Martin Pedersen

You could use torch hub and load the model to a variable, then loop your images and feed them to the model, writing or displaying the results.

The easiest way would be to add the coco2017 dataset to your novel dataset and train the model. This way you keep all the 80 coco classes and add your...

If you are in the Yolov5 directory then use: ```python from utils.plots import plot_results plot_results('PATHTO/results.csv') ```

@star4s You are welcome, please don't forget to close the issue if your problem has been solved 😉

https://medium.com/augmented-startups/how-hyperparameters-of-yolov5-works-ec4d25f311a2 These are the biggest ones

> But after I upload data to YoloV5, its label image created by YoloV5 (left side ) By this, do you mean the train_batch_01, 02, 03.jpgs created when training is...

 I just tried drawing the bounding box from your coordinates and it looks correct to me, are you sure you are using yolo annotations? class x center y center...

> Hello Martin, > > Thank you for your testing. You see, right side one is correct. It covers the fracture area. The left side one is NOT correct. I...

👍🏼 glad to be of help. Please don't forget to mark the issue as solved if your problem has been solved.

A mix of what @glenn-jocher mentions is normally a good way to go. Add more data and try evolving your hyperparameters.