We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
Use new onnxoptimizer, enable more optimization pass
Revert "use onnxoptimizer instead of onnx.optimizer" This reverts commit c54d4ec.
use onnxoptimizer instead of onnx.optimizer
Fix daquexian#89
disable fuse_add_bias_into_conv for now
update dynamic shape nodes
Support dynamic shape nodes
add --skip-shape-inference cli arg to avoid segfault on some large mo… …dels
change the default value of skip_fuse_bn from False to True
keep the increased input list