-
Notifications
You must be signed in to change notification settings - Fork 23
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
How to train my task #6
Comments
The original repo of this model is https://github.com/dog-qiuqiu/MobileNet-Yolo/tree/master/yoloface-50k. This model is build based on the original Yolo, which is written in C. So no pytorch or tensorflow code. If you want to train your own dataset, you can use part of my pytorch code https://github.com/imuncle/yoloface-50k/blob/main/pytorch/yoloface.py. In this code, I convert the network into pytorch. Then you can add your own train code. |
Thanks for your replys.I do just as what you say, and export model as .onnx data successfully. However, i'd like to analyze it by Cube-AI and there is an error "[AI:network] NOT IMPLEMENTED: 4 or more number of tensor input dimensions are not implemented". Then, i put tflite model of yoloface-500k model into Cube-AI and there is no wrong. Therefore, i wonder if pytorch model cant be analyzed by Cube-AI cuz tensor in torch is like [B,C,H,W] and tensor in tensorflow is like [B,H,W,C].i sincerely appreciate it if you can give me some opinions. |
Hi, i'd like to train my dataset with the yoloface-50k model, but i dont find any pytorch or tensorflow code for training.Can you tell me where i can find that if you know one. Thank you!
The text was updated successfully, but these errors were encountered: