Skip to content

issues Search Results · repo:open-mmlab/mmdetection language:Python

Filter by

8k results
 (92 ms)

8k results

inopen-mmlab/mmdetection (press backspace or delete to remove)

I have been trying to train an object detection model, using Faster RCNN and Swin Backbone, however, I am going through several hoops. Here is my training config: Config Script to train RCNN / Swin ...
  • kameshkotwani
  • Opened 
    16 hours ago
  • #12389

请问现在框架是否支持定义多个验证集 Motivation 做域泛化需要测试多个目标域,目前detectron2是可以很方便添加多个数据集的,但我没有在mmdetection文档里面找到相应的配置功能。 我预想的良好设计是可以使用列表的方式去添加多个数据集就像这样: val_dataloader = [ dict( ... dataset=dict( ...
  • binbla
  • Opened 
    2 days ago
  • #12387

Checklist - [x] I have searched related issues but cannot get the expected help. - [x] I have read the [FAQ documentation](https://mmdetection.readthedocs.io/en/latest/faq.html) but cannot get the ...
  • codingbus821
  • Opened 
    3 days ago
  • #12386

I have been trying to install the MMDetection library as given in the get started step, however, I am facing significant library conflict issues. I want to install: mmdetection PyTorch any compatible version ...
  • kameshkotwani
  • 4
  • Opened 
    7 days ago
  • #12385

After training a model for instance segmentation, I used SAHI s slicing inference (via demo/large_image_demo.py) to handle large images. However, the predicted masks are not being merged properly – they ...
  • kieran0625
  • 1
  • Opened 
    10 days ago
  • #12384

mmcv platform is so difficult, I have met many many problems and I still can t to train it. WTF
  • X-WN
  • Opened 
    11 days ago
  • #12382

在多机训练时,跑完一轮开始测试的时候报了这个错误。发现主节点上可以创建.pkl文件,但从节点没办法创建,请问如何解决
  • Jackluisus
  • Opened 
    13 days ago
  • #12381

Recently, I have been using rtmdet to train specific model for object detection, image size in dataset is 2448 * 2048, I want to train the rtmdet_s_model with original image size(2448 * 2048), but when ...
  • ashlod
  • Opened 
    17 days ago
  • #12380

Hi, I m dealing with a lot of overlapping bounding box predictions during training my model. So I was wondering, does it make sense to optimize things like nms.iou_threshold during the validation step ...
  • ir2718
  • Opened 
    19 days ago
  • #12379

I was trying to load weights of pretrained model of yolox_large from the documentation of the YOLOX readme into the backbone yolox_large which I will training on my custom dataset. But it is showing missing ...
  • Abhishek0075
  • Opened 
    25 days ago
  • #12377
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! 
Press the
/
key to activate the search input again and adjust your query.
Issue search results · GitHub