model1 / llava /datasets /tt_gptv_v1_dataset.py
multitensor's picture
Upload folder using huggingface_hub
bbfa6f6 verified
raw
history blame contribute delete
440 Bytes
import json
import os
from pathlib import Path
with open('/mnt/bn/algo-masp-nas-2/kaili.zhao/data/masp_data/train/gpt4v_annotation/20240325week_gpt4v_all_videos_unique_ids.json') as f:
data = json.load(f)
for sample in data:
video_path = Path(sample['video_path'])
file_names = os.listdir(sample['video_path'])
if len(file_names) == 10:
file_names.sort(key=lambda x: int(x[:-4]))
print(file_names)