human-pose-estimation.pytorch

human-pose-estimation.pytorch copied to clipboard

test on my own dataset

1

when i try to test on test2017 dataset, i got the following information: => num_images: 20288 => load 0 samples => Writing results json to output/coco/pose_resnet_50/256x192_d256x3_adam_lr1e-3/results/keypoints_test_results.json | Arch | Null...

WangZhaoxue

/home/gyc/anaconda3/envs/py36/lib/python3.6/site-packages/torch/nn/functional.py:52: UserWarning: size_average and reduce args will be deprecated, please use reduction='elementwise_mean' instead. warnings.warn(warning.format(ret)) => load 2958 samples => fail to read data/mpii/images/005808361.jpg => fail to read data/mpii/images/080936116.jpg => fail...

gyc521zsc

FileNotFoundError: [Errno 2] No such file or directory: 'data/mpii/annot/valid.json'

1

/root/anaconda3/bin/python /home/dell/下载/human-pose-estimation.pytorch-master/pose_estimation/valid.py --cfg ../experiments/mpii/resnet152/256x256_d256x3_adam_lr1e-3.yaml --flip-test --model-file ../models/pytorch/pose_mpii/pose_resnet_152_256x256.pth.tar => creating output/mpii/pose_resnet_152/256x256_d256x3_adam_lr1e-3 => creating log/mpii/pose_resnet_152/256x256_d256x3_adam_lr1e-3_2019-03-20-21-12 Namespace(cfg='../experiments/mpii/resnet152/256x256_d256x3_adam_lr1e-3.yaml', coco_bbox_file=None, flip_test=True, frequent=100, gpus=None, model_file='../models/pytorch/pose_mpii/pose_resnet_152_256x256.pth.tar', post_process=False, shift_heatmap=False, use_detect_bbox=False, workers=None) {'CUDNN': {'BENCHMARK': True, 'DETERMINISTIC': False, 'ENABLED': True},...

c1a1o1

I just follow the step to test coco dataset,the output is person's keypoints rather than connected joints.I have no too much experience about pose estimation. Don't you put out the...

wmx17806275903

Hi all, i have a problem when connect cuda with the codes by running "make" in (ROOT)/lib. They search cuda path at the host (e.g. /usr/local/cuda-9.0/), but in anaconda environment,...

soonchanpark

how to do the NMS between bounding boxes from joints propagation and a detector?

6

I was trying to reproduce your algorithm of the tracking part. But there's a really specific detail that I can't figure out how to manage to complete. You got the...

aaab8b

The use of split in the loss function? What is it for?

1

This code is in core/loss.py: `heatmaps_pred = output.reshape((batch_size, num_joints, -1)).split(1, 1)` I was just wondering what is the `split(1,1)` for? I From my understanding it splits the tensor into equally...

jahdiel

the error about tensorboard is happen when i run the train.py

3

here is log of error: -------------------------------------------- /home/boyun/anaconda3/envs/tc0.40/bin/python /home/boyun/PycharmProjects/Humanpose/MultiPose/MSRA_BASELINE/human-pose-estimation.pytorch/pose_estimation/train.py => creating output/coco/pose_resnet_101/384x288_d256x3_adam_lr1e-3 Namespace(cfg='experiments/coco/resnet101/384x288_d256x3_adam_lr1e-3.yaml', frequent=5, gpus=None, workers=None) => creating log/coco/pose_resnet_101/384x288_d256x3_adam_lr1e-3_2019-01-24-14-54 {'CUDNN': {'BENCHMARK': True, 'DETERMINISTIC': False, 'ENABLED': True}, 'DATASET': {'DATASET': 'coco', 'DATA_FORMAT': 'jpg',...

do-oo

Re-Implementation in GluonCV

4

Hi, We have re-implemented the estimation model in [GluonCV](https://gluon-cv.mxnet.io/). We also achieve slightly higher AP by using pre-trained ResNet with higher accuracy: https://gluon-cv.mxnet.io/model_zoo/pose.html Besides, you mentioned in https://github.com/Microsoft/human-pose-estimation.pytorch/issues/2 that the...

hetong007

First of all , thank for you awesome project. For to use the pose estimator on real-time, I insert YOLOv3 to get human bbox, now I want test the AP...

lxy5513