search

eriklindernoren / PyTorch-YOLOv3

Minimal PyTorch implementation of YOLOv3
GNU General Public License v3.0
7.33k stars 2.63k forks source link

this repo is good ONLY for INFERENCE with PROVIDED WEIGHTS. #527

Open ScottHoang opened 4 years ago

ScottHoang commented 4 years ago

like the title said, this implementation suffers serious issue when trained from scratch with mAP stalling at around 20%. If you are planning to train this on custom data, I suggest go looking at a different PyTorch implementation of yolo.

tjiagoM commented 4 years ago

Hi @voodoopotato do you have a suggestion of a good pytorch implementation? I've found different ones around so was curious to see what you think.

ScottHoang commented 4 years ago

@tjiagoM yes I did. https://github.com/ultralytics/yolov3. I achieved much much better results using their model.

Khalifa1997 commented 4 years ago

@voodoopotato @tjiagoM do you think I can achieve results here training on only 100 images?

ScottHoang commented 4 years ago

No.

Khalifa1997 commented 4 years ago

@voodoopotato thanks for the quick reply, I am abit lost here though, what approachs do you think I should look into with dataset of that size? thanks!

ScottHoang commented 4 years ago

@Khalifa1997 maybe I was a bit in haste. One hundred images are very small sample population but can be artificially multiplied with proper data-augmentation. It depends on how many cls you have, how common they are in your samples, etc... But as I said in my title, this repo is only suitable for inference.

aningineer commented 3 years ago

@tjiagoM yes I did. https://github.com/ultralytics/yolov3. I achieved much much better results using their model.

Are there any minimal Yolov3 implementations that achieve the original results from the authors? The Ultralytics repo seems to be quite heavy to develop on.

XZLeo commented 2 years ago

This issue may not be true. I trained on my own dataset from scratch, the mAP reaches 50+%.