Dustin Franklin

Hmm I have not done this myself @eanmikale - basically I've moved all my training to PyTorch (no longer using DIGITS), and I export the ONNX directly from PyTorch checkpoints....

Hi @Unweptpit, not sure what would be causing this - are you double-clicking this shell script, or running it from terminal? Is there any output from the program? What happens...

What if you use `xterm -hold -e "python3 detect.py"` in your script instead? or gnome-terminal or lxterminal, ect https://stackoverflow.com/a/23105350 https://askubuntu.com/questions/394897/double-click-on-sh-file-to-open-terminal-and-execute-series-of-commands-in-it

Hmm okay - sorry, I don't know what is happening Can you try making a `.desktop` launcher like shown here: https://stackoverflow.com/a/23105350

Hi @namaws, the default number of training epochs with train_ssd.py is 30 if you don't specify it (with the `--epochs` command-line option). You may need more however if your model...

IIRC I recommend 100 images per class minimum

It shouldn't typically take that long, no. My guess is that your board is low on memory and is swapping out. Did you follow these steps? * https://github.com/dusty-nv/jetson-inference/blob/master/docs/pytorch-transfer-learning.md#mounting-swap * https://github.com/dusty-nv/jetson-inference/blob/master/docs/pytorch-transfer-learning.md#disabling-the-desktop-gui

> I've mounted the swap space for 4GB before I trained a few days ago. Do I need to do it everytime before I train? If you edited `/etc/fstab` like...

It appears that you have built this for x86 - I haven't yet ported gstDecoder to x86, so it will be using gstreamer elements that are only on Jetson and...

I haven't used virtual environments with this project before, so I'm of limited help with this, sorry about that. However after installing jetson-inference, can you make the virtualenv with `virtualenv...