-
Notifications
You must be signed in to change notification settings - Fork 115
add dropout_infer op, PE and tests and EfficientNet model #242
Conversation
62cafde
to
b310e82
Compare
b310e82
to
de23d1e
Compare
@@ -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()); |
There was a problem hiding this comment.
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
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
done,thanks~
python/tests/test_efficientnet.py
Outdated
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' |
There was a problem hiding this comment.
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?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
done,thanks~
80dde06
to
e518d36
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
351c49b
to
51d29d4
Compare
51d29d4
to
22c7b3b
Compare
add dropout_infer op, PE and tests and EfficientNet model(#138 )