Yufeng Li baa86f181f Handle the case that initializers are in graph input (#3449) ... warn that initializers are in graph input provide a tool to move initializer out of graph input Motivation and Context ONNX model from IR_VERSION 4 only treats initializers that appear in graph input as non-constant. This may fail some of the graph optimizations, like const folding, operator fusion and etc. Warn the case and provide a tool.		2020-04-14 09:06:04 -07:00
..
dump_subgraphs.py	Add python script to export subgraphs from Scan/Loop/If nodes in an ONNX model. (#583)	2019-03-08 14:51:30 -08:00
FindOptimizerOpsetVersionUpdatesRequired.py	Add script to find if optimizer updates are required due to onnx operator updates. (#1957)	2019-10-21 11:38:30 -07:00
gen_doc.py	fix the link to the script in the doc. fix some error messages (#960)	2019-05-02 19:21:41 -07:00
gen_opkernel_doc.py	Generate documentation from the registered operator kernels (#1395)	2019-08-14 18:12:24 -07:00
get_submodules.py	Fix cgmanifest.json generating script (#2770)	2020-01-14 14:59:07 -08:00
onnx_test_data_utils.py	Add a python script with a number of helper actions for creating/editing/dumping onnx test runner format pb files (#2294)	2019-11-01 06:39:14 +10:00
remove_initializer_from_input.py	Handle the case that initializers are in graph input (#3449)	2020-04-14 09:06:04 -07:00
update_version.py	Upgrade version number for ORT in preparation for release (#1468)	2019-07-23 16:33:06 -07:00