shishaoyan
shishaoyan
#97 when I set lr to 0.01 or 0.001 when training private datasets,training is normal, and the final result ap is lower than paper eight percent
没有看到UniGS的代码的代码啊
@yuanhangio @juxuan27 there are only about 5-10 images in own data set, can brushnet converge?? how many images at leat should I prepare??
I trained with coco datadet, the total batch size is 12, and I have solved Nan by adding gradient clip set as visdrone_train.yaml, also the reproduced result is close to...