zihaomu

Hi @asmorkalov, any update?

> Can be merged as is, we'll fix dynamic shapes on the engine level in the future. Agree.

`Range` layer is unsupported on OpenCV at present. I will try to support.

Hi @alalek and @asmorkalov, can you please check if the update can fix the data alignment issue?

Great thanks! @asmorkalov I will follow your suggestion and re-implement it with `CV_STRONG_ALIGNMENT `.

Thanks for the reminder, @asmorkalov. there seems to be a depth bug on float16 and I'm trying to fix it.

Hi @asenyaev, other CI works fine, only Win10 can not download the new added testing model from Github. Can you please check what's happening? [Win10 CI error](https://github.com/opencv/opencv/runs/7928796799?check_suite_focus=true#step:11:736)

Hi, `ONNX_importer.cpp` may encounter bugs when load float16 model. When the format version of ONNX is lower than 7, `dnn/misc/opencv_onnx.pb.cc` will parse float 16 tensor into int32, which will cause...

Hi, with the help of ONNX teams, we can load all the ONNX float16 models now! ONNX saves float 16 data to two different way: `int32_t` and `raw_data`. [ONNX convert...

Update: Model can works fine with this patch. The following is old comment. Hi @fengyuentau, please take a look [this comment](https://github.com/opencv/opencv/issues/22446#issuecomment-1233649431). This patch can work correct on `Simple Layer`, but...