TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its cross-platform capability, high performance, model compression and code pruning. Based on ncnn and Rapidnet, TNN further strengthens the support and performance optimization for mobile devices, and also draws on the advantages of good extensibility and high performance from existed open source efforts. TNN has been deployed in multiple Apps from Tencent, such as Mobile QQ, Weishi, Pitu, etc. Contributions are welcome to work in collaborative with us and make TNN a better framework.
Other
4.37k
stars
765
forks
source link
Any documentation on how to add more layer types? #1990
Is there any sort of documentation around that I can reference if I want to add additional supported layer types to tools/onnx2tnn/onnx-coreml/coreml2onnx.py?
I figured out how to modify the existing coreml2onnx script to support blob_weights_f16 and softmax. There were also a few bugs that I fixed where the shapes of some of the conv layers that were being generated were incorrect. Would you take a PR to look at it?
1. 使用环境(environment)
OS Version: Sonoma 14.2.1
2. Github版本
branch:master
3. 详细描述bug 情况 (Describe the bug) A clear and concise description of what the bug is.
original model: CoreML (espresso file)
4. 日志(Log)
Is there any sort of documentation around that I can reference if I want to add additional supported layer types to
tools/onnx2tnn/onnx-coreml/coreml2onnx.py
?