Closed zsdonghao closed 3 years ago
I release the APIs to download or visualise MPII dataset in 1 line of code here: https://github.com/tensorlayer/tensorlayer/pull/482
import pprint
import tensorlayer as tl
img_train_list, ann_train_list, img_test_list, ann_test_list = tl.files.load_mpii_pose_dataset()
print(img_train_list[0])
pprint.pprint(ann_train_list[0])
for i in range(100): # show 100 images
image = tl.vis.read_image(img_train_list[i])
tl.vis.draw_mpii_people_to_image(image, ann_train_list[i], '_temp%d.png' % i)
OpenPose | Idea | |
---|---|---|
image size | 368x654 i.e. 9:16 | 244x244 ? |
CNN | VGG-19 | mobilenetV2 or others, see https://github.com/tensorlayer/tensorlayer/issues/416 |
CNN | Residual Squeeze | (1), (2) |
I think where you can achieve better results easier is in post-processing. At least in tf-pose-estimation that's the current bottleneck. maybe implementing a c++/cython multiprocessing module for that can be enough
Implementing openpose in https://github.com/tensorlayer/tensorlayer/pull/765
I'm trying to implement a real time pose estimation(mulit-person) on mobile. For the mobile performence, I'm trying to quantize the model.
@1icas I think mobilenet is a easier approach than quantisation..
@zsdonghao yes,i know. But it's not satisfy the performance requirement. Also i'm very interested in quantisation.
Or do you have other suggesstion for model acceleration ?
A discussion for real-time (multi-person) pose estimation using TensorLayer and TensorFlow
Paper List
Existing code/resource
"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields"
provides some links in his github: ZheC/Realtime_Multi-Person_Pose_Estimation, [video], [training log]pip3 install pycocotools
, see keras_Realtime_Multi-Person_Pose_EstimationBlog
About Data Augmentation
Others