-
I wanted to make transfer learning from yolov3-spp.pt for single object detection. So I followed the tutorials but when I trained I got these errors.
![Screenshot from 2019-09-19 18-17-32](https://us…
-
Hello, your code is very beautyful. I want to train Single Class, and following the "Example: Train Single Class" , it works. There is one question:
How to initial the weights ?
Is there some p…
-
@glenn-jocher Thank you very much for your code.
I am attempting to using GIoU loss with yolov3 on my own dataset with single class. I am confused about some relative problems. So I wanna ask you guy…
-
hi all. i did use darknet for a few different things and never had this issue. i used both default and calculated anchors.
the base image is like 250 x 150 pixels
default anchors:
[![detection…
ghost updated
4 years ago
-
Thanks for your great work!!
It seems to be a small flaw on follow code :
https://github.com/ultralytics/yolov3/blob/ee319aeefd97d99fcaac499d148116c71b83397f/utils/utils.py#L528-L537
In NMS mode…
-
I noticed you changed the yolov3 weights file name and model in Sept 2018. Going by previous comments it seems that the previous model was obtained by just training for object detection task on COCO. …
-
**Describe the bug**
When I train my custom dataset (via transfer learning) over 273 epochs (for example 840 epochs) , I found out that I get different results if I stop at 273 epochs, then do "--res…
-
Thanks for your great work.I got the below parameter when i run train.py,It seems that i have use the GPU to train,but when i checked it from my compute Device manager,I found it seems only be trained…
-
Thank you very much!
-
Hi @AlexeyAB ,
I've trained a model that I want to identify the fields.
The bounding box is not right when the field is identified.
Number of images: ~500
Classes: 8
My iteration: ~20K
Model: …