def _process_image(self,xml_file,img_file):
if not os.path.exists(img_file):
return None,None,None,None,None,None,None
if self.image_preprocess is not None:
img = wmli.imread(img_file)
img = self.image_preprocess(img)
image_data = wmli.encode_img(img)
else:
image_data = tf.gfile.FastGFile(img_file, 'rb').read()
shape, _bboxes, _labels_text, _difficult, _truncated,_ = odu.read_voc_xml(xml_file, adjust=None)
_labels = self.labels_text_to_labels(_labels_text)
bboxes = []
labels_text = []
difficult = []
truncated = []
labels = []
for data in zip(_bboxes,_labels,_labels_text,_difficult,_truncated):
if self.category_id_filter(data[1]):
bboxes.append(data[0])
labels.append(data[1])
labels_text.append(data[2])
difficult.append(data[3])
truncated.append(data[4])
if len(labels) == 0:
#print(f"Ignore {name}.")
return None,None,None,None,None,None,None
return image_data, shape, bboxes, labels, labels_text, difficult, truncated
def trans_dir(src_dir, out_dir):
sub_dirs = wmlu.recurse_get_subdir_in_dir(src_dir)
pattern = "img_{:05d}.jpg"
wmlu.create_empty_dir(out_dir, remove_if_exists=False)
for sd in sub_dirs:
if sd[-1] == "/":
sd = sd[:-1]
rsd = osp.join(src_dir, sd)
files = glob.glob(osp.join(rsd, "*.jpg"))
if len(files) == 0:
continue
save_name = osp.join(out_dir, sd + f"_{data_type}_{len(files)}.np")
save_dir_name = osp.dirname(save_name)
wmlu.create_empty_dir(save_dir_name, remove_if_exists=False)
all_frames = []
for i in range(len(files)):
file_name = pattern.format(i + 1)
file_path = osp.join(rsd, file_name)
if not osp.exists(file_path):
print(f"File {file_path} not exists, len={len(files)}")
continue
with open(file_path, "rb") as f:
data = f.read()
if args.new_short > 2:
img = wmli.decode_img(data)
img = wmli.resize_short_size(img, args.new_short)
data = wmli.encode_img(img)
all_frames.append(data)
print(f"Save {save_name}")
with open(save_name, "wb") as f:
pickle.dump(all_frames, f)
def extract_frame(vid_item):
"""Generate optical flow using dense flow.
Args:
vid_item (list): Video item containing video full path,
video (short) path, video id.
Returns:
bool: Whether generate optical flow successfully.
"""
full_path, subdir, save_path = vid_item
out_full_path = save_path
vr = wmli.VideoReader(full_path)
print(f"{full_path} fps {vr.fps}.")
sys.stdout.flush()
# for i in range(len(vr)):
all_frames = []
try:
for i, vr_frame in enumerate(vr):
if vr_frame is not None:
if img_process_fn is not None:
vr_frame = img_process_fn(vr_frame)
w, h, _ = np.shape(vr_frame)
if args.new_short == 0:
if args.new_width == 0 or args.new_height == 0:
# Keep original shape
out_img = vr_frame
else:
out_img = mmcv.imresize(vr_frame,
(args.new_width,
args.new_height))
else:
if min(h, w) == h:
new_h = args.new_short
new_w = int((new_h / h) * w)
else:
new_w = args.new_short
new_h = int((new_w / w) * h)
out_img = mmcv.imresize(vr_frame, (new_h, new_w))
all_frames.append(wmli.encode_img(out_img))
else:
warnings.warn(
'Length inconsistent!'
f'Early stop with {i + 1} out of {len(vr)} frames.')
break
out_full_path = out_full_path+f"_{len(all_frames)}.np"
with open(out_full_path,"wb") as f:
pickle.dump(all_frames,f)
except Exception as e:
print(f"Process {full_path} faild, {e}")
print(f'{full_path} -> {out_full_path} done')
sys.stdout.flush()
return True
def create_tf_example(image, annotations):
global src_file_index
image_height = image['img_height']
image_width = image['img_width']
img_path = image['img_path']
if RECORD_IMG_SIZE is None:
with tf.gfile.GFile(img_path, 'rb') as fid:
encoded_jpg = fid.read()
else:
img = wmli.imread(img_path)
img = wmli.resize_img(img, RECORD_IMG_SIZE, keep_aspect_ratio=True)
encoded_jpg = wmli.encode_img(img)
xmin = []
xmax = []
ymin = []
ymax = []
is_crowd = []
category_ids = []
for l, box in annotations:
xmin.append(box[1])
xmax.append(box[3])
ymin.append(box[0])
ymax.append(box[2])
is_crowd.append(False)
category_ids.append(l)
if len(xmin) == 0:
return None
feature_dict = {
'image/height': dataset_util.int64_feature(image_height),
'image/width': dataset_util.int64_feature(image_width),
'image/filename': dataset_util.bytes_feature(img_path.encode('utf8')),
'image/encoded': dataset_util.bytes_feature(encoded_jpg),
'image/format': dataset_util.bytes_feature('jpeg'.encode('utf8')),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmin),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmax),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymin),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymax),
'image/object/class/label':
dataset_util.int64_list_feature(category_ids),
'image/object/is_crowd': dataset_util.int64_list_feature(is_crowd),
}
example = tf.train.Example(features=tf.train.Features(
feature=feature_dict))
return example