Summary: 46 instances, 42 unique

Text	Count
// TODO remove the dependency on input and use instead its sizes -> save memory	2
# TODO: parallelize	1
# FIXME remove check once we have better integration with device	1
# TODO Ideally, just remove this and let me model handle arbitrary	1
# TODO think about a representation of batch of boxes	1
# TODO use size instead of scale to make it robust to different sizes	1
# TODO Yang: solve this issue in the future. No good solution	1
# TODO maybe add an API for querying the ws / hs	1
# TODO this doesn't look great	1
# TODO should I split them?	1
// TODO raise error if not compiled with CUDA	1
# FIXME: CPU computation bottleneck, this should be parallelized	1
# TODO maybe push this to nn?	1
# FIXME ideally this would be achieved with a CombinedLRScheduler,	1
TO_REMOVE = 1  # TODO remove	2
# TODO:Yang: Not easy to do. Because the numbers of detections are	1
THCState *state = at::globalContext().lazyInitCUDA(); // TODO replace with getTHCState	1
# TODO: Issue #527 - bad Masker interface	1
# TODO might be better to add an extra field	1
// TODO add more checks	1
# TODO need to make the use_07_metric format available	1
# TODO do this properly	1
# TODO: specify init for the above	1
# TODO: Use JIT to replace CUDA implementation in the future.	1
# TODO check if want to return a single BoxList or a composite	1
# TODO most of this can be made out of the loop for	1
# TODO: not parallel! parallelize this process safely	1
# TODO make this nicer, this is a direct translation from C2 (but removing the inner loop)	1
# TODO should I filter empty boxes here?	1
# TODO remove and use only the Keypointer	1
# TODO check if this is the right one, as BELOW_THRESHOLD	1
# TODO rename x to roi_box_features, if it doesn't increase memory consumption	1
# TODO redundant, remove	1
# TODO:  Is this JIT compatible?	1
// TODO make it in a common file	3
# TODO replace with get_img_info?	1
# TODO: Implement the sigmoid version first.	1
torch.cuda.empty_cache()  # TODO check if it helps	1
# TODO very similar to filter_results from PostProcessor	1
# TODO maybe remove this and make it explicit in the documentation	1
# FIXME remove this once c10d fixes the bug it has	1
// TODO improve this part	1