mean-teacher
mean-teacher copied to clipboard
The accuracy of validation data is very low
Thank you for sharing this project.
I run the cifar10_test.py with the default configuration, and the accuracy of training data is about 50% for top 1and 90% for top 5.
However, for validation data, the accuracy is very low, and the accuracy is 0.154% for top1/5. Please have a look for the following figure.
Any suggestion is appreciated!