Skip to content
This repository has been archived by the owner on Jan 24, 2024. It is now read-only.

add dropout_infer op, PE and tests and EfficientNet model #242

Merged
merged 2 commits into from
Sep 29, 2020

Conversation

wenming2014
Copy link
Collaborator

add dropout_infer op, PE and tests and EfficientNet model(#138

@@ -128,6 +128,25 @@ void PaddleModelToProgram::AddOpMapper_elementwise_add() {
};
}

void PaddleModelToProgram::AddOpMapper_elementwise_mul() {
op_mappers_["elementwise_mul"] = [&](const paddle::cpp::OpDesc& op_desc) {
CHECK(!op_desc.Input("X").empty());
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

是不是 CHECK_EQ(op_desc.Input("X").size(), 1UL) 会更精确
一来,check 非空,二来,精确表明当size > 1的时候不支持会报错

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done,thanks~

self.target.os = Target.OS.Linux
self.model_dir = model_dir
self.x_shape = [1, 3, 224, 224]
self.target_tensor = 'pool2d_16.tmp_0'
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

这里'pool2d_16.tmp_0'应该不是最终输出的tensor吧?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done,thanks~

Copy link
Collaborator

@Superjomn Superjomn left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants