Error received while trying to chip and train

[georgeper2001]

I ran the following commands which is using Object detection: first: "docker run -it --rm -v $HOME/.aws:/root/.aws:ro -v $(pwd):/workdir -w /workdir quay.io/azavea/raster-vision:pytorch-0.20 /bin/bash"
then: "rastervision run local chev_object_tst.py -a root_uri /tmp/hello -a cowc cowc.csv -a batch_size 16 -a epochs 32 -a arch FasterRCNN analyze chip train"
I got the following error: "RuntimeError: DataLoader worker (pid 611) is killed by signal: Bus error. It is possible that dataloader's workers are out of shared memory. Please try to raise your shared memory limit.
make: *** [/tmp/hello/Makefile:12: 2] Error 1"
Any idea why?

[AdeelH]

You will need to pass the --ipc=host option to docker run. Example:

raster-vision/docker/run

Lines 141 to 142 in db46a7e

	docker run \
	${RUNTIME} ${NAME} --rm --ipc=host -it \