deep-head-pose icon indicating copy to clipboard operation
deep-head-pose copied to clipboard

:fire::fire: Deep Learning Head Pose Estimation using PyTorch.

Results 60 deep-head-pose issues
Sort by recently updated
recently updated
newest added

Hi @natanielruiz @tfygg , I am training the model again on `300W-LP` dataset with filtered filenames. There is high fluctuation in the training loss as mentioned in previous issues as...

![image](https://github.com/natanielruiz/deep-head-pose/assets/70904270/f33fc6b1-d04f-40df-b402-87e8b3613c5a) The inference speed of each frame is very slow, and the graphics card is NVIDIA's RTX 3060 12GB

Hi, I request you to add this to this repo if you feel relevant. Thanks! It uses mtcnn for face detection. https://colab.research.google.com/drive/1vvntbLyVxxBHoVN0e6-pfs7gB3pp-VUS?usp=sharing Thanks!

@natanielruiz Hi, the paper says: "In order to compare to Gu et al. [5] we train on three different 70-30 splits of videos in the BIWI dataset and we average...

Hello, What is the range of yaw and pitch of the head pose? What will be the estimated yaw and pitch be when the head is turned opposite to the...

I think the operation to clear the gradient is missing here

hello, I have some problem running the test_on_video_dlib.py I think the problem is that I use the wrong version of pytorch, could anyone please tell me the correct pytorch version?...

I am trying to run train_hopenet.py `python3 train_hopenet.py --dataset AFLW2000 --data_dir datasets/AFLW2000 --filename_list datasets/AFLW2000/files.txt --output_string er ` I got this error: Loading data. ``` /home/redhwan/.local/lib/python3.8/site-packages/torch/optim/adam.py:90: UserWarning: optimizer contains a parameter...

Dear authors of the code and GitHub community, can you please let me know about the preprocessing steps to make the data readable by the data loaders proposed in this...

ERROR: ![image](https://user-images.githubusercontent.com/80949842/195831149-ba05373e-06fc-4460-90ed-8db107ebeb97.png) I am completely confused. It seems like my labels are either -1 or bigger than num_classes. But I don't know why... It's just that I the label files...