updates for batch processing

1 files changed, 37 insertions, 24 deletions

diff --git a/megapixels/commands/cv/face_roi.py b/megapixels/commands/cv/face_roi.py
index 950936cf..e83b0f61 100644
--- a/megapixels/commands/cv/face_roi.py
+++ b/megapixels/commands/cv/face_roi.py
@@ -105,23 +105,29 @@ def cli(ctx, opt_fp_in, opt_dir_media, opt_fp_out, opt_data_store, opt_dataset,
 
   
   # 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, dtype={'fn':str}).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)