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"
According to the paper, HRNet is trained on 4GPUs, which have larger memory. If there are at most 8 GPUs available to me, but all have less than 12GB of...
for w32, it seems that the downsampling is done like this: input: 64X48 [32 channels] -> 32X24 [32 channels] -> 16X12 [128 channels] The downsample from 64X48 to 32X24 should...
Dear sir, Thanks for your excellent job of paper "Deep High-Resolution Representation Learning for Human Pose Estimation"! I have an question about the "exchange block": In the "Repeated multi-scale fusion"part,...
Hello, I can't reproduce result for setting "res101_256x256_d256x3_adam_lr1e-3" mpii pckh0.5: Paper report : 89.6 % From pretrained model (provided in this repo): 89.2% Retrain it: 88.87% Is there anything I...
I've read the dockerfiles and contains dependencies, is the docker used for getting the dependency files?
I want to test model on test-dev set, but the code pose_estimation/valid.py is only for testing on validation set (5000 images): So, I have a question: How to test the...
how can i solve such error? it happened when i train with mpii dataset.
Is the top down realized in the post process code, just judge the key point is in the predicted box. Right?
Does the HRNet Bottom up perform better than the HRNet this github report states?
heyyyyy, appreciate ur great work. Here is my problem, I couldn't see your pre-trained model, *models/pytorch/pose_mpii/pose_hrnet_w48_256x256.pth* in neither Google Drive or One Drive link. Will you upload it again? Or...
Metadata
Owner
Metadata
The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"