AllentDan

Hi, @amitbcp. We have example codes about how to deploy some detection and recognition models in mmocr. Dive into `tools/deployment/pytorch2onnx.py` and add some codes to make codes execute to torch.onnx.export...

> Hi @AllentDan ! > > can you provide some more pointers on how to go forward with the conversion.. even the ONNX inference for SDMGR. Or how you guys...

Hi, @gouttham. Good job. The line `nodes[valid] = rnn_nodes[valid].gather(1, (all_nums[valid] - 1).unsqueeze(-1).unsqueeze(-1).expand(-1, -1, rnn_nodes.size(-1))).squeeze(1)` is too long to analyse codes. Maybe we can split it to several short lines. BTW,...

> here is index of output node name, when you freeze graph you will see 30 variable convert to const, file freeze graph had weight is 35Mb, hope it help...

@trungtinnguyen many thanks, I will have a try

https://github.com/yangxue0827/R2CNN_FPN_Tensorflow/issues/5 这个可能是解决办法，应该是转化tfrecord时候部分图片没有gtbox导致

Maybe in the future if I got time. But only yolox because of license limitation.

Thanks for reporting the bug. It occurred in all the instance-seg models of MMDeploy. Will fix it ASAP.

After checking it with an NVIDIA card with larger memory, the error might be raised by a lack of enough mem.

I met the same error as yours with Mask-RCNN with `export_postprocess_mask=True` on a 1060 card with 6 GB mem. But the conversion succeeded on a 2080 Ti card with 8GB...