RSS blog page - 1/3 ==> Blog benchmark (4) onnx (8)


blog page - 1/3#

Don’t use id(node)#

2022-11-15

I was expecting the following code to be produce unique keys. But it seems python objects for the nodes are created one the fly and destroyed in the same loop. Then id(node) are not unique.

post

Array API#

post

ONNX Backend Scoreboard#

2022-05-29

ONNX Backend Scoreboard shows how many operators a runtime supports. Page ONNX Backends for Python/Numpy runtime computes the same figure for the Python Runtime implemented in this package, more than 90%.

post

Xop, easy to create onnx graph#

2022-02-27

onnx package has a very verbose API to create ONNX graph. Could you imagine a user to directly write the syntax tree of a program instead of some python code? Creating a ONNX graph is very similar to that task except ONNX language is more simple than python.

post

A few tricks for tf2onnx#

2021-08-12

A few things I tend to forget. To run a specific test on a specific opset.

post

Decompose einsum into numpy operators#

2021-08-11

Notebook Einsum decomposition what function numpy.einsum does and how it can be decomposed into a series of basic operations, all available in ONNX. That’s the purpose of function Function decompose_einsum_equation. With function export2numpy, it is possible to convert back this ONNX graph into a series of numpy operations.

post

onnxruntime shape [] != None#

2021-08-10

None is the undefined shape, [] is an empty shape. And when shapes do not fit the results, the outputs can be suprising. The following example shows what onnxruntime produces for the same graph except input and output shapes when defined as None and [].

post

ONNX from C##

2021-07-09

This example shows how to compute the predictions of a model using C#.

post

Convert a Lightgbm dump#

2021-07-09

This example shows how to convert a lightgbm model dumped as a text file. It uses lightgbm to restore the model, converts it and checks the discrepencies.

post

Numpy API for ONNX and scikit-learn (part II)#

2021-05-05

This follows blog post Numpy API for ONNX and scikit-learn (part I). It demonstrated how to insert a custom function in a pipeline and still be able to convert that pipeline into ONNX. This blog post shows how to implement a custom transformer.

post


RSS blog page - 1/3 ==> 2021-08 (3) 2022-02 (1) 2022-05 (1) 2022-06 (1) 2022-11 (1)