why the train loss doesn't converge?

[3bobo]

I run the train.py without imagenet datasets and init model , all I have is alov datasets, but after 60000 iterations, I notice that the net's loss is all around 200, I try the snapshot caffemodel to track but they all go badly, is it because of the missing of the init caffemode or the imagenet datasets? thank you for your help!

[nrupatunga]

1. Use Init model, along with alov dataset, but it might not generalise well because it might not be able to track objects that aren't there in the dataset.
2. Should use imagenet, it helps to avoid overfitting.