Did you use COCO pretrain weight when training DeepLabv2-resnet101 ?

zbf1991 / RRM

Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach

94 stars 11 forks source link

Did you use COCO pretrain weight when training DeepLabv2-resnet101 ? #9

Closed johnnylu305 closed 4 years ago

johnnylu305 commented 4 years ago

Since you said that your setting of DeepLabv2-resnet101 was the same as the paper, I wonder whether you used COCO pretrain weight or not?

zbf1991 commented 4 years ago

Yeah. When you refer to the caffe version, the only provided init.model is pretrained on COCO, if you can find the init model without COCO, please tell me. I really think use this model is not a good choice.

johnnylu305 commented 4 years ago

Yeah. We are working on this problem. We will inform you if we find any solution.