Eason

> I created internal task 3741010 to track this issue. > > @deephog , could you wait for next major release? Thanks! Thank you for the effort! Yes I will...

I did a few more tests. It turns out that even if I clamp the weights of the original model to 6.1e-5, the normal value range of FP16, if I...

I'm trying to use the precision debug tool provided by Polygraphy. There is no direct example of how to use it and there are a ton of arguments. polygraphy debug...

> @deephog You can automate it using the `--check` option, similar to [debug reduce](https://github.com/NVIDIA/TensorRT/tree/main/tools/Polygraphy/examples/cli/debug/02_reducing_failing_onnx_models#reducing-failing-onnx-models). For example: > > 1. Dump out golden outputs with: > > > ``` > polygraphy...

> > Hi, have you solved this issue? I encountered this problem when training on Sceneflow. > > besides,I think it's the lack of memory that causes it NAN.You can...

> @deephog I used https://github.com/ibaiGorordo/CREStereo-Pytorch and solved NAN. I use the datasets of Baidu Web disk provided by the author (Download from BaiduCloud [here](https://pan.baidu.com/s/1iB96-ftCgPFTlrj220qw8Q)(Extraction code: aa3g) and extract the tar...

> I don't think so. @nvpohanh correct me if I'm wrong excuse me, my question has two parts, which part do you not think so?

> will TRT use the OFA units when we deploy OF or SM models? -> No, TRT doesn't support OFA. Or do we have to use the models specifically provided...

> I don't think so, TensorRT is mainly focused on GPU. Ok, so that OFA unit is not like Tensor Core or something similar that is dedicated to certain type...

> I am not able to answer this question since I know nothing about OFA :) Ok I will just wait for the official release and see if there will...