-
Notifications
You must be signed in to change notification settings - Fork 7.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Loss can't be below 1. #829
Comments
Use these params: Lines 18 to 23 in e29fcb7
And train about 2000 iterations.
|
@AlexeyAB When I change to use "AlexeyAB/darknet", "./darknet detector train cfg/kitti.data cfg/yolov3-kitti.cfg model/yolov3.weights" will directly save original model without training |
Your learning rate is about 1e-8 which is too small. Try using the option of -clear, then the iteration will restart from 0, if you'd like to use yolov3.weights as pre-trained weights. |
@panda9095 Thank you for your response. |
@BlueAnthony ./darknet detector train cfg/kitti.data cfg/yolov3-kitti.cfg model/yolov3.weights -clear By doing so, the step number will start from 0 instead of 500200. Then you can use @AlexeyAB 's parameters for training. |
@panda9095 Really thank you for your helping! I will try. |
@BlueAnthony
darknet/build/darknet/x64/partial.cmd Line 21 in fb9fcfb
|
@AlexeyAB does this mean that I can further train my last trained model(on my dataset)....with new data? |
The loss can not decrease under 1. It will stop and jitter around some number, like 5 to 6 or 12 to 13, when the iteration is around 50.
![image](https://user-images.githubusercontent.com/17959032/40092523-46d96fce-58f0-11e8-8822-6faab9d42786.png)
I already try different base learning rate, like 0.001, 0.0001, 0.00001, 0.000001.
And the loss start from about 1000.
I have 2 classes(Car and pedestrian), 3712 images for training and 3769 images for validation.
I use yolov3.weight as pretrained.
Thank you!!
I use the code from pjreddie/darknet and try to fine-tune with yolov3.weight.
The command I use is below.
"./darknet detector train cfg/kitti.data cfg/yolov3-kitti.cfg model/yolov3.weights"
Yes, I use random=1. My cfg is modified from yolov3.cfg of pjreddie/darknet.
And why I use these learning rate and steps?
It's because the yolov3.weights seems to remember the max iteration number, the max_batches for fine-tuning must be larger than 500200 and the fine-tuning just can be start.
The loss start about 1000 and stop decreasing about "500200+50" iterations.
Do I misunderstand something?
@AlexeyAB Really thank you for your patience.
The text was updated successfully, but these errors were encountered: