Simon

Successfully installed detectron2 on Win10

6

**Requirements:** - **Python 3.6.1** - **Pytorch 1.4.0** - **torchvision 0.5** - **fvcore:** `pip install git+https://github.com/facebookresearch/fvcore` - **pycocotools:** `pip install git+https://github.com/philferriere/cocoapi.git#subdirectory=PythonAPI` - **VS2019/CUDA10.1** **Procedures** - **Step1:** `git clone https://github.com/conansherry/detectron2.git` - **Step2:**...

Some error in prediction(SGDet) on custom images.

2

## ❓ Questions and Help When I use the command line following for SGDet: CUDA_VISIBLE_DEVICES=0 python -m torch.distributed.launch --master_port 10027 --nproc_per_node=1 tools/relation_test_net.py --config-file "configs/e2e_relation_X_101_32_8_FPN_1x.yaml" MODEL.ROI_RELATION_HEAD.USE_GT_BOX False MODEL.ROI_RELATION_HEAD.USE_GT_OBJECT_LABEL False MODEL.ROI_RELATION_HEAD.PREDICTOR CausalAnalysisPredictor...

Using a detector model pretrained on 1750-700-400 vg datasets, the mAP is relatively low when testing

9

## ❓ Questions and Help Hi, I generate a new vg datasets (1750-700-400) followed this repro [https://github.com/danfeiX/scene-graph-TF-release](https://github.com/danfeiX/scene-graph-TF-release) and use the scripts [generate_attribute_labels.py](url) you provide. Then, we trained the detector model...

How to generate the scene graph based on the bottom up features ?

8

## ❓ Questions and Help In bottom up features, every images contains a 2048 dim features and a five tuples features about bounding boxs (x1, y1, x2, y2, w*h). In...

Some issues about generating the realtionships (using PreCls) based on boxes and classes label.

5

## ❓ Questions and Help Hi, it seems like that the pretrained PredCls model is trained on VG datasets (51 relationships, 150 objects). But if I want to test on...

How to resume the checkpoint to continue pretraining？

1

I find a issue when I attempt to continue pretraining? ` trainer.train(resume_from_checkpoint=True) File "/opt/conda/lib/python3.8/site-packages/transformers/trainer.py", line 1539, in train return inner_training_loop( File "/opt/conda/lib/python3.8/site-packages/transformers/trainer.py", line 1676, in _inner_training_loop deepspeed_load_checkpoint(self.model_wrapped, resume_from_checkpoint) File "/opt/conda/lib/python3.8/site-packages/transformers/deepspeed.py",...

Hi, when training based on your default parameters on VQA task ( dropout_input: 0.1, dropout_pre_lin: 0.0, dropout_output: 0.0), Isn't that overfitting? when I training the model , the val score...

Can not submit on the VideoBench Leaderboard

1

Hi, I want to evaluate result of our model, and I convert our results into Video-Bench-Input.json. When I press the "submit eval" botton on the hugging face page of Video-Bench...