SrikanthMalla

TrackID inconsistent across across cameras and lidar

6

Hi, I found out that the track-ids for same object across different sensors (lidar and camera) at same timestep. Across different timesteps, across different cameras is not same as shown...

interacting agents in interaction prediction dataset

9

Hi, How are the 2 interacting agents labeled in this interaction prediction dataset: https://waymo.com/open/challenges/2021/interaction-prediction/ Was there some criteria for selecting those interacting objects? Best Regards, Srikanth

I am getting so many errors at different points for different torch versions (0.3.0, 0.4.0 or >1.0). Just wanted to share: ` pip install torch==0.4.1 torchfile==0.1.0 torchvision==0.2.0 ` This solved...

I3D AVA input full image?

1

Hi, Could someone point me where the box information is used in I3D AVA. I think the whole image is being used (bounding box is not used any where)? Am...

How to set camera intrinsics?

3

Hi, Is it possible to set different camera parameters while creating images from the 3d models using your plugin? Please let me know. Thank you, Srikanth

car keypoint extraction

2

Hi, Thanks for open sourcing such an amazing simulator. Is there any update on the keypoint generation using the vehicle X interface (https://github.com/yorkeyao/VehicleX/issues/6)? If the annotations are not available, can...

Overfitting

1

Hi @AI-liu , Using the same hyperparameters from the repo, I trained it for 200 epochs on KITTI. It overfits to the train data. After training, I checked the first...

Evaluation

1

Hi @AI-liu , Did you evaluate mAP on the KITTI? were you able to get the scores mentioned in the paper?

[BUG] (NVMe Offload with Zero3) Not enough buffers 0 for swapping 1

11

Hi, I am currently trying off-the-shelf tranformer example with deepspeed: ``` BS=4; PYTHONPATH=src USE_TF=0 deepspeed examples/pytorch/translation/run_translation.py \ --model_name_or_path t5-11b --output_dir /tmp/zero3 --overwrite_output_dir --max_train_samples 64 \ --max_eval_samples 64 --max_source_length 128 --max_target_length...

llama support

4

Hi, I am trying to use llama (https://huggingface.co/docs/transformers/main/model_doc/llama) with ecco. It shows not supported yet. Could you please let me know how I can make it work? Best Regards, Srikanth