Epiphqny / CondInst

Conditional Convolutions for Instance Segmentation, achives 37.1mAP on coco val
https://arxiv.org/abs/2003.05664
138 stars 15 forks source link

Postprocess of ContInst #2

Closed Anikily closed 4 years ago

Anikily commented 4 years ago

I have noticed that you just resize the pred_masks to the original image size: if results.has("pred_masks"): if results.pred_masks.shape[0]: results.pred_masks = F.interpolate(input=results.pred_masks, size=results.image_size,mode="bilinear", align_corners=False).gt(0.5).squeeze(1)

but the input image has been padded to the max size of a batch, so I think in the post process, the pred_mask needs to be crop first, just like sem_seg_postprocess.