deep-head-pose
deep-head-pose copied to clipboard
natanielruiz
:fire::fire: Deep Learning Head Pose Estimation using PyTorch.
When i download the 300-lp dataset, i find that there are AFW, HELEN and other folders. How to generate the data_dir and filename_path?
Thank you for your work firstly. Q:I test alpha1.pkl and robust_alpha1.pkl with same dataset,but get obvious different mean average error.why this happened? Did you train alpha1.pkl and robust_alpha1.pkl with different...
Hi and thanks for the great work :) I have a question about the the table 1 and 2 in your paper. Some networks like 3DDFA and FAN can only...
!python code/test_on_video_dlib.py --snapshot models/hopenet_robust_alpha1.pkl --face_model dlib-models/mmod_human_face_detector.dat --video data/sample_video.mp4 --output_string new_output --n_frames 2000 --fps 6 Loading snapshot. Loading data. /opt/anaconda3/lib/python3.7/site-packages/torchvision/transforms/transforms.py:207: UserWarning: The use of the transforms.Scale transform is deprecated, please use...
I used the train code to train a resnet-18 model last year and it did work ,the predictions were normal , but recently the model does not work ,3 predictions...
https://github.com/natanielruiz/deep-head-pose/blob/175dff7849b3cdb342b48253bba401a7a9ef0e87/code/train_hopenet.py#L58 Hi, in your code, you use model.named_modules() to get the parameter generator, thus control the learning rate of different layers, but I find that in a model that contains...
Hi, @natanielruiz Sorry to bother you, but here's a problem. Could pls. take a look at it? It won't match when parse the ypr for [BIWI dataset](https://data.vision.ee.ethz.ch/cvl/gfanelli/head_pose/head_forest.html#db). Take following sample...
Hello,thank you for your great work.How are their positive and negative directions defined when using roll, pitch, and yaw in function" draw_axis(img, yaw, pitch, roll, tdx=None, tdy=None, size = 100)"?
After loosely cropping the input images, I see that the cropped images have different sizes. And they are not resized to the same size. Am i correct? If yes, Is...
Metadata
Owner
Metadata
:fire::fire: Deep Learning Head Pose Estimation using PyTorch.