Xie.Tao

using centermask_V_99_eSE_FPN_ms_3x.yaml and centermask-V2-99-FPN-ms-3x.pth it occurs this bug: self.__class__.__name__, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for GeneralizedRCNN: size mismatch for roi_heads.mask.predictor.mask_fcn_logits.weight: copying a param with shape torch.Size([81, 256, 1, 1])...

i wanna use centermask-V2-99-FPN-ms-3x.pth model for my own datasets which yaml should i choose and how modify the file?

how to export boxinst model into onnx file ?

1

hello, does boxinst support onnx ?

any demo script?

6

Is there any demo script to inference one single image and visualize? like [https://github.com/open-mmlab/mmdetection/blob/master/demo/image_demo.py](url)

my pytorch 0.4.1 with cuda 9.0 and i use voc dataset, the image can be read correctly , but got some problem in forward i debug the code : def...

mask2former export onnx？

5

is there any schedule to support mask2former exporting to onnx ？

any script for demo or evaluation?

1

i trained model in nuScenes datasets following the instruction. how can i visualize or make a demo for generated model?

how to test ?

1

what is the difference of this three .py file ? evaluate_deeplab.py and test_model.py and deeplab.py which one is for test ? how can i run it ?

如何以高利用率、高GPU功率占卡

1

组里设置了限制，不仅仅看GPU显存，还看GPU利用率和GPU功率，导致经常被释放 单纯提高占用GB数，无法提升利用率和功率，有什么好办法嘛？ 

how can i get the json file?