Use "detectron" tag for questions related to FAIR's detectron or detectron2 framework for object detection and segmentation.
Questions tagged [detectron]
217 questions
0
votes
0 answers
How can I convert a spatial dataset (raster and vector) to COCO format for object detection?
I am doing an object detection project using detectron2, which requires datasets to be in COCO format. This format needs images as png and polygons in a JSON file. However, spatial images (e.g. satellites or drones) are georeferenced (tif format),…
Andres Camilo Zuñiga Gonzalez
- 487
- 4
- 7
0
votes
1 answer
ValueError: while training detectron2 model
I am training a detectron2 model on google cloud platform and want to run thin model on 4 gpus.
to launch the training i am using:
if __name__ == "__main__":
launch(main, num_gpus_per_machine=4)
but when i run this model training i get an…
Nitya Rakhe
- 41
- 2
0
votes
1 answer
Received server error (500) from primary and could not load the entire response body
I'm running a detectron2 instance segmention with a AWS endpoint, I used this tutorial [https://github.com/aws-samples/amazon-sagemaker-pytorch-detectron2][1] for Object Detection, and I adapted to instance segmentation and worked well, but to draw…
Curious G.
- 838
- 8
- 23
0
votes
1 answer
Running detectron2 in C++. Encountered TorchVision Error while building tools/deploy/torchscript_mask_rcnn.cpp
I want to run the detectron2 model in C++. I am using the steps mentioned in the readme. I took the following steps:
I setup libtorch by unzipping libtorch-cxx11-abi-shared-with-deps-2.0.0+cpu.zip in /home/hiqbal/Downloads/libtorch
Installed torch…
HIq
- 105
- 6
0
votes
1 answer
Keypoint detection for objects with double symmetry
I'd like to detect something like game cards in images and I need to very precisely pinpoint their corners.
I wanted to use a framework like Detectron2 or Keras which support keypoint detection. The problem is that in these sorts of frameworks,…
user2203031
- 402
- 3
- 14
0
votes
0 answers
Detectron2 pre-trained model using layoutparser in Docker container Error: Checkpoint Not Found
following is my Dockerfile.
FROM python:3.9
RUN apt-get clean && apt-get update
pip install --upgrade pip
RUN pip install layoutparser
RUN pip install "layoutparser[ocr]"
RUN pip install pytesseract
RUN pip install pdf2image
RUN pip install…
SMI
- 71
- 1
- 11
0
votes
0 answers
How can I create a confusion matrix with the results of the COCOEvaluator of detetctron2?
I am really new in this topic and I wanted to ask how I can generate the file instances_default.json for the confusion matrix described in the answer here:
Build confusion matrix for instance segmantation (mask r-cnn from detectron2)
If I am using…
NewOnThis
- 1
- 1
0
votes
1 answer
AttributeError: module 'os' has no attribute 'geteuid'
when I run the code on Win11
# PyTorch still may leave orphan processes in multi-gpu training.
# Therefore we use a deterministic way to obtain port,
# so that users are aware of orphan processes by seeing the port occupied.
port = 2 ** 15 + 2…
zhang zhang
- 1
- 1
0
votes
0 answers
I can't install the module detectron2 for python
I tried many times to install the library . It always ended up with a different error.
I tried to install the detectron environment thanks to anaconda. I used the same interpreter in Visual studio code.
The last error is :
"""
Requirement already…
chloe bke
- 1
- 1
0
votes
0 answers
How do i register my custom dataset for detectron2
I am using my custom images for object detection using detectron2. I have created a json file with the details and annotations of my images. And the code I am using to register my dataset is:
def load_data(t):
if t == "train":
with…
Nitya Rakhe
- 41
- 2
0
votes
0 answers
IOU configuration do not overlap in Detectron2
I'm researching the IOU configuration in detectron2,
the configuration for ensuring that the bounding boxes detected do not overlap with each other.
How is this configuration set up in detectron2?
Thank you.
I has…
Son Le
- 13
- 6
0
votes
1 answer
In detectron2, how can I assign the same color to bounding box of same class?
I am learning detectron2 for using Faster R-CNN.
I am trying to draw the bounding boxes of same class. For example, if bounding box includes "cat", it is blue while if another bounding box includes "dog", it is assigned to red.
However, the below…
Seunghyeon
- 103
- 1
- 2
- 10
0
votes
0 answers
Does detectron2 normalise the bounding box?
I know that detectron2 pefrom normalization for the training and inference image but does it normalise the bounding box as well? Also, for custom dataset, do we need to pass own value for PIXEL_MEAN, PIXEL_STD? Any help would be very much…
0
votes
0 answers
detectron2 diffusioninst: oom-kill during training
I tried to run code for DiffusionInst based on Detectron2 (source code: https://github.com/chenhaoxing/DiffusionInst). During my training, my python process has always been killed (at 10000-20000 iteration epochs, which is insufficient for…
noname
- 11
- 2
0
votes
0 answers
Detectron2 saving predicted annotation images to COCO file
I am doing semantic segmentation. Detectron2 can produce prediction mask labels as pictures.
Can I save the predicted annotation images in COCO file instead of pictures. The COCO file can be used for editing in annotation tools like labelme.
Do you…
Lim Cheng Wei
- 11
- 3