Stack Overflow
Stack Overflow

Questions tagged [detectron]

Use "detectron" tag for questions related to FAIR's detectron or detectron2 framework for object detection and segmentation.

217 questions
13
votes
4 answers

_C.cpython-38-x86_64-linux-gnu.so: undefined symbol: _ZN6caffe28TypeMeta21_typeMetaDataInstanceIdEEPKNS_6detail12TypeMetaDataEv

What is the reason for this error and how can I fix it? I am running the code from this repo: https://github.com/facebookresearch/frankmocap (frank) mona@goku:~/research/code/frankmocap$ python -m demo.demo_frankmocap --input_path…
Mona Jalal
  • 34,860
  • 64
  • 239
  • 408
8
votes
3 answers

How many images per iteration in Detectron2

I am new to using detectron2, just learning it.This might be a noob question, but I really need the answer. I find nothing related to number of epochs in the repository. We know , epoch means single passing of all data through the model, and a batch…
Sawradip Saha
  • 1,151
  • 11
  • 14
7
votes
1 answer

What is total_loss,loss_cls etc

I want to train a custom dataset on using faster_rcnn or mask_rcnn with the Pytorch and Detectron2 .Everything works well but I wanted to know I want to know what are the results I have. [11/29 20:16:31 d2.utils.events]: eta: 0:24:04 iter: 19 …
Miliia
  • 83
  • 1
  • 3
5
votes
1 answer

what does cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.5 do in detectron2?

Hope you're doing great! I didn't really understand these 2 lines from the detectron2 colab notebook tutorial, I tried looking in the official documentation but i didn't understand much, can someone please explain this to me…
Mountassir EL MOUSTAAID
  • 79
  • 1
  • 4
5
votes
0 answers

pip: No matching distribution found for detectron2

When I have the following line in requirements.txt detectron2 -f https://dl.fbaipublicfiles.com/detectron2/wheels/cu101/index.html I get an error: ERROR: Could not find a version that satisfies the requirement detectron2 (from versions:…
szabgab
  • 6,202
  • 11
  • 50
  • 64
5
votes
1 answer

How do I convert a Detectron2 model into another deeplearning framework?

I would like to convert a detectron2 model into a another deeplearning framework i.e. PyTorch, TensorFlow or ONNX. How do I do this conversion? I can run inference on the detectron2 model with the cfg (which I believe means config in detectron2…
KamKam
  • 103
  • 1
  • 8
5
votes
1 answer

How to save and load models of custom dataset in Detectron2?

I have tried to save and load the model using: All keys are mapped but there is no prediction in output #1 from detectron2.modeling import build_model model = build_model(cfg) torch.save(model.state_dict(), 'checkpoint.pth')…
Ajay Pyatha
  • 154
  • 1
  • 9
5
votes
1 answer

Detectron2 - Extract region features at a threshold for object detection

I am trying to extract region features where class detection is higher than some threshold using the detectron2 framework. I will be using these features later in my pipeline (similar to: VilBert section 3.1 Training ViLBERT) So far I have trained a…
Kevin
  • 3,077
  • 6
  • 31
  • 77
4
votes
0 answers

Detectron2 - Same Code&Data // Different platforms // highly divergent results

I use different hardware to benchmark multiple possibilites. The Code runs in a jupyter Notebook. When i evaluate the different losses i get highly divergent results. I also checked the full .cfg with cfg.dump() - it is completely…
Natrium2
  • 83
  • 7
4
votes
0 answers

Can't build Detectron2 on Windows 10

Although there's no official support for Detectron2 on Windows, there're many instructions available. I tried following these instruction, but ended up with the same error. Here's my setup: OS: Windows 10 Pro 19043.1466 Microsoft Visual Studio:…
SagRU
  • 448
  • 4
  • 17
4
votes
3 answers

What do the class labels output be detectron 2 refer to?

In the documentation for detectron2, it states that class labels are located in output_dict['Instances'].pred_classes. This is all fine, and I can access this easily, but at no point in the documentation (or the output dictionary, as far as I can…
user8577930
  • 193
  • 2
  • 9
3
votes
1 answer

How to use detectron2's augmentation with datasets loaded using register_coco_instances

I've trained a detectron2 model on custom data I labeled and exported in the coco format, but I now want to apply augmentation and train using the augmented data. How can I do that if I'm not using a custom DataLoader, but the…
Ramon Griffo
  • 333
  • 5
  • 14
3
votes
0 answers

Detectron2: Inference using pre-trained model - The checkpoint state_dict contains keys that are not used by the model: pixel_mean pixel_std

I m trying to do inference on a pre-trained model (centermask2) with Detectron2. The inference results are not great, and I get this message below - The checkpoint state_dict contains keys that are not used by the model: pixel_mean …
Peter Lee
  • 31
  • 1
3
votes
0 answers

Convert a torchscript model into Core ML

I am trying to convert a Detectron 2 model into Core ML. I have scripted it and now I have a model of type 'torch.jit._script.RecursiveScriptModule'. If I try and convert it into Core ML using this code: mlmodel = ct.converters.convert( …
Gle6557
  • 31
  • 2
3
votes
2 answers

detectron 2 custom weight file not detecting object

I am trying to train a custom model from within the coco dataset just for one class - apple.This is for instance segmentation. I have used some opensource programs to extract the apple images and corresponding json file with the bounding box data…
Akshay Acharya
  • 253
  • 4
  • 13
1
2 3
…
14 15