Stefano Pini
Stefano Pini
Looking at the order of the indexes in the output of `get_max_preds` https://github.com/microsoft/human-pose-estimation.pytorch/blob/18f1d0fa5b5db7fe08de640610f3fdbdbed8fb2f/lib/core/inference.py#L39-L40 This line https://github.com/microsoft/human-pose-estimation.pytorch/blob/18f1d0fa5b5db7fe08de640610f3fdbdbed8fb2f/lib/core/evaluate.py#L55 shouldn't be as following (i.e. with inverted h and w)? ``` norm = np.ones((pred.shape[0],...
@aFewThings thank you for looking at it! That's true, it doesn't result in any error as long as the heatmaps are squared. However, the same code is used also in...
Hi! There isn't a Test script for COCO yet, but it should be easy to adapt the [COCOTrain class](https://github.com/stefanopini/simple-HRNet/blob/master/training/COCO.py) and create a COCOTest class predicting the OKS score. I'll try...
Hi @basicvisual , thank you for reporting that interesting repository, it would be definitely worth a try. Unfortunately, at first glance it looks like a quite different architecture thus it...
Hi, I'm happy you found the project useful! There was some discussion in the past on how to train on custom datasets (see issue #56 ). I'm not aware of...
Hi! I'm sorry for the late reply. I've checked and OpenPose, in the 19-keypoint version (i.e. without additional keypoints for feet), provides the same keypoints of COCO plus an additional...
Hi @Mystickal , sorry for the late reply. Unfortunately, I haven't found the time to work on this yet. In SimpleHRNet.py, you will have access to all the keypoints after...
Hi @basicvisual , awesome! Are you willing to share the notebook so that I can add it to this repository (with proper referencing)? Regarding running it on GPU, have you...
Sure! If you are willing to share the notebook, feel free to share it at your convenience/when you think it is ready! 🙂 Regarding the issue, that's weird. It should...
Wonderful, thank you! I've been able to have it working and it did run on GPU. I just had to switch twice from CPU to GPU runtime, but after that...