Skip to content

issues Search Results · repo:kuangliu/pytorch-retinanet language:Python

Filter by

0 results
 (62 ms)

0 results

inkuangliu/pytorch-retinanet (press backspace or delete to remove)

kuangliu/pytorch-retinanet
Issue with encoder.py

Would like to clarify the input for _get_anchor_boxes function under encoder.py is a tuple or a int? As I realised after the code went to line 50 it is not able to assign the values to fm_w and fm_h. ...
  • CluelessIT
  • 1
  • Opened 
    on Feb 18, 2021
  • #79

kuangliu/pytorch-retinanet
Instruction

你这也没个说明，然后也没有数据介绍，真的好难看懂，数据集总是提示不全
  • mayuelala
  • Opened 
    on Nov 14, 2020
  • #78

kuangliu/pytorch-retinanet
classification of image with no objects but having class label as 0

If an image has just background (no objects in entire image,so no need of bounding boxes) with class label 0, will this code give the correct classification as class 0 or should I tweak the loss function? ...
  • sramakintel
  • Opened 
    on May 26, 2020
  • #77

kuangliu/pytorch-retinanet
Background should have been considered in the loss function.

First I want to thank the author for this implementation. I find the overall codes are clear and easy to follow than many others. However, after checking across several others implementations, e.g., https://github.com/NVIDIA/retinanet-examples/blob/5663247b88a19fcdee78ae5ae9fba5b4a88de029/retinanet/model.py#L156-L158 ...
  • zjysteven
  • 1
  • Opened 
    on Jan 22, 2020
  • #76

kuangliu/pytorch-retinanet
About detecting many extra boxes

Hello author, thank you for your hard work! Drawing on your ideas, I am developing my own single-stage object detection network, but there are a lot of extra boxes in the visualization results. Since my ...
  • pengjizhi
  • 2
  • Opened 
    on Dec 9, 2019
  • #74

kuangliu/pytorch-retinanet
pytorch version is 0.4？

  • q248953144
  • Opened 
    on Nov 28, 2019
  • #73

kuangliu/pytorch-retinanet
closed

1
  • miaow1988
  • Opened 
    on Nov 22, 2019
  • #72

kuangliu/pytorch-retinanet
There are too many prediction boxes, although the loss is very low.

I can reduce my loss in both the training dataset and the test dataset to about 0.02, but my output of prediction visualization results is completely wrong, because there are too many prediction boxes. ...
  • chuxiang93
  • 14
  • Opened 
    on Oct 12, 2019
  • #71

kuangliu/pytorch-retinanet
environment

  • aboy2018
  • Opened 
    on Oct 11, 2019
  • #70

kuangliu/pytorch-retinanet
I try to run test.py by using your net.pth, but I get a image without boxes. Can you help me?

  • Ttt749
  • Opened 
    on Sep 27, 2019
  • #69
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue search results · GitHub