-
- 用CPU 2.0-beta版本可以跑CPU训练，但觉得比较慢，就想换成GPU
- 安装了GPU 2.0-beta版本后，无法跑GPU训练，提示`CUDA driver version is insufficient for CUDA runtime version`。
```
$ python tools/train.py -c configs/yolov3_mobilenet_v1_r…
-
```
>
报错信息
E:\baiduai\PaddleDetection>python -u tools/train.py -c configs/mask_rcnn.yml --use_vdl=true --vdl_log_dir=vdl_dir/scalar --eval -o use_gpu=true
Traceback (most recent call last):
…
-
训练命令：
```
python tools/train.py -c configs/mobile/ssdlite_mobilenet_v3_large.yml --eval -o use_gpu=false
```
报错提示：
```
Traceback (most recent call last):
…
-
```
2021-03-07 13:42:51,049-INFO: Infer iter 10
Traceback (most recent call last):
File "infer.py", line 261, in
main()
File "infer.py", line 211, in main
mask_results, lmk_results)…
-
F:\anaconda\Lib\site-packages\PaddleDetection>python tools/train.py -c configs/yolov3_mobilenet_v1_roadsign.yml --eval -o use_gpu=false
2021-02-03 11:52:57,174-INFO: If regularizer of a Parameter has…
-
OsmAnd version: 3.5.5 (from 2019-11-28)
Reproduction instructions:
1. Open OsmAnd app.
2. Set the "Units of length" setting in "Settings > Browse map (App profile) > General Settings" to "Kilomet…
-
It would be nice to have a Portuguese translation of the app. :portugal:
The _Translation Editor_ in [_Android Studio_](https://developer.android.com/studio/) let's you easily identify the missing…
-
- 操作：PaddleDetection在线Serving部署
[https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0-beta/deploy/serving](url)
- docker中执行
```
python -m paddle_serving_server_gpu.serve --model …
-
ubuntu20系统，安装的CPU版本
wangjh@ubuntu:~/work/paddlepaddle/paddledetection/PaddleDetection$ python3 tools/train.py -c configs/yolov3_mobilenet_v1_roadsign.yml --eval -o use_gpu=false
/home/wangjh/.loca…
-
It would be nice to have a Swedish translation of the library. :sweden:
The _Translation Editor_ in [_Android Studio_](https://developer.android.com/studio/) let's you easily identify the missing …