Q-engineering

Also in the forward pass, I had to make an educated guess about memory usage, as the cudnnGetConvolutionForwardAlgorithm is also missing in cuDNN 8. (see line 141 src/caffe/layers/cudnn_conv_layer.cpp)

see #6970 for a cuDNN 8.0 solution

Please see [this pull request](https://github.com/Tencent/TNN/pull/1825)?

@Filmimagine , Where is it going wrong? When you have flashed the SD card and put it in the Jetson Nano, what do you see on the screen? By the...

@Filmimagine , I'm not sure if I understand it right. First you need the download the JetsonNanoUb20_2.img.xz onto your computer is a folder. Save the file in a folder. For...

@Filmimagine, That's normal behavior. The SD burner allocates a 32 GB partition on the card and writes its content byte by byte. The other 32 GB (in case of a...

Sorry, the SD-image is only suitable for the 4 GB Jetson Nano.

Sorry, you can not install CUDA 11 on a Jetson Nano, due to low-level incompatibility. The 'regular' CUDA version is 10 and is already installed. No need to use the...

nvcc should be located in folder /usr/local/cuda/bin/. Please incorporate the location into your PATH string

Tip: ask chatGPT. It can give valuable answers. In your case: The error you're encountering indicates that the `libmpi_cxx.so.20` shared library cannot be found. This library is part of the...