search

JJBOY / BMN-Boundary-Matching-Network

A pytorch-version implementation codes of paper: "BMN: Boundary-Matching Network for Temporal Action Proposal Generation", which is accepted in ICCV 2019.
MIT License
291 stars 64 forks source link

csv_mean_100/v_nt4Ag91306U.csv does not exist #35

Open lucky-23 opened 4 years ago

lucky-23 commented 4 years ago

Hi,

I got this problem of data/activitynet_feature_cuhk/csv_mean_100/v_nt4Ag91306U.csv does not exist. It seems that some of the files are missing.Can you please tell me how to solve this problem?

JJBOY commented 4 years ago

Please refer to this issue #11

lucky-23 commented 4 years ago

Hello @JJBOY , I encountered another problem. I trained the model but it seems to get stuck after printing the following: train subset video numbers: 9649 validation subset video numbers: 4728 It still remains the same after a couple of hours. Is there any reason for this?

JJBOY commented 4 years ago

First , you can clone the latest code from my github. Then, you can watch the usage of your GPU or print the imformation every iteration. It's about 10 minutes to train an epoch on 2 1080Ti cards.

------------------ 原始邮件 ------------------ 发件人: "lucky-23"<notifications@github.com>; 发送时间: 2020年9月4日(星期五) 中午11:01 收件人: "JJBOY/BMN-Boundary-Matching-Network"<BMN-Boundary-Matching-Network@noreply.github.com>; 抄送: "Hello World"<1135869534@qq.com>; "Comment"<comment@noreply.github.com>; 主题: Re: [JJBOY/BMN-Boundary-Matching-Network] csv_mean_100/v_nt4Ag91306U.csv does not exist (#35)

Hello, I encountered another problem. I trained the model but it seems to get stuck after printing the following: train subset video numbers: 9649 validation subset video numbers: 4728 It still remains the same after a couple of hours. Is there any reason for this?

— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.

lucky-23 commented 4 years ago

Hi @JJBOY thanks. The training is finally working. I also want to know if you could please provide me the code for the action detection part?