdm
+  import numpy as np
+  import dlib  # must keep a local reference for dlib
+  import cv2 as cv
+  import dlib
+  import pandas as pd
+
+  from app.utils import logger_utils, file_utils, im_utils
+  from app.models.bbox import BBox
+  from app.processors import face_recognition
+
+  # -------------------------------------------------
+  # init here
+
+  log = logger_utils.Logger.getLogger()
+
+  if not opt_force and Path(opt_fp_out).exists():
+    log.error('File exists. Use "-f / --force" to overwite')
+    return
+  
+  # init dlib FR
+  facerec = face_recognition.RecognitionDLIB()
+
+  # load data
+  df_rois = pd.read_csv(opt_fp_in)
+  df_records = pd.read_csv(opt_fp_records)
+
+  if opt_slice:
+    df_rois = df_rois[opt_slice[0]:opt_slice[1]]
+  log.info('Processing {:,} rows'.format(len(df_rois)))
+  nrows = len(df_rois)
+
+  # face vecs
+  vecs = []
+
+  for roi_idx, row in tqdm(df_rois.iterrows(), total=nrows):
+    # make image path
+    record_id = int(row['id'])
+    df = df_records.iloc[record_id]
+    fp_im = join(opt_fp_media, df['subdir'], '{}.{}'.format(df['fn'], df['ext'])) 
+    # load image
+    im = cv.imread(fp_im)
+    # make bbox
+    xywh = [row['x'], row['y'], row['w'] , row['h']]
+    bbox = BBox.from_xywh(*xywh)
+    # scale to actual image size
+    dim = (row['image_width'], row['image_height'])
+    bbox_dim = bbox.to_dim(dim)
+    # compute vec
+    vec = facerec.vec(im, bbox_dim, jitters=opt_jitters, padding=opt_padding)
+    vec_str = ','.join([repr(x) for x in vec])
+    vecs.append( {'id': row['id'], 'vec': vec_str})
+  
+  # save data
+  file_utils.mkdirs(opt_fp_out)
+  df_vecs = pd.DataFrame.from_dict(vecs)
+  df_vecs.to_csv(opt_fp_out, index=False)
+  log.info('saved {:,} lines to {}'.format(len(df_vecs), opt_fp_out))
+\ No newline at end of file