optimizer
optimizer copied to clipboard
onnx
Actively maintained ONNX Optimizer
Recently, I noticed that the split pass does not work, both in `init` and `predict` operations. In particular, it results into invalid model parts. I would expect that each part...
While optimizing a number of `Mask` and `Faster` R-CNN models on `opset=12` from the ONNX Model Hub, the optimizer generated the models, but I encountered the following error when applying...
I recently used `GPT-2`, with `opset=10` from ONNX Hub. While applying the `rewrite_input_dtype` pass, I encountered the `C.check_model_path(\nonnx.onnx_cpp2py_export.checker.ValidationError: Graph must be in single static assignment (SSA) form, however \\'2907\\' has...
While doing some research, I tried optimizing a number models with `opset=7, 8, 9`. These models have `ONNX v3` format, but when optimized, although the structure remains the same, the...
While running `eliminate_shape_gather` pass for model **R-CNN R-50-FPN** obtained from ONNX Hub with `opset=10`. I receive the error: `onnxoptimizer/passes/eliminate_shape_gather.h:48: runTransform: Assertion "indices_val < dims.size()" failed`.
I tried to use the "lift_lexical_references" pass on a number of models. I think that the pass removes the references arbitrarily, without checking if they are used in the model...
It seems that the laste release on PyPi is 0.3.13, while here on the repository there is 0.3.19. Also the release on PyPi being a few years old is missing...
