-
Hello,
I am getting in touch with you again to raise a problem I am running on, that is reccurent when I try to set up the posenet model to too high settings:
https://www.youtube.com/watch?v=4oRdq…
-
#22
PoseNet 是一个先进的姿势预测模型，可从图像数据中提取非常精准的姿势数据（即便在图像模糊不清、分辨率低或仅为黑白色的情况下仍能做到）
Move Mirror 是一项 AI 实验，能够检测您的姿势，并将检测到的动作与全球成千上万张图像进行匹配
# Reference
- [ ] [Move Mirror：使用 TensorFlow.js 在浏览器中预测姿势之 AI 实验](h…
-
Upon running the infer.py script with the pre-trained openpose-lightweight resnet50 model, at times the pose estimation results repeat certain parts, and also omit certain parts.(refer attached images…
-
May I know is it possible to use the Teachable machine exported pose model to integrate with the [Tensorflow React Native](https://github.com/tensorflow/tfjs/tree/master/tfjs-react-native) module?
…
-
if imageSize equal 224， it's realtime，but keypoint‘s coordinate is incor。
how can i do to make the keypoint's coordiante coorect？thaks a lot！
-
Hi,
You say a feed-forward inference on this model is very fast--2ms on a Titan Xp. Do you think the speed would hold up on a recent Android device (like a Google Pixel 4)? I'm looking to do real-t…
-
When I evaluate the pre-trained models for the ICVL and NYU datasets using `main_icvl_posereg_embedding.py` and `main_nyu_posereg_embedding.py`, I get the mean errors 6.41 mm and 4.1 mm whereas at yo…
-
how to convert to onnx, I meet the problem,
assert target.dim() == 4 and target_weight.dim() == 3
AttributeError: 'NoneType' object has no attribute 'dim'
code:
model = build_posenet(cfg.mo…
-
Hi, this is Jaehyun Lim
I have a problems in learning rate scheduling to reproduce the results on the paper using sgd (as in the paper) (see https://github.com/lim0606/caffe-posenet-googlenet).
As…
-
Hi, I trained the Monodepth2 on KITTI Odometry Dataset twice, the first one with flip augmentation enabled and the second one with flip augmentation disabled, and got very different trajectories on te…