简体繁体中英

why the validation accuracy (or training accuracy) is not exactly matched with the number of dataset?

原文 2020-06-29 05:19:05 7 1 python/ tensorflow/ keras/ cnn/ resnet

I'm currently using Keras to training ResNet model with dog and cat dataset. For example, if I have 4000 training sets, then I think the training accuracy should be 1/4000 or 0 or the multiples of 1/4000. but the accuracy shown in the prompt is not multiples of 1/4000 and 0. how does this happen?

enter image description here

1 answers

I don't know for sure, but I think the problem is related to the fact your lass is nan and the accuracy is 1. I will recommend you to check your hyperparameters like the "lass function" or the "batch size".

In any case, good luck!

why training accuracy and validation accuracy oscillate and increase very slowly?

Why at first epoch validation accuracy is higher than training accuracy?

Why there's a bad accuracy on dataset when it's used both for validation and training?

Good training accuracy but poor validation accuracy

Validation accuracy is much less than Training accuracy

Training accuracy is less than validation accuracy

Good training/validation accuracy but poor test accuracy

Very low validation accuracy but high training accuracy

Why is the training accuracy fluctuating?

Why is accuracy and loss staying exactly the same while training?

暂无

The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.

Related Question why training accuracy and validation accuracy oscillate and increase very slowly? Why at first epoch validation accuracy is higher than training accuracy? Why there's a bad accuracy on dataset when it's used both for validation and training? Good training accuracy but poor validation accuracy Validation accuracy is much less than Training accuracy Training accuracy is less than validation accuracy Good training/validation accuracy but poor test accuracy Very low validation accuracy but high training accuracy Why is the training accuracy fluctuating? Why is accuracy and loss staying exactly the same while training?

Related Tags

why the validation accuracy (or training accuracy) is not exactly matched with the number of dataset?

Question

1 answers

solution1 0 2020-06-30 07:18:36

solution1
0 2020-06-30 07:18:36