[ARM] calib op change kInt32/kInt64 to kFloat #10128
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Thanks for your contribution! |
mjp9527
commented
Mar 23, 2023
| @@ -37,7 +37,8 @@ std::shared_ptr<std::mt19937_64> GetCPURandomEngine(uint64_t seed) { | |||
| } else { | |||
| VLOG(4) << "Use default random engine with fixed random seed = " << seed; | |||
| } | |||
| engine->seed(seed); | |||
| std::seed_seq seq({seed}); | |||
There was a problem hiding this comment.
此处是为了和paddle_cpu对齐
There was a problem hiding this comment.
paddle_cpu是只在seed=0的情况下是这样处理的吧？
There was a problem hiding this comment.
paddle_cpu是只在seed=0的情况下是这样处理的吧？
应该是不为0也这么处理，之前测试过，固定seed=2023可以精度对齐
6 tasks
mjp9527
changed the title
|
这个 pr 仅能转 arm 模型无法转 x86 模型（但是没关系，仅是提醒下） |
mjp9527
changed the title
移除fill_constant_op临时修改，等待pass方案解决 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR devices
Arm
PR types
Bug fixes
PR changes
OP
Description
calib 作为ARM通用算子，应该支持INT8/FP32/FP16 所有精度，而不是根据数据类型设置精度。比如一个int8模型也有从FP32转为int的需求。