Matija Teršek

Hey @sevocrear, how exactly have you managed to export the model to ONNX? I've tried removing NMS and exporting the model without it (I'd do it after computing the output),...

> Hi @tersekmatija , have you removed NMS totally? In my implementation, I just changed the CUDA NMS to python NMS function (which, of course, is much slower). And then...

@hwang12345 It seems that @sevocrear uses it in his forward method and he managed to export it.

You can get per-layer benchmarks the easiest using `benchmark_app`. You can install `openvino-dev` 21.4 or 22.1 Python package instead of installing locally, and then call something like below with `-pc`...

Hi @schreiterjp, could you try using SDK version `1.1.8`. I think draw method got updated in the latest one `1.2.0`.

Hi @pinolo7 , could you try adding `box_detections_per_img=25` and `rpn_post_nms_top_n_test=100` arguments when calling `maskrcnn_resnet50_fpn`. This reduces default number of detections per image from 100 to 25, as well as reduces...

Thanks, I am pretty sure those were the settings I used for export, but I'll check whether I still have the export script that I used here and get back...

I am looking at the XML from the experiment, I think the correct settings should be `box_detections_per_img=20, rpn_post_nms_top_n_test=50`. Could you try this and share the XML of the model if...

Hey, I noticed some discrepancies in the Detect layer when comparing yours and the one from our ZOO. Will have to investigate. Best, Matija

Hey, I re-checked this and I can confirm this was my export script: ``` import torchvision.models as models import torch # Create model model = models.detection.mask_rcnn.maskrcnn_resnet50_fpn(pretrained=True, box_detections_per_img=20, rpn_post_nms_top_n_test=50) model.eval() print(model(torch.rand([1,...