Open-Sora: Democratizing Efficient Video Production for All
Python
skip empty folder & meta
pxy109e870e6a7e
diff --git a/tools/datasets/convert.py b/tools/datasets/convert.pyindex f35d91e..2d49c4d 100644--- a/tools/datasets/convert.py+++ b/tools/datasets/convert.py@@ -94,6 +94,8 @@ def process_vidprom(root, info):def process_general_images(root, output):root = os.path.expanduser(root)+ if not os.path.exists(root):+ returnpath_list = get_filelist(root, IMG_EXTENSIONS)fname_list = [os.path.splitext(os.path.basename(x))[0] for x in path_list]df = pd.DataFrame(dict(id=fname_list, path=path_list))@@ -105,6 +107,8 @@ def process_general_images(root, output):def process_general_videos(root, output):root = os.path.expanduser(root)+ if not os.path.exists(root):+ returnpath_list = get_filelist(root, VID_EXTENSIONS)path_list = list(set(path_list)) # remove duplicatesfname_list = [os.path.splitext(os.path.basename(x))[0] for x in path_list]diff --git a/tools/datasets/datautil.py b/tools/datasets/datautil.pyindex 5e68802..7006d21 100644--- a/tools/datasets/datautil.py+++ b/tools/datasets/datautil.py@@ -473,6 +473,9 @@ def read_data(input_paths):if i != len(input_list) - 1:input_name += "+"print(f"Loaded {len(data[-1])} samples from \'{input_path}\'.")+ if len(data) == 0:+ print(f"No samples to process. Exit.")+ exit()data = pd.concat(data, ignore_index=True, sort=False)print(f"Total number of samples: {len(data)}")return data, input_name@@ -487,9 +490,6 @@ def read_data(input_paths):def main(args):# reading datadata, input_name = read_data(args.input)- if len(data) == 0:- print(f"No samples to process. Exit.")- exit()# make differenceif args.difference is not None:diff --git a/tools/scene_cut/cut.py b/tools/scene_cut/cut.pyindex ed958c9..c5eebf3 100644--- a/tools/scene_cut/cut.py+++ b/tools/scene_cut/cut.py@@ -155,10 +155,14 @@ def parse_args():def main():args = parse_args()- os.makedirs(args.save_dir, exist_ok=True)+ meta_path = args.meta_path+ if not os.path.exists(meta_path):+ print(f"Meta file \'{meta_path}\' not found. Exit.")+ exit()# create loggerlogger = None+ os.makedirs(args.save_dir, exist_ok=True)# initialize pandarallelif args.num_workers is not None:@@ -168,7 +172,7 @@ def main():process_single_row_partial = partial(process_single_row, args=args)# process- meta = pd.read_csv(args.meta_path)+ meta = pd.read_csv(meta_path)meta.parallel_apply(process_single_row_partial, axis=1)diff --git a/tools/scene_cut/scene_detect.py b/tools/scene_cut/scene_detect.pyindex a9acf54..0df68d7 100644--- a/tools/scene_cut/scene_detect.py+++ b/tools/scene_cut/scene_detect.py@@ -43,6 +43,9 @@ def parse_args():def main():args = parse_args()meta_path = args.meta_path+ if not os.path.exists(meta_path):+ print(f"Meta file \'{meta_path}\' not found. Exit.")+ exit()if args.num_workers is not None:pandarallel.initialize(progress_bar=True, nb_workers=args.num_workers)