K.Kuai Jin

RV1126 rockchip_npu加速运行报错

3

- 标题：RV1126 rockchip_npu加速运行报错 - 版本、预测库信息：    1）Paddle Lite 版本：PaddleLite-generic-demo 自带的库    2）Host 环境：Ubuntu 18.04    3）运行设备环境：RV1126 非EVB    4）预测后端信息： /bin/sh: line 1: 2619 Segmentation fault (core dumped) - 预测信息    1）预测 API：C++    2）预测选项信息：armv7 rknpu    3）预测库来源：官网下载...

MACE运行mtcnn的Pnet不认PRELU这种activation

6

Before you open an issue, please make sure you have tried the following steps: 1. Make sure your **environment** is the same with (https://mace.readthedocs.io/en/latest/installation/env_requirement.html). 2. Have you ever read the...

is it support aarch64

2

is it support aarch64? which driver should i select in aarch64.

electrum server install ImportError

3

I have a trouble when i install the electrum server.The electrum server install document reference(https://github.com/spesmilo/electrum-server/blob/master/HOWTO.md).everything has been done before run "electrum-server start" command to launch electrum server.but it print an...

How can i train landmarks

1

@Seanlinx Sorry for trouble you. Do you have any suggestion about training the face landmarks. The wider dataset not contains the landmarks annotations, do you know some dataset with the...

请问dubbo.config.js的参数和格式是怎么样的 @binlaniua

npu用户态驱动怎么更新

5

按文档更新了NPU驱动，报了个错误 [ 1] HAL user version 6.4.3.5.293908 [ 2] HAL kernel version 6.4.3.5.293908 Segmentation fault (core dumped) 查文档是由于用户态驱动没有更新

evaluating widerFace validation datesets mAP problem

4

Hi, @dechunwang I try to evaluate widerFace validation datasets(easy medium hard) with your pretrained mode, and just get this mAP(0.910, 0.897, 0.620) VS origin SSH(0.919, 0.907, 0.814)。Why the hard sets...

train方法矩阵批量更新参数

1

@hankcs 我看最后train方法遍历样本，每个实例经过BP去更新w和b参数值，这一步能不能通过矩阵批量计算。 这样速度是否会更快。