Air

Great work! May i ask where the mask_loss calculated?

关于如何使用命令行进行操作

1

感谢作者大大的辛勤工作！我想请问一下这份数据增强软件是否能通过命令行的形式键入所需参数呢？

关于视频数据增强

4

尊敬的啥都生大大您好！ 非常有用的工作！感谢您的付出！ 同时向您请教，假设我有一份视频，我将视频逐帧读取为图片获得图片集，我是否可以使用您的数据增强软件，对这个图片集下的所有图片做相同的变换呢？ 恳请您的回复。

A description of the output results

2

Rex Hello! I would like to ask you if there are two results for each video in the output result, is this because the J&F value of both targets in...

When I run your code, it constantly prompts "Finish saving the results, 15 masks and 0 overlays left." and no further inference is made

When test Cuda out of Mem

4

Code : ———————————————————————————— from cutie.utils.get_default_model import get_default_model from cutie.inference.inference_core import InferenceCore import torch import os os.environ['CUDA_VISIBLE_DEVICES']='0' from PIL import Image import numpy as np from torchvision import transforms def main():...

There is almost no difference between the two images, but the MTJ key points marked are very different, please provide adequate explanation.  

Sincerely waiting for 2d tracking code

1

Thank you for your excellent work, this work is deeply inspiring to us we sincerely waiting for 2d tracking code

What a beautiful cake — if only it had cream, or even cake.