Large-Scale-VRD.pytorch
Large-Scale-VRD.pytorch copied to clipboard
jz462
Implementation for the AAAI2019 paper "Large-scale Visual Relationship Understanding"
Thanks for your wonderful work, It really inspires me a lot. And I wanna evaluate your code on my own database to do my further research, Could you please give...
When I ran make.sh, I had some errors about it. Can the author provide the results after working make,sh so that we can use them directly
Hi, Can we use ground truth boxes and/or labels with run_inference()? If so, I cannot find an example of the format that they need to be provided in. Any help...
Is the output textual or embedding vector？I hope you can solve my confusion. Thanks in advance!
hi~ I want to know how to visualize the result like the example image after getting rel_detections.pkl
Hi, While trying to run the following command `sh make.sh` I'm getting errors. Attaching the errors for your reference. ``` : not found make.sh: : not found make.sh: /home/abc/def/venv/lib/python3.7/site-packages/setuptools/distutils_patch.py:26: UserWarning:...
When evaluating on VRD dataset，we record different recall@N of k=1, k=10, k=70. But when evaluating on VG dataset, what is the 'k' value to chose ?
Hello all, I am strugelling for a while to interpret the object, subject and relationship embeddings extracted as described by @jz462 in [issue 8](https://github.com/jz462/Large-Scale-VRD.pytorch/issues/8). I am looking to extract the...
Hi, I have been able to successfully run the VG100k model on some random images and it produced the output in `/Outputs/e2e_relcnn_X-101-64x4d-FPN_8_epochs_vg_y_loss_only/rel_detections.pkl` however I am having some trouble interpreting the...
