Jiaming Han

```python import sys sys.path.append('./') import os import json import types import numpy as np from PIL import Image import torch import torch.nn as nn import multiprocessing as mp import torch.distributed...

Hi @vittoriopipoli @qixueweigitbub , hope this script can help you for mixed modal input.

Hi @vittoriopipoli I cannot access the original code at Shanghai AI Lab, but you can find AVSD at https://github.com/dialogtekgeek/DSTC8-AVSD_official and Valor32k at https://casia-iva-group.github.io/projects/VALOR/download.html

Hi @proxymallick , I did not test our method with one GPU, but I think the number of GPUs may affect the final results. Since your mAP is ~3% lower...

理论上是可行的。可能需要重新调整loss weight