wanJ

Does it support dynamic batch inference?

4

When I try onnx->tensorrt and use dynamic batch, the tensorrt output is all [0,0,0,0,.....]

I got the weight file after successful quantization, but I found that the weight file after quantization is inconsistent with that before quantization, how can I read the int8 weight...

SwinTransformer3D

3

Does this framework support SwinTransformer3D quantification?