human-pose-estimation.pytorch
human-pose-estimation.pytorch copied to clipboard
microsoft
The project is an official implement of our ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking(https://arxiv.org/abs/1804.06208)"
I try to train simplebaseline(resnet18) in caffe framework. However, the loss decreases so slowly and the prediction is a little bad.
In your paper, you used pretrained model on COCO and then fine-tuned on Posetrack. But their points format are different, so there must be a conversion otherwise the model could...
# When I excuted the following cmd `python3 pose_estimation/train.py --cfg experiments/mpii/resnet50/256x256_d256x3_adam_lr1e-3.yaml ` # But got error: => loading pretrained model models/pytorch/imagenet/resnet50-19c8e357.pth Traceback (most recent call last): File "pose_estimation/train.py", line 206,...
Hi, thank you for your well done jobs. I want test the caffe-style model on val2017. where I can download the caffe-style model you have trained ,such as "256x192_pose_resnet_50_caffe "....
**Please Update the readme and highlight the validataion method whether use the GT bbox during the training**. This bothers lot of people. https://github.com/microsoft/human-pose-estimation.pytorch/issues/55 https://github.com/microsoft/human-pose-estimation.pytorch/issues/58
Your test.json contains 7247 test samples while the original .mat file contains 11731 test samples. Can you explain the discrepancy? In effect, can you tell me how to start from...
I plan to implement the code myself and wanted to ask if there was any information about inference time. I couldn't find anything about it.
Should I follow the guidelines in the paper "Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour"?
When I run the training code, only gpu '0' is loaded. How can I run with all 4 gpus?
