Closed zeeshanalipanhwar closed 3 years ago
@zeeshanalipanhwar Please check your data.
Thank you for the reply. ^^ Like what, please elaborate? The data contains instances of different sizes. I am able to visualize my annotations as well.
Here, it says, "NaN
means the metric cannot be computed (e.g. due to no predictions made).". What I have done is use a pretrained set of weights and train it for 3k iterations, so maybe that's why the large objects are not learned well.
I just trained it for 90k iterations, still got nan for APL. How are the sizes for s, m, and l instances decided?
Hi, I am getting results like:
How can I resolve that?