Got it

YOLOv3 Custom Dataset

Latest reply: May 2, 2021 22:57:45 634 2 0 0 0

Hi. 


I trained a YOLOv3 model with Backbone darknet-53 in my custom dataset (2 classes) with the original implementation: https://github.com/pjreddie/darknet 


After that, I converted the .weights file to .pb file with this: https://github.com/mystic123/tensorflow-yolo-v3. And then to .om model. 


There are some implementation or example in .py to run inference in yolov3 with darknet backbone? 


I tried to change this example  https://gitee.com/ascend/samples/tree/master/python/level2_simple_inference/2_object_detection/YOLOV3_mask_detection_picture  with the input of the network (416, 416), the anchor boxes and the number of classes but don't works.


How to change the postprocess function for works in yolo-darknet model?. This example was implemented in TF and Resnet18 backbone but the original implementation is missing. is it in somewhere?  


Thanks for your reply




 

Hi,the postprocess may refer to this:
https://gitee.com/Atlas200DK/learningAtlas200DK/blob/lg/samples_python/atlasutil/ai/post_process.py

Yolov3_post_process
some detail maybe should change。
View more
  • x
  • convention:

Posted by windyxyz at 2021-04-21 03:28 Hi,the postprocess may refer to this:https://gitee.com/Atlas200DK/learningAtlas200DK/blob/lg/sampl ...
Hi, and the pre-process is the same???
View more
  • x
  • convention:

Comment

You need to log in to comment to the post Login | Register

Notice: To protect the legitimate rights and interests of you, the community, and third parties, do not release content that may bring legal risks to all parties, including but are not limited to the following:
  • Politically sensitive content
  • Content concerning pornography, gambling, and drug abuse
  • Content that may disclose or infringe upon others ' commercial secrets, intellectual properties, including trade marks, copyrights, and patents, and personal privacy
Do not share your account and password with others. All operations performed using your account will be regarded as your own actions and all consequences arising therefrom will be borne by you. For details, see " User Agreement."

My Followers

Login and enjoy all the member benefits

Login

Block
Are you sure to block this user?
Users on your blacklist cannot comment on your post,cannot mention you, cannot send you private messages.
Reminder
Please bind your phone number to obtain invitation bonus.