1.0.22

• sed4onnx release
• eval() -> ast.literal_eval()

1.0.21

• sit4onnx 1.0.3
  • Allow static fixed shapes to be specified when dimensions other than batch size are undefined.
  • Bug fixes.

1.0.20

• sit4onnx 1.0.2
  • Add an interface to allow arbitrary test data to be specified as input parameters.
    1. numpy.ndarray
    2. numpy file

1.0.19

• sor4onnx v1.0.1
• Added Rename mode

mode: Optional[str]
    Specifies the type of node to be replaced.
    full or inputs or outputs.

    full: Rename all nodes.
    inputs: Rename only the input node.
    outputs: Rename only the output node.

    Default: full

1.0.18

• Changed onnx-simplifier to extras_require package to avoid conflicts caused by the coexistence of onnxruntime-gpu and onnxruntime.
• sit4onnx 1.0.1
  • Returns numpy.ndarray of the last inference result as a return value when called from a Python script.
  • Add --output_numpy_file option. Output the final inference results to a numpy file.
  • Add --non_verbose option.

1.0.17

• sit4onnx release

1.0.16

• sam4onnx 1.0.5
  • Fixed a bug that caused rewriting of direct constants to fail

1.0.15

• sbi4onnx 1.0.2
  • Added model structure optimization process
    • onnx-simplifier https://github.com/daquexian/onnx-simplifier

1.0.14

• sbi4onnx 1.0.1
  • Added avoidance process for processing exceptions for OPs of indefinite shape PINTO0309/sbi4onnx#1 @fateshelled

1.0.13

• scc4onnx 1.0.2
  • Modified to give op_name to extrapolated Transpose
    • e.g. input_order_convert_transpose_0, input_order_convert_transpose_1, ...