-
Comment
-
### 问题确认 Search before asking
- [X] 我已经查询[历史issue](https://github.com/PaddlePaddle/PaddleDetection/issues)，没有报过同样bug。I have searched the [issues](https://github.com/PaddlePaddle/PaddleDetection/issue…
-
用arm cpu跑tinypose demo，picodet model采用320*320分辨率，tinypose model采用官网文档128 96和 256 192 两种分辨率分别尝试，手机上运行 ./main det_runtime_config.json ，demo.jpg采用官方包里面的640x404的行人jpg图片，log 信息如下：
注意 ./demo.jpg The number…
-
您好，paddledetection中的关键点检测是否有详细的yml参数文件的解释说明？因为是刚接触关键点检测问题，我要做的不是人体的关键点，是物体的关键点检测，但是不知道如何修改配置参数
我看hrnet、lite_hrnet、tiny_pos中的architecture都是TopDown**，这样的方式需要前面接目标检测吗？标注时需要把目标的bbox也标注吗？
然后对于配置文件中的 nu…
-
D:\Anaconda3\envs\opencv\lib\site-packages\tensorboard\compat\proto\tensor_shape_pb2.py:23: DeprecationWarning: Call to deprecated create function FileDescriptor(). Note: Create unlinked descriptors i…
-
Hi,
I compiled Tengine and my build install directory looks like:
```
dan@antec:~/Khadas/utils/Tengine-Lite/build/install$ tree
.
├── bin
│ ├── tm_classification
│ ├── tm_classification…
-
Hello! I trained Lite HRNet on MPII,I meet a similar question as #300 but still can't sovle it, I can train it but when I evaluate the model，error occurs. I’d really appreciate it if you could help m…
-
it is amazing lightweight work, would u consider add a script to test a img with model?
as demo.py like [https://github.com/HRNet/HigherHRNet-Human-Pose-Estimation/pull/28/commits/57c1f30a5d5e3d789dc…
-
Hi Developers,
The problem I'm facing is that, I cannot export a batch size 4 model in ONNX because it will exceed the 2 GB proto buffer limit, so I can only export an ONNX with batchsize =1 (which…
-