Ignacio Rocco
Ignacio Rocco
Hi, which pretrained model are you using? I'm using model [35861858](https://s3-us-west-2.amazonaws.com/detectron/35861858/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml.02_32_51.SgT4y1cO/output/train/coco_2014_train:coco_2014_valminusminival/generalized_rcnn/model_final.pkl) and it's working fine for me.
Which python & pytorch version are you using?
I applied the fix from @youansheng Please try now. Also, an official Mask RCNN was released by Facebook here https://github.com/facebookresearch/maskrcnn-benchmark
Hi, glad you liked the code :) Please see the demo notebooks for the usage of the mask head. Essentially there is a results postprocess stage between the forward pass...
Hi, this is just a matter of terminology. For consistency with the ProposalFlow paper that uses inverse warping we also transform the points from the second image (target) to the...
Please see the explanations about inverse warping here: https://www.cs.unc.edu/~lazebnik/research/fall08/lec08_faces.pdf this should help you understand!
Hi, this model is only intended to provide a set of matches. If you want to fit a geometric model such as a homography you can use a method such...
Hi, the matches folder is for the InLoc evaluation. In this case you are running the PF Pascal evaluation, the PCK result is shown in the last line of the...
Hi, these are publicly uploaded images. It is possible that some user removed it from the web. It should not change the training.
Hi, you need to use the TSS evaluation kit from https://taniai.space/projects/cvpr16_dccs/