-
hi, it seems lite-hrnet semantic segmentation has higher precision than your bisenetv2. will the code relase. wait in hope.
-
@wuyefeilin
Is there a ready demo code to run "humanseg-mobile" on Android?
1. I checked the [Paddle-Lite](https://github.com/PaddlePaddle/Paddle-Lite) repo, but I don't seem to find ready demo…
-
**Describe the bug**
I downloaded the checkpoint from mmpose modelzoo. I used the pytorch2onnx.py and failed.
**Reproduction**
Use command:
```
python tools/deployment/pytorch2onnx.p…
-
测试机型：华为 mate30 pro 5G
PaddleSeg :Release 2.2
模型生成方式：
1.paddle_lite_opt --model_file=./model.pdmodel --param_file=./model.pdiparams --quant_model=true --quant_type=QUANT_INT8 --valid_targets=arm --o…
-
```bash
/data1/control/project/mmpose/mmpose/models/backbones/utils/channel_shuffle.py:20: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't rec…
-
why don't you use lite-hrnet as your backbone？ limited performence or lite-hrnet isn't suitable in this paper
-
**Describe the bug**
Unable to build onnxruntime due to this error. It says could not find git for clone of pybind11. I looked at the call stack provided
```
CMake Error at C:/Program Files/CMake/…
-
Traceback (most recent call last):
File "tools/train.py", line 17, in
from models import build_posenet
File "/home/sa/workspace/zap/Lite-HRNet/models/__init__.py", line 1, in
from .b…
-
1. **HumanSeg**
I noticed that [HumanSeg](https://github.com/PaddlePaddle/PaddleSeg/tree/develop/contrib/HumanSeg) uses HRNetV2-W18-SMALL-v1.
Is it possible to use HRNetV2-W18-SMALL-v2 in the H…
-
#### 问题描述
官方TIM-VX例子在RV1109上运行，只有tm_classification_timvx能运行，其他都报错
1) yolov4_tiny_timvx
` ./tm_yolov4_tiny_timvx -m /userdata/yolov4-tiny_uint8.tmfile -i /userdata/ssd_dog.jpg`
输出
tengine-lite l…