From e25255547a9bf21273347befeedf18ac767643f5 Mon Sep 17 00:00:00 2001 From: Katsuya Hyodo Date: Wed, 6 Apr 2022 12:26:19 +0900 Subject: [PATCH] Update README.md --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index ad21354..8659e25 100644 --- a/README.md +++ b/README.md @@ -11,6 +11,7 @@ A very simple tool that compresses the overall size of the ONNX model by aggrega - [ ] ~Finally, create a Fork of **[onnx-simplifier](https://github.com/daquexian/onnx-simplifier)** and merge this process just before the onnx file output process~ -> Temporarily abandoned because it turned out that the onnx-simplifier specification needed to be changed in a major way. - [x] Implementation of a specification for separating the weight of a specified OP name to an external file. - [ ] Implementation of a specification for separating the weight of a specified Constant name to an external file. +- [ ] Added option to downcast from Float64 to Float32 and INT64 to INT32 to attempt size compression. - [ ] Final work-around idea for breaking the 2GB limit, since the internal logic of onnx has a Protocol Buffers limit of 2GB checked. Recombine after optimization. Splitting and merging seems like it would be easy. For each partitioned onnx component, optimization is performed in the order of onnx-simplifier → scs4onnx to optimize the structure while keeping the buffer size to a minimum, and then the optimized components are recombined to reconstruct the whole graph. Finally, run scs4onnx again on the reconstructed, optimized overall graph to further reduce the model-wide constant.