Rauf Yagfarov
Rauf Yagfarov
I got an error when trying to train model with DistributedDataParallel and set num_workers>0 in DataLoader. With num_workers=0 everything works fine. My code: ```python from l5kit.dataset import AgentDataset from l5kit.data...
Hi! Is it possible to split task data to jobs after data uploading ? I didn't find how to do it. It's possible to split data to jobs only on...
Hi, @ZFTurbo ! Thank you for your amazing approach and code! I have a question: what is a right way of choosing **weights** parameter? I have several models and in...
Hi! Thank you for amazing work! I am trying to train r50vd_giam_aug model on my dataset in COCO format. In categories I have only 1 class with id=1 and each...
Hi, @Charmve ! Thank you for amazing job! I have a question about GD_net usage: Is it possible somehow to get reflections from glass prediction? I want to separate objects...
Thank you for the amazing work! In the last FCOS model update, you divided regression head predictions by the FPN level stride value. However, why not divide regression predictions by...
Hi @HuangJunJie2017 ! Thank you for amazing work! I have a question about how to configurate model training parameters on my own data. I already prepared data and can start...
Hi, @yzhou377 ! Thank you for your work on argo to kitti converter! Using this script, my data was not converted correctly Am I doing something wrong or is there...
Hi! Thank you for the amazing work! I have a question regarding video grounding on a sequence of frame images. I want to do the same thing you demonstrated in...
Hi! I am trying to load 640m.onnx model, but it gives an error: ```bash InvalidProtobuf Traceback (most recent call last) [](https://localhost:8080/#) in () 1 from nudenet import NudeDetector ----> 2...