-
Notifications
You must be signed in to change notification settings - Fork 5.7k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Paddle Tensorrt] change int32 to int64 in test file #69191
Conversation
你的PR提交成功,感谢你对开源项目的贡献! |
"x": np.random.randn(7, 3).astype(np.int32), | ||
"out_dtype": np.int64, |
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.
cast处理的不是shape tensor,这里没必要这样修改吧,改了反而测试不到float16的场景了
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.
已修改
790b729
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.
代码提交有问题吧,third_party目录应该不需要修改吧
@@ -54,8 +54,8 @@ class TestLessThanFloat32TRTPattern(TensorRTBaseTest): | |||
def setUp(self): | |||
self.python_api = paddle.less_than | |||
self.api_args = { | |||
"x": np.random.randn(2, 3).astype(np.float32), | |||
"y": np.random.randn(3).astype(np.float32), | |||
"x": np.random.randn(2, 3).astype("float32"), |
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.
这类修改的作用是什么呢?
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.
规范了样式
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
dbd332e
PR Category
Inference
PR Types
Bug fixes
Description
card-71500
将测试文件中的int32转为int64操作,并删除test_trt_marker