Skip to content
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

About Part 1 training accuracy #1

Open
JiaYouLin opened this issue Aug 28, 2020 · 1 comment
Open

About Part 1 training accuracy #1

JiaYouLin opened this issue Aug 28, 2020 · 1 comment

Comments

@JiaYouLin
Copy link

JiaYouLin commented Aug 28, 2020

After the first part of the training, I want to know how accurate your model is, what can I do?

I'm trying to add the metrics=["accuracy"]
But it doesn't work, it shows the following.

InvalidArgumentError: 2 root error(s) found. (0) Invalid argument: Cannot update variable with shape [] using a Tensor with shape [100], shapes must be equal. [[{{node metrics_1/accuracy/AssignAddVariableOp}}]] [[metrics_1/accuracy/Identity/_159]] (1) Invalid argument: Cannot update variable with shape [] using a Tensor with shape [100], shapes must be equal. [[{{node metrics_1/accuracy/AssignAddVariableOp}}]] 0 successful operations. 0 derived errors ignored.

@Ekeany
Copy link
Owner

Ekeany commented Jan 22, 2021

Hi,

Sorry for the late response hopefully you got sorted, the accuracy of for part 1 is stated in the READme itself 88%

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

No branches or pull requests

2 participants