maggiez

> can provide more detail about inference speed of each model > > the speed compare between each method > > thanks Do you mean the comparison of difference models...

> Hello! Thank you very much for your open source cod！ I would like to know how the results of the analysis below are obtained. How was the QDREP file...

> When I try onnx->tensorrt and use dynamic batch, the tensorrt output is all [0,0,0,0,.....] Tried dynamic batch, failed. Both onnx model and tensorRT engine can not output the expected...

> When I cancel the softmax, in pytorch->onnx(dynamic batch), It's work, you can try it, Thanks for your info, will do the attempt.

> Hardware: V100 Model: Swin-tiny > > trt engine size: 115M (fp16) vs 116M (fp32) throughput: 184 (fp16) vs 178 (fp32) > > All the processes were kept the same...

> Hi do you plan to support Swin transformers object detection TensorRT https://github.com/SwinTransformer/Swin-Transformer-Object-Detection Since I have other payloads, it is hard to launch the new object detection work.

Actually the `image_class_accurate` is in `trt\trt_utils.py`, will modify this error later.

> hello there, I am trying to convert swin model to onnx and then tensorrt, but a problem which I face is that it does not support dynamic input resolution...

Updated Readme.

> Hello there. I have the exact same problem with dynamic inputs, but I could not find a way to cancell softmax during converting pytorch model to onnx. Can you...