Closed Songyima closed 2 years ago
Use mnn you can get correct result: https://github.com/alibaba/MNN
embedding is supported via pnnx, see https://github.com/Tencent/ncnn/tree/master/tools/pnnx
针对onnx模型转换的各种问题,推荐使用最新的pnnx工具转换到ncnn In view of various problems in onnx model conversion, it is recommended to use the latest pnnx tool to convert your model to ncnn
pip install pnnx
pnnx model.onnx inputshape=[1,3,224,224]
详细参考文档 Detailed reference documentation https://github.com/pnnx/pnnx https://github.com/Tencent/ncnn/wiki/use-ncnn-with-pytorch-or-onnx#how-to-use-pnnx
I have converted my pytorch model to onnx and simplified it by onnx-simplifier. However, there still a GATHER op which refers to nn.embedding in pytorch. Hence, I failed to run onnx2ncnn.
In fact, my model is used in an NLP task, I wonder if ncnn doesn't support NLP well.