deep-high-resolution-net.pytorch
deep-high-resolution-net.pytorch copied to clipboard
leoxiaobin
The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"
How do I feel when I encounter this problem while training coco? cv2.error: OpenCV(3.4.1) /io/opencv/modules/imgproc/src/color.cpp:11115: error: (-215) scn == 3 || scn == 4 in function cvtColor.
另外一份开源代码：https://github.com/HRNet/HigherHRNet-Human-Pose-Estimation
i refer to the test.py code and write a single image test code demo. the demo code will forward a single image and get the preds points, finally i draw...
Hello, could you provide the code to convert the mpii mat annotation into your json file? Thanks.
I'm trying to inference HRNet with Volleyball dataset to extract pose keypoints. Since the dataset is annotated with manual BBs. I did slight modifications for the `demo/inference.py` file and the...
Can anyone specify what is the BB format expected by HRnet? is it `(x1,y1,x2,y2)` or `(x,y,w,h)` Are the BBs should be normalized by the image `w,h` or to use absolute...
When using the HRNet network to test my own data set, if multiple people are detected in the image through faster_rcnn, but I only select the coordinate return value of...
hi, i use test.json to creat a [7247. 16. 2] pred.mat, can i submitt pred.mat to mpii official website to have a test result?
Hello, I used the network model in this article to estimate the gaze point, but the loss function is already very small during the training process, but there is no...
I want to know the inference speed (like FPS) on cpu only machines, but I don't know how to do. Someone solved it?
Metadata
Owner
Metadata
The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"