thtrieu / darkflow

Translate darknet to tensorflow. Load trained weights, retrain/fine-tune using tensorflow, export constant graph def to mobile devices
GNU General Public License v3.0
6.13k stars 2.08k forks source link

YOLOv3 weights #767

Open maiminh1996 opened 6 years ago

maiminh1996 commented 6 years ago

thanks you for this tutorial but how do you do to convert the weights from darknet to tensorflow?

ambakick commented 6 years ago

you don't need to convert it , you can use it directly after downloading from https://pjreddie.com/darknet/yolo/

maiminh1996 commented 6 years ago

@ambakick How do you do that? Because i want to build a real-time bounding-box object detection system for the boat (using fine-tuning in tensorflow based on YOLOv3-416 weights trained en COCO dataset). Then use SVM for distinguish between a motorboat and a sailing boat (un bateaux à moteur et un voilier). But i don't know how to use the weights from https://pjreddie.com/darknet/yolo/ in my model! Can you help me, pls!

prateethvnayak commented 6 years ago

@maiminh1996 Right now, there is no conversion script from Darknet to Tensorflow Yolov3 model. But you can convert it to high level keras using this . Then you need to decide how to use it further for your application.

shenyingying commented 5 years ago

@prateethvnayak hi,i use yolo-tiny.weight -> yolo-tiny.h5 then to yolo-tiny.pd but i am not sure what i all do is right

sjain-stanford commented 5 years ago

For those wanting to convert Yolo-v3 from Darknet to TensorFlow:

Yolo-v3 support was recently added to DW2TF (see this PR).

Worth noting that unlike Darkflow which is also a runtime env for training/inference, DW2TF can only convert a Darknet model & weights to TensorFlow. Running training/inference on it would then be up to the user.