The accuracy calculation in tensorflow is calculated in units of batch_size.

it seems to say on the Internet that accuracy in TF is calculated according to batch_size (denominator batch_size). Why is it that when batch_size = 4 is set, the output accuracy of each batch_size after updating the model parameters is not one of 0meme 0.25meme0.5mag0.75? But a result that is difficult to divide, such as 0.8763? I don"t know if there is any deviation in my understanding.


this depends on which accuracy you use. There are two kinds of accuracy of TF you know so far:

  1. stream-acc: this is to count the accuracy of all past training results
  2. batch-acc: this is the accuracy you understand
MySQL Query : SELECT * FROM `codeshelper`.`v9_news` WHERE status=99 AND catid='6' ORDER BY rand() LIMIT 5
MySQL Error : Disk full (/tmp/#sql-temptable-64f5-7b6481-250e5.MAI); waiting for someone to free some space... (errno: 28 "No space left on device")
MySQL Errno : 1021
Message : Disk full (/tmp/#sql-temptable-64f5-7b6481-250e5.MAI); waiting for someone to free some space... (errno: 28 "No space left on device")
Need Help?