-
Currently, there are two models that are not converted as part of the competition:
- [ ] grcnn_robust (no model weights) @mike-ferguson
- [ ] resnet18_local_aggregation (Complex, custom Stanford TF…
-
I trained this model with the command "python main.py --config-file configs/sgg_res101_step.yaml --algorithm sg_grcnn".
SOLVER:
BASE_LR: 5e-3
MAX_ITER: 8000
STEPS: (8000,12000)
batch_si…
-
File "main.py", line 127, in
main()
File "main.py", line 122, in main
model = train(cfg, args)
File "main.py", line 68, in train
model = build_model(cfg, arguments, args.local_r…
-
Thanks for your code and paper!
I am trying to `create_scene_graph_input_files`. But I can't run `PYTHONPATH="/path/to/graph-rcnn.pytorch" python create_sg_h5.py` successfully, since `graph-rcnn.pyto…
-
Hi,
I try to train a model following "python tools/train_sg_net.py --config-file "/path/to/config/file.yaml"
". But I confuse which config.file I need to use, can you share more details about trai…
-
After evaluating pretrained RelDN model on Visual Genome dataset we get the following results:
{"danfei_metric": {"sgdet20": 0.03587473726452877, "sgdet50": 0.059597123157443185, "sgdet100": 0.082031…
-
Hello,
First, thank you for this impressive contribution to the robotics community and for making it open source!
I had a couple of questions regarding setting up GR-Convnet on a new machine:
…
-
Once all of the "important" models have been tracked down, they may not be in converted form. Martin has provided the model conversion script that has been used previously. If that script works, then …
-
While playing with acm observability, I realised we have two HCP cluster where an API server pod is consuming >20cores.
That does not feel right!
See e.g. here:
![image](https://github.com/stormsh…
-
I run my own data on aldi-cmt to train SADA, but get this error. However, it's not found on other model. This error is also found on branch extras.
![Snipaste_2024-05-14_00-20-46](https://github.com…