@wuming 那两个文件的权限改一下
Posts made by george
-
RE: Introduction to COOL PI CM5 interface
git://git.kernel.org/pub/scm/linux/kernel/git/firmware/linux-firmware.git https://git.kernel.org/pub/scm/linux/kernel/git/firmware/linux-firmware.git https://kernel.googlesource.com/pub/scm/linux/kernel/git/firmware/linux-firmware.git
-
RE: Introduction to COOL PI CM5 interface
@wuming 确认你的/lib/firmware路径有没有这个文件iwlwifi-ty-a0-gf-a0-59.ucode
-
RE: CoolPi CM5 intel AX200 Adaptation record
@wuming 你的模组需要的固件是iwlwifi-ty-a0-gf-a0-59.ucode
sudo cp ./linux-firmware/iwlwifi* /lib/firmware -
CoolPi CM5 intel AX200 Adaptation record
-
JD bought a cheaper one
-
The kernel code has been updated to the latest version, including the following submission records: commit 4235ffbfee944d67d14d8143762e0a9314af8ee3
-
Compile the kernel and copy it to the device,Remember that modules.tar.gz needs to be decompressed
sudo cp ./out /boot/firmware -R sudo tar -zxvf ./out/modules.tar.gz -C /lib sudo reboot
-
Confirm that the network card is properly recognized,Confirm Bluetooth recognition is normal.
-
Download WiFi/BT firmware
git clone git://git.kernel.org/pub/scm/linux/kernel/git/firmware/linux-firmware.git sudo cp -rfp ./linux-firmware/iwlwifi-cc-a0* /lib/firmware/ sudo cp -rfp ./linux-firmware/intel /lib/firmware/ -R sudo reboot
- Actual measurement effect
-
-
RE: rk mpp平台YUV格式支持问题
@jugg 关于I420格式的问题,环境变量增加GST_MPP_NO_RGA=0
关于黑边和数据大小不对的问题,编码器数据需要四字节对齐,比如:1920X1080 需要设置为1920X1088 -
Coolpi 4b driver eDP LCD
Some users have been asking what kind of LCD can be compatible with the 4b machine. Due to compatibility with Raspberry Pi, the MIPI interface cannot support high resolution screens. However, the 4b machine has a DP interface, which can drive the eDP interface LCD with a simple transfer, and the software does not need to be modified. The actual debugging effect of the adapter board is as follows:
-
RE: Introduction to COOL PI CM5 interface
- 编译完成out目录文件拷贝到机器/boot/firmware路径
sudo cp ./out/* /boot/firmware -R
- 解压modules.tar.gz 到机器/lib 路径
sudo tar -zxvf /boot/firmware/modules.tar.gz -C /lib
-
Quickly build an RKNN environment
To facilitate users' development based on RKNN, the RKNN C and Python environments have been made into PPA installation sources. Running the following command can complete the installation and setup.Currently, only the ubuntu22.04 environment is supported, and other versions will be added in the future.
sudo add-apt-repository ppa:george-coolpi/rknpu sudo apt update sudo apt-get install rknpu2
Environmental testing
- Python
cd /usr/share/rknn-toolkit2/examples/inference_with_lite/ python3 test.py
The following results indicate that the environment was successfully built
--> Load RKNN model done --> Init runtime environment I RKNN: [11:36:49.473] RKNN Runtime Information: librknnrt version: 1.4.0 (a10f100eb@2022-09-09T09:07:14) I RKNN: [11:36:49.474] RKNN Driver Information: version: 0.8.2 I RKNN: [11:36:49.475] RKNN Model Information: version: 1, toolkit version: 1.4.0-c15f5e0b(compiler version: 1.4.0 (c73777b51@2022-09-05T12:06:01)), target: RKNPU v2, target platform: rk3588, framework name: PyTorch, framework layout: NCHW done --> Running model resnet18 -----TOP 5----- [812]: 0.9996696710586548 [404]: 0.0002492684288881719 [657]: 1.632158637221437e-05 [833]: 1.0159346857108176e-05 [466 895]: 9.02384545042878e-06 done
- C
sudo apt-get install git cmake -y git clone https://gitee.com/yanyitech/rknpu2.git cd rknpu2/examples/rknn_mobilenet_demo ./build-linux_RK3588.sh cd install/rknn_mobilenet_demo_Linux/ ./rknn_mobilenet_demo model/RK3588/mobilenet_v1.rknn model/dog_224x224.jpg
The following results indicate that the environment was successfully built
model input num: 1, output num: 1 input tensors: index=0, name=input, n_dims=4, dims=[1, 224, 224, 3], n_elems=150528, size=150528, fmt=NHWC, type=INT8, qnt_type=AFFINE, zp=0, scale=0.007812 output tensors: index=0, name=MobilenetV1/Predictions/Reshape_1, n_dims=2, dims=[1, 1001, 0, 0], n_elems=1001, size=1001, fmt=UNDEFINED, type=INT8, qnt_type=AFFINE, zp=-128, scale=0.003906 rknn_run --- Top5 --- 156: 0.984375 155: 0.007812 205: 0.003906 -1: 0.000000 -1: 0.000000
-
RE: Coolpi support 32GB of RAM
@Mz3D-0 The new machine will default to the WIFI&BT module of AP6275S. You can also replace other models of 1T1R modules, and there will be multiple models for users to choose from.
-
RE: Coolpi uses UMS to update the system
@edwardzhou 先确认WIN是否OK,MAC暂时还没有测试,这个回头我们跟一下。
-
RE: Introduction to COOL PI CM5 interface
@wuming 你的内核版本不对!内核请更新到最新,使用cm5-evb-v11的配置编译
-
RE: coolpi4b 在EMMC使用时,40pin 5V是否有功耗限制?
@AugustRobot_Zou 确认你的TTL转RS232模块使用的芯片是3.3V的还是5V的,如果是5V的可能存在漏电导致系统3.3V电压升高,进而影响EMMC正常工作。解决办法使使用3.3V的模块。
-
RE: coolpi4b 在EMMC使用时,40pin 5V是否有功耗限制?
@AugustRobot_Zou 应该不是这里5V电源导致的。提供一下不能启动的串口日志。
-
RE: Introduction to COOL PI CM5 interface
@george WIFI固件下载链接如下 ,根据日志信息把对应firmware拷贝到机器/lib/firmware目录即可。
git clone git://git.kernel.org/pub/scm/linux/kernel/git/firmware/linux-firmware.git
-
RE: Introduction to COOL PI CM5 interface
@wuming 驱动默认已经集成。只需要拷贝BIN文件进去。晚点发链接出来,先帮忙上传一下dmesg