graph-rcnn.pytorch
graph-rcnn.pytorch copied to clipboard
jwyang
[ECCV 2018] Official code for "Graph R-CNN for Scene Graph Generation"
There are some papers using sub-graph proposal instead of relation proposal. However, they perform experiments on other subset of Visual Genome, and is hard to compared with the methods mentioned...
Hi, I am facing the following error while evaluating the main.py D:\GitHub_Repos\graph-rcnn.pytorch> python main.py --config-file configs/faster_rcnn_res101.yaml --inference --resume $CHECKPOINT Traceback (most recent call last): File "main.py", line 14, in from...
I want to train this model. But I encounter out of memory. I use GTX Titan X. I think that exist memory leak... Which GPU is right for this model?
Hi, I want to use the script written for relation proposal network in my work. How can I separate it and how to use it my own faster r-cnn pipeline?
https://github.com/jwyang/graph-rcnn.pytorch/blob/83a95c4b9ce4fc48ec63d67d7ed63df25218550e/lib/scene_parser/rcnn/modeling/relation_heads/grcnn/agcn/agcn.py#L23 While in your paper, the present node zi is added in Relu.
When compiling lib/scene_parser/rcnn got error: ... lib/python3.7/site-packages/torch/include/ATen/Functions.h:4128:229: required from here /usr/include/c++/6/tuple:495:244: error: wrong number of template arguments (4, should be 2) return __and_
Many recent papers start to report the graph `Unconstrained` scores. > Two evaluation protocols are used in the literature differing in whether they enforce graph constraints over model predictions. The...
 The command that I use "python main.py --config-file configs/sgg_res101_joint.yaml --inference --resume 0". And I use this checkpoints: https://drive.google.com/file/d/1VbgX3_OLhzgdNseXgS_2DiLmJ8qiG8P/view What am I doing wrong?...