Yoav
Yoav
I have run the code in multiple GPUS successfully! You need to wrap models by DataParallel firstly. There are still some changes to be made in the code, beacuse when...
改了空图片的问题以后又报错“Invalid SOS parameters for sequential JPEG”，这又是怎么了，不知道原文是怎么在nwpu上训练的。
Because the keys in pre-trained models' state dict is different from the keys of models defined in the code. First set strict = True and then I solved it in...
可以在.cls文件中相应的地方修改
> Did you use the imagenet pretrained backbone weights (`weights/darknet53.conv.74`)? > > Training totally from random initialization is not feasible on coco in 24 epochs. Even if you use the...
> I also started a training after you opened the issue and I have also a mAP of ~3 at the same epoch. I would train it for a couple...
> I am currently testing a hyperparameter set that achieves 11.6 mAP at epoch 3. I'll keep you updated. I train the code with default hyperparameter using my dataset, and...
> I am currently trying to find better hyperparameters for coco and already have a few promising sets. Sadly training on coco takes quite some time. Even it you are...
I also encountered this problem and successfully solved it with the help of GPT. Here’s how you can fix it step by step: 1. Copy the `pyproject.toml` file from project...
> [@fyw1999](https://github.com/fyw1999) , > > Thanks for confirming this workaround — and I appreciate you mentioning [groundingdino-cu128](https://github.com/ghostcipher1/groundingdino-cu128). I will be adding additional updates in the days to come. > >...