out of memory ConvertSegToBoundingBoxCoordinates
MancaZerovnikMekuc opened this issue · 0 comments
MancaZerovnikMekuc commented
Hey,
I am trying to run MASKRCNN inference on my data, but the process crashes in this line in utils.py:
rois = np.array([(clusters == ii) * 1 for ii in range(1, n_cands + 1)]) # separate clusters and concat
More specifically the process is killed, because of too high memory consumption.
It's because I have a large number of instances per one test volume (around 400) and volumes of sizes 256^3 so the previous line tries to allocate (256^3)*400 booleans.
Do you have any suggestions on how to solve this problem?