Too low accuracy in evaluation
fukui-kentaroh opened this issue · 3 comments
fukui-kentaroh commented
When I run the code in Google Colab, the accuracy in training is over 90%, but the accuracy in evaluation is much lower. The output looks as follows.
---- batch: 550 ----
mean loss: 0.154208
accuracy: 0.943750
---- batch: 600 ----
mean loss: 0.160189
accuracy: 0.946250
2021-04-07 06:03:49.119485
---- EPOCH 250 EVALUATION ----
eval mean loss: 7361.237774
eval accuracy: 0.062399
eval avg class acc: 0.048500
Does anyone know the cause?
By the way, the version of Python in Colab is 3.7.10 and the version of Tensorflow is 2.4.1, so I made some changes to absorb the difference between the versions.
pratibhashinde commented
Hi,
I am also getting very low accuracy for evaluation. Did you manage to solve it? Can anyone help?
Thanks.
elenacliu commented
Are the labels in your dataset correct?
lisj575 commented
Maybe you can check the batch_normalizaiton function you use