HOPE

HOPE copied to clipboard

Hi, I found that there is no pre-trained weights for HOPE-Net but only the Graph network, and in Graph.py, you use label2d directly for testing instead of the results from...

ZhengdiYu

Test error is bigger than reported

11

Hi, I know this issue has been raised in issue [13](https://github.com/bardiadoosti/HOPE/issues/13) and issue [17](https://github.com/bardiadoosti/HOPE/issues/17), and it doesn't seem that they are addressed. I was hoping if you could provide with...

zc-alexfan

environment

1

Hi Bardia Doosti! Thank you for your excellent work and willing to share it. I want to know the environment configuration required by this code, I'm a beginner. I hope...

Liqi255

The range or unit of the output result

7

Hi Bardia Doosti! Thank you for your excellent work and willing to share it. Recently I am trying to predic the 21 key points of hand, but now I have...

LiuYi-Up

I have downloaded the dataset from the given sources and created the *.npy files using the make_data.py file. Do I still need dataset images/videos for training?

deepakraina99

Hello, your research is very valuable, I am trying to apply your research in the field of robotics, and I really need the model parameters of the whole HOPE-Net, I...

kkjsk

I have done training some epoch (less 1000) on the whole HopeNet and Resnet10 part separately，i find training loss is going to converge at begining but val loss seem to...

claylau

Some weights and baises are missing in the graphunet pre-trained model

10

Hi bardiadoosti, Thanks for updating the trained model and sharing it again. However, there are some missing weights in the shared model. I run the updated testing code and get...

Almadani92

Hi bardiadoosti, I noticed that the currently provided pre-trained model of GraphUNet only converts 2d point coordinates to 3d predictions, but I am more interested in the Resnet part, which...

UCASRMT

Thank you for this great work, can you share the detailed data of picture 5 and picture 6 ? I want to know the detailed results of this paper and...

Leslie1234