search

dmlc / gluon-cv

Gluon CV Toolkit
http://gluon-cv.mxnet.io
Apache License 2.0
5.82k stars 1.21k forks source link

Any easier tutorial for custom object detection? #281

Open theprodev opened 6 years ago

theprodev commented 6 years ago

First of all, many thanks for the great tutorials for object detection using pre-trained models. The code is so simple and easier to follow.

The problem is that custom object detection (with a small dataset) and transfer learning tutorials are complicated for beginners. I saw a tutorial somewhere that shows custom object detection using just 5 lines of code. Can you write a simple tutorial for us?

This looks very complicated. https://gluon-cv.mxnet.io/build/examples_classification/transfer_learning_minc.html Do we really need to learn all these details while you have such a great high level API?

I am sorry if this is not the right place to post this question but I need your help on this.

Thanks again.

zhreshold commented 6 years ago

We are working on that right now.

theprodev commented 6 years ago

Thanks a lot.

I have just trained a custom dataset using another library and got the resulting model file in .h5 format. I need to convert it to .params model file that you have used in your examples. Can you tell me how to convert that?

On Fri, Aug 31, 2018 at 1:01 AM Joshua Z. Zhang notifications@github.com wrote:

We are working on that right now.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/dmlc/gluon-cv/issues/281#issuecomment-417448868, or mute the thread https://github.com/notifications/unsubscribe-auth/AFXxIEAzesT0dSb2CNddIhT7I6iYENcTks5uWESbgaJpZM4WQC7u .

hlnull commented 5 years ago

https://gluon-cv.mxnet.io/build/examples_detection/finetune_detection.html shall fix this issue.