Open peepo opened 9 years ago
The project doesn't have a CUDA path, so it won't take advantage of the Jetson hardware. Caffe might be a good alternative, if it's able to run on the system.
The Raspberry Pi example needs an 'sudo' at the start of the command, to get access to the raw GPU interface.
The Jetson port shouldn't be too complex. The core acceleration is wrapped by BLAS interface. But will CUDA run-time be as popular as GLES2.0/3.0 on Android device? -Andy
please let me know whether you will be able to support Jetson, and any information armv7 192 cores CUDA 6.0 etc....
cd ../LinuxLibrary/ $ sudo ./install.sh libjpcnn installed $ cd ../examples/SimpleLinux/ $ make gcc -o deepbelief ./main.c -L/usr/lib -ljpcnn /usr/lib/libjpcnn.so: file not recognized: File format not recognized collect2: error: ld returned 1 exit status make: *\ [deepbelief] Error 1
$ cd RaspberryPiLibrary/ $ sudo ./install.sh libjpcnn installed $ cd ../examples/SimpleLinux/ gcc -o deepbelief ./main.c -L/usr/lib -ljpcnn $ ./deepbelief Can't open device file: /var/lib/jpcnn/char_dev