Mihai David
> Well, there is already a standard/solution for coco that´s somehow not being used by roboflow: RLE (_frString) > > Also, not supporting masks causes other issues: When converting to...
@thomasf1 Yes, that's true, from Image/PNG format to Coco Masks (rle or polygons) annotations. It supports instance segmentation, therefore multiple classes and multiple instances of the same class in an...
@thomasf1 Hi, I did not understand your question. Which generated masks are you talking about?
@thomasf1, oh, I see. Currently, I'm only using already annotated base datasets, so I'm not using any tool to annotate raw images :) I might look into that!
I was trying to run distribute training on a VertexAI Workbench notebook. After 10000000 tries, I finally got it working in this way: 1. Get a machine with Pytorch 2.2...
Hello, @Code-of-Liujie, @FrancoisPorcher . I was able to make it work. 1. git clone https://github.com/Sense-X/Co-DETR.git 2. conda create --name codetr python=3.8 -y 3. conda activate codetr 4. pip install torch==1.11.0+cu113...
Me too. Do you know other place where can I get this file ?
@ccdatas do you have any updates on these? Thank you very much!
Hello @HRliao1109 :) After a couple of weeks I made it work. Here is a small markdown formatted list of instructions for installation, data prep., training, and evaluation, that worked...
Hi, @ccdatas. Thank for getting back. I used only 1 GPU with 4 samples per GPU, and a 1:3 ratio. Do you think the higher batch size could be the...