nπ

for yolov5/yolov7/yolox, refer here https://github.com/airockchip/rknn_model_zoo/tree/main/models/CV/object_detection/yolo

目前不支持，需要自行移至模型外部进行处理

Torch model needed to be exported with torch.jit.trace API. Refer here https://github.com/rockchip-linux/rknn-toolkit/blob/master/examples/pytorch/resnet18/test.py

1.7.3版本已经发布，可以试下新版本是否仍有此问题，仍然存在的话，可以上传模型，我们复现下问题

**RKNPU(Capi)** 1. For **RK1808/RV1109/RV1126**, refer here https://github.com/rockchip-linux/rknpu 2. For **RK3399pro**, refer here https://github.com/rockchip-linux/RKNPUTools (This respository was old, the newer one is coming )

**About rknn.init_runtime with devices connected** 1. **Init Failed** There could be many reasons for the failure of the rknn.init_runtime. Normally it only returns a short code or description. To obtained...

> This was helpful thank you, do you have any advice or insight on a way to use this with python 3.9 (trying to avoid using venvs)? Haven't tried just...

可以单独debug一下是哪个语句造成 Illegal instruction (core dumped). 看起来可能是python的版本问题

conv2d_transpose dilation support is added in v1.7.3. Please update your RKNN-Toolkit and try again.

Hello, Sorry for the miss of this file, here it is. [freeze_inshape_for_onnx_model.zip](https://github.com/rockchip-linux/rknn-toolkit/files/8105516/freeze_inshape_for_onnx_model.zip)