YTHmamba
YTHmamba
> OH, Mine is working right now > > 1. change it to ===> p = subprocess.run(ffprobe_cmd,stdout= subprocess.PIPE,shell=True) > 2. Do you install the ffmpeg? > I forgot to install...
> @Katou2 @kenshohara Great discussion.What I want to ask is how do I get the video accuracy and what is input with eval_ucf101.py, I don't see val.json.I only have val.log...
> @huangwei1995 hello ,Have you solved it? How to obtain the accuracy in the paper
> @slighting666 I have the same question as you, there seems to be no eval_UCf101.py file in the code in the master branch
> I believe the reason is UCF101 is a relatively small dataset. Model should pre-train on bigger dataset for instance Kinetics or sport1M then fine-tune on UCF101 for getting a...
> > 我相信原因是UCF101是一个相对较小的数据集。模型应该在更大的数据集上进行预训练，例如Kinetics或sport1M，然后在UCF101上进行微调以获得更好的精度。我用这种方法训练我自己的模型可以在UCF101上获得近90%的准确率。 > > hello ,Can you tell me the configuration in opts.py that you trained to 90% accuracy? thanks! 请问你的精度是什么精度，原文中提到了Clip / Top-1 / Top-5 acc三种精度，我的精度是clip精度，请问为什么Top-1精度就比clip精度高呢，这三个精度有什么区别吗？十分感谢
> @ @guilhermesurek Hi, can only KINETICS data set calculate top1 accuracy? How is the UCF101 dataset calculated? I get an error using these two lines, and the ground_truth of...
> @YTHmamba我没有在 UCF101 中运行，但代码似乎是通用的，独立于数据集。尝试检查您的推理 json（或 val.json）是否与您的基本事实 json 相似。或者可能是 class_labels_map 中的任何差异。 @guilhermesurek Thank you very much. Is the clip accuracy of the paper the identification accuracy of 16 frames? How is...
> 我的联系方式发你邮件了 您好，请问您如何处理数据集UCF101生成csv文件的呢，方便交换联系方式交流一下吗，十分感谢
Hello, how did you reproduce it？