I am not able to achieve nearly the same accuracy on Camvid as shown in Lesson 3. I am running the notebook ‘lesson3-camvid.ipynb’ without any changes to the NB on Salamander, but even in the basic training I have the validation accuracy diverging from training:
Any ideas what could be going wrong?
Can you link to your notebook ?
I am rerunning on Colab and don’t have the same issue. Really weird. Maybe something to do with the version of the library…
i am trying to do a binary dataset in the gcu and my acc is all over the place, including 0 sometimes
Try to kill the kernal and start again. I had some similar issues. But couldn’t find a way to reproduce it.
Ron, I got the same 0.2-0.3 accuracy at one point after playing around. I blew away the files in data folder and created them from scratch and all was fine after that. Not sure if you have tried - but blowing away your data and re-downloading it (or at least re-unzipping it) from scratch may help?
Very interesting! I wonder what could be the cause… All I know is when I switched to Colab the problem went away.