DINO

DINO copied to clipboard

Masks to COCO format

1

How do I generate COCO format dataset from a dataset of instance masks?

sri9s

Dynamic DN groups

1

Thanks for your great work! As mentioned in Appendix D.1, > Considering that the number of objects in one image in COCO dataset ranges from 1 to 80, this design...

fushh

Plan to support for ONNX

4

These days, I trained and evaluated my own dataset and got significant result with your model compared to YOLOS. Now, I have tried to convert DINO(pytorch) into DINO(onnx or tensorrt)....

jhj7905

Border line thickness

1

how to change the Border line thickness of the box

skyfallsss

Long-skinny object

4

@SuperHenry2333 , I have two questions: 1. My data might have more than 200 objects in an image, which parameter takes care of this situation? 2. If I need to...

AI-Passionner

Can we train the model on the CPU?

hamzakhalil798

AssertionError: Invalid boxes

1

Hi @SuperHenry2333 @SlongLiu @FengLi-ust Update: some bboxes after data augmentation are `nan`:  --- I tried to reproduce the Objects365 pre-training with a large resolution, however, this error always occurs....

liming-ai

Support for TorchScript export

2

Hi, I have been trying to export the 4-scale model with ResNet50 backbone to TorchScript with the following code: ```python import torch from util.slconfig import SLConfig from main import build_model_main...

cywinski

DINO Contributors, your guys are very awesome!

1

Today I got my first DINO evaluation on my own dataset (non-COCO objects), which was used to compare the model performance across different object systems in my own way. Lots...

AI-Passionner

Is there a better to see the training details, like tensorboard?

3

There is so much information logged after each training step. So I am wondering if there is a better way to see the overall model performance, such as training_loss, eval_loss,...

AI-Passionner