Skip to content

issues Search Results · repo:yqyao/SSD_Pytorch language:Python

Filter by

39 results
 (64 ms)

39 results

inyqyao/SSD_Pytorch (press backspace or delete to remove)

yqyao/SSD_Pytorch
how to merge and VOC07 and VOC12

the method listed in the structions i can t understand, for example, the merged txt list as follows: 2012_test.txt, 2007_test.txt, 0712_trainval_test.txt, 2012_trainval.txt, 0712_trainval.txt how to ...
  • leeyeea
  • 1
  • Opened 
    on Sep 18, 2021
  • #39

yqyao/SSD_Pytorch
ONNX support

This repository is a great work. Thank you for your work. I was wondering if you can add ONNX support to your model. Currently, your model gives following error while exporting to ONNX. I am using resnet50-SSD ...
  • SakshamSinha
  • Opened 
    on Jun 9, 2020
  • #38

yqyao/SSD_Pytorch
pretrain model

hello,could you give me the pretrained-model:mobilenetv2_feature.pth，I can t find it.
  • Fy19951114
  • 1
  • Opened 
    on Jan 7, 2020
  • #37

yqyao/SSD_Pytorch
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
  • 7
  • Opened 
    on Dec 9, 2019
  • #36

yqyao/SSD_Pytorch
关于dataloader

您好，voc0712.py中标注信息为何不进行归一化呢？没有在后续的代码中找到归一化的部分
  • buptcai
  • 1
  • Opened 
    on Dec 1, 2019
  • #35

yqyao/SSD_Pytorch
What does DRF mean？

  • wzz513878041
  • 1
  • Opened 
    on Nov 25, 2019
  • #34

yqyao/SSD_Pytorch
About test your code

hi, when I run your test code, I meet this, Traceback (most recent call last): File demo.py , line 11, in module from data import COCODetection, VOCDetection, detection_collate, BaseTransform, preproc ...
  • ylc2580
  • 1
  • Opened 
    on Aug 4, 2019
  • #33

yqyao/SSD_Pytorch
sigmoid focal loss

@yqyao sigmoid focal loss implement seems not right. origin code: loss_neg = -1. * torch.pow(1 - P, self.gamma) * torch.log(1 - P) * ( 1 - targets) * (1 - alpha_mask) but according to paper, I think it ...
  • pikerbright
  • 1
  • Opened 
    on Aug 2, 2019
  • #32

yqyao/SSD_Pytorch
I only got 78.8 mAP for RefineDet320 on voc2017 test

Hi, I retrained the RefineDet320 but only got 78.8 mAP on VOC2017 test dataset. I didn t change settings in the refine_vgg_voc.yaml file except for the batch size, which I used 99 for three GPU paralleling. ...
  • yijingru
  • 1
  • Opened 
    on May 4, 2019
  • #31

yqyao/SSD_Pytorch
Can not use optim.Adam

File /data/tangkai/SSD_Pytorch/layers/modules/refine_multibox_loss.py , line 164, in forward targets_weighted = conf_t[(pos + neg).gt(0)] RuntimeError: copy_if failed to synchronize: device-side assert ...
  • tuxiangshibie
  • 2
  • Opened 
    on Apr 4, 2019
  • #30
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 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