0aqz0 / slr Goto Github PK
View Code? Open in Web Editor NEWisolated & continuous sign language recognition using CNN+LSTM/3D CNN/GCN/Encoder-Decoder
isolated & continuous sign language recognition using CNN+LSTM/3D CNN/GCN/Encoder-Decoder
/home/haodong/Data/CSL_Isolated/color_video_125000'“这个视频时不是未处理过视频?下载链接里没有,up主和路过的朋友谁有下载网址呢?
CSL的有些数据集的百度云链接挂了,您这边还有其他下载路径吗
请问dataset.py里的Skeleton部分中的selected_skeleton = torch.FloatTensor([selected_x, selected_y])语句会导致这个错误产生ValueError: expected sequence of length 38 at dim 1 (got 37),请问有什么解决办法吗
我看代码里有r(2+1) 18,但是这个识别率是18的吗?有点疑惑。
孤立词手语数据集CL500视频是怎么处理成视频帧的
Hi,
It's me again. I tried to use your cnnlstm model which is Rescnnlstm, but the loss isn't going down. So I am wondering where I was wrong. I set the same parameter that you provided. How many epochs did you train for 92% accuracy? Thanks
请分享。
运行文件时出现错误。因为那个文件。
您好,看您在读取数据时读取的是.jpg文件,想知道您是否对连续手语数据集进行了视频帧提取?
你好,我想请问一下怎么做可视化检测界面啊,能实现实时手语识别
Hello guys can these code works for Phoenix2014 continuous sign language data set if we correct the dataset directory or the path
please let met know if they correct
test.py文件中resnet18等模型的坚果云下载路径已经失效,请问您是否还有保存这些模型。有的话能分享一下吗?谢谢~
一类50或者250份的都行,谢谢啦
你好,
请问你有试着用ctc loss来训练 continuous SLR 吗?我的模型很简单,就是 pretrained EfficientNet + self-attention(3 layer) + linear + ctc loss. 我是在RWTH-PHOENIX- Weather-2014T 这个数据集上训练的,然后发现loss完全降不下去,维持在5.2左右,而且在解码的时候只预测blank。个人感觉应该不是我的ctc loss使用问题,因为我之前用ctc loss训练machine translation是没有问题的。想知道你有训练过这个数据集和用ctc来训这个模型吗?
您好,请问CSL_Continuous和CSL_Continuous_Char有什么区别呢?我从官方的数据集中好像没有看到dictionary.txt这个文件
请问作者是怎么样申请的csl500数据集的,我找不到申请的入口,百度网盘链接失效了
作者你好,我训练孤立词的时候发现在前几个epoch的时候acc就能到接近100,并且最后的loss值大概是0.0008左右,请问这是什么问题呢
我下载了slr500_rgb这个文件,将dataset.py里isolated的data_path中的color_video_125000直接换成slr500_rgb就可以了吗
您好,我在官网下载了数据集,下载完成后想用您的代码进行训练,但是对独立手语动作数据集读取这部分的路径和官方下载的数据集不太一样,想知道是不是您对数据集做了预处理,是把动作中不同的录入者放到了一个文件夹中吗?
在最后计算WER的值时,有没有办法知道substitution、insertion、deletion这三种单独的次数?
请问,您有500类别的骨架信息的文件吗?我在分享的百度网盘里下载的数据集,没有找到骨架信息的txt文件。
hello guys can any one tell me about how CSL Dataset data path or directory is prepared i want to try these code in my local sign language dataset but because of the CSL Dataset is private i don't about the data structure please tell me or give me the small data
email: [email protected]
Excellent job!! Cause I am a fresh bird in this area, could you please tell me what is l and g which are as inputs for linearattentionblock?
can you give me the detail excution for csl_continuous execution please
请问训练的时候需要对数据集进行什么处理吗
请问最后需要通过AzureKinect摄像头展示效果吗
code
When use openpose, why used the link (11, 5), (8, 2)?
I only see the link (11, 1) and (8, 1) in openpose.
Also in "ntu-rgb+d", i can not find the link (22, 23), (24, 25), but you used it in the neighbor_link.
Hello
I am currently working on a continuous seq2seq code.
I am trying to work on our dataset.
However, I cannot check dictionary.txt and corpus.txt file.
Can you upload files here or explain the composition of each file?
Thank you.
你好,我想测试我训练好的连续句子的模型,但是test.py文件好像是针对的是孤立词模型,请问我该怎样测试连续句子的模型呢,谢谢
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.