search

leon-liangwu / MaskYolo_Caffe

YOLO V2 & V3 , YOLO Combined with RCNN and MaskRCNN
115 stars 50 forks source link

No mask result #33

Closed guods closed 4 years ago

guods commented 4 years ago

I train step1 with batchsize 32 and prop_num 32, step2 with batchsize 16 and prop_num 32; but when I test the model at 80000 iter, there are only the detection results and no the mask result.

leon-liangwu commented 4 years ago

@guods In step2, please make prop_num equal to batchsize too.

guods commented 4 years ago

@guods In step2, please make prop_num equal to batchsize too.

Thanks for your reply, I will try it.