The whole idea is as follows:
When training, can be validated at the same time, when the accuracy rate reaches a certain level, it can be tested simultaneously. That these three processes can be a
training:
verification:
test:
TensorFlow base (XI) - Based on the data set MNIST trained models do predict the picture input
Guess you like
Origin blog.csdn.net/qq_37764129/article/details/94660198
Recommended
Ranking