* Update onnx_decoder.py

* Update opset.py

* Update opset.py

* Update opset.py

* Update onnx_decoder.py

* fix gemm and resize

* add_hardsigmoid

* add_reduce_op

* fix

* fix

* add reduceL2

* fix

* remove onnx

* remove onnx

* remove onnx

* remove onnx

* refix

* fix

* test

* retest

* add logical ops

* add run_dynamic switch

* add Or and Xor

* add Compare ops

* fixed compare bug

* fixed pad bug

* fixed pad bug

* fixed reload bug

* Add AveragePool tests

* fixed opset version

* fixed mod op

* fixed bug

* fixed bug

* add model.eval()

* mv dynamic default false to true

* add shutil to rm files

* move to paddleinference api

* fixed float64 bug

* add logical ops

* add run_dynamic switch

* add Or and Xor

* add Compare ops

* fixed compare bug

* Add autoscan Add op test

* Add elementwise op tests

* Add mod optest

* support 7-15 opset version

* re-lint

* re-lint

* fix_resiz

* check

* fix-ci

* fix split and resize

* fix resize and split

* re-lint
Co-authored-by: NSunAhong1993 <sunyanfang01@baidu.com>

* Support bigbird model

* Support GPT2

* rm useless code

* deal with comments

* fixed topk

* deal with comments

* add notes

* fixed Flatten

* fixed Where and ConstantOfShape

* fixed inf bug

* deal with comments

* Support bigbird model

* Support GPT2

* rm useless code

* deal with comments

* add replication pad

* update op_list.md

* re-lint

* fixed aten::index

* rm useless code

* Support Wav2vec2

* Support onnx roberta

* update op_list.md

* deal with comments

* deal with comments

* Support T5

* fixed for ci

* deal with comments

* deal with scalar tensor

* add replication pad

* update op_list.md

* re-lint

* fixed aten::index

* rm useless code

* Support Wav2vec2

* Support onnx roberta

* update op_list.md

* deal with comments

* deal with comments