Open zhangliliang opened 4 years ago
@zhangliliang thanks for checking us out, we do not support any quantization related facilities yet although this is something that we hope to cover eventually. We are also open to collaboration if you are interested!
@tjingrant Thanks for your reply.
Could you share some plans on the roadmap of onnx-mlir?
@zhangliliang the objective of this project is to provide production-ready and research-friendly infrastructure for anyone interested in building their own deep learning oriented compiler software stack.
The immediate implication is that we are trying to provide as many compiler/low-level IR definitions of ONNX operators as possible. Meanwhile, we are also actively engineering/researching a few systematic/generic methods of optimization:
Hi, Has there been any change in the area of support for QuantizeLinear & DequantizeLinear operators? I'm generating a quantized ONNX model and I'd like to convert them to mlir.
I try to convert a simple network with QuantizeLinear/DequantizeLinear but it fails.
The network is very simple that it only contains one tensor as input. Its definition could be found in test of pytorch (https://github.com/pytorch/pytorch/blob/master/test/onnx/model_defs/op_test.py).
The onnx model could be generated via![Screenshot from 2020-08-02 10-59-28](https://user-images.githubusercontent.com/7007684/89114820-23053600-d4b3-11ea-91a1-3076e5e9580d.png)
torch.onnx.export(toC(FakeQuantNet()), toC(x), "fake_quant_net.onnx", export_params=True, opset_version=10, input_names=['input'], output_names=['output'])
. And its visualization using Netron could be like,And the onnx file is uploaded as fake_quant_net.zip
The command for converting is
./onnx-mlir --EmitONNXBasic /home/zhangll/liliang-learning-home/pytorch/test/onnx/fake_quant_net.onnx
, and the error message isCould someone give some suggestion to solve it?