-
Notifications
You must be signed in to change notification settings - Fork 226
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
C++ API test with synthetic data #284
base: master
Are you sure you want to change the base?
Conversation
951f264
to
65ed25c
Compare
dd03467
to
653ea0a
Compare
cf30938
to
8d2c59f
Compare
064de53
to
eb97b19
Compare
27ef7b8
to
535c132
Compare
@meena-at-work: for review |
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.
Overall, it looks fine to me as is -- considering that it is intended to be a standalone example of using synthetic data (and not a benchmark). If you can address the one small nit, I think it's good to go.
// Converts an MNIST Image to a tensorflow Tensor. | ||
tensorflow::Tensor MNISTImageToTensor(int offset, int batch_size); | ||
|
||
std::vector<mnist::MNISTImage> images; |
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.
just a nit here -- can you name the member variables with a m_images or images_ so we know that they're member variables?
cf4f9f4
to
0f999c4
Compare
e8da9e9
to
a742619
Compare
f8c43a2
to
41bbfde
Compare
6cf16c4
to
ccc606f
Compare
0c12576
to
bfed396
Compare
Test program to run TF-TRT conversion with the C++API with synthetic data.
This is based on #271
Todo