MichalBusta
commented
5 years ago one of the most parameters is input_size (size of the crops fed to network) - bigger=better.
- you can use debug option of the script to see the data you are feeding. (the situation (probably) is, that you are feeding "empty data"
- size of the text is too big or too small compared to input_size ... )
On 19/01/2019 17:18, wasfly wrote:
When I train my own dataset, the values of ·loss· and seg_loss· are always equal -2.00. Other values are 0. Is there a problem? , I have not changed anything ,excep data set and batch_size(32), and train start from scratch
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/MichalBusta/E2E-MLT/issues/18, or mute the thread https://github.com/notifications/unsubscribe-auth/AD6jsAQabx3p7OMawGzbE4EVTtVd0SzZks5vE0VRgaJpZM4aJNXW.
WasFly
When I train my own dataset, the values of ·loss· and seg_loss· are always equal -2.00. Other values are 0. Is there a problem? , I have not changed anything ,excep data set and batch_size(32), and train start from scratch