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 to scale up inference prediction with detectron with PaddleOCR using Ray in Python
I am using Ray and trying to perform image classification (using Detectron2) and OCRing (using PaddleOCR). I have 2 APIs for the same.
Tried to autoscale the APIs but my RPS is 1-2 with Image classification & OCR and max 15 RPS with only image…

R.K
- 1,721
- 17
- 22
0
votes
0 answers
How to run paddleocr-gpu after detectron2
I have a detectron2 model for image classification followed by paddleocr.
My detectron runs on GPU while paddleocr on CPU and the complete request takes 2-4s for execution.
when I try to run paddleocr-gpu, i get an error "gpu properties already…

Kiran Roy
- 1
- 1
0
votes
0 answers
Eliminate Classification Head in Mask R-CNN
Is it possible to remove the classification head in Mask R-CNN.
Despite enabling class-agnostic settings for both bounding box regression and mask prediction, I am still observing classification loss during training. This seems to suggest that the…
0
votes
0 answers
detectron2 model evaluation error :Unsupported type found in checkpoint! epoch:
I was trying to evaluate detectron2 model separately using model.pth file in python using the below code:
import torch
import detectron2
from detectron2.config import get_cfg
from detectron2.engine import DefaultPredictor
from detectron2.evaluation…

Abin Jilson
- 35
- 6
0
votes
0 answers
running build_ext gives `[WinError 2] The system cannot find the file specified` while building detectron2
I'm currently trying to build detectron2 in environment in Anaconda. Below is the packages that I'm using in my env:
windows 11
conda package
python 3.8
cuda 11.3
pytorch 1.11
torchaudio 0.11.0
torchvision 0.12.0
ninja 1.10.2
pybind11 2.10.4
I've…

lea
- 1
- 2
0
votes
0 answers
Extracting Info from detectron2 panoptic segmentation and using it to mask a particular object in an image
In theory, I'd like to emulate what is done at the beginning of this blog: https://www.sicara.fr/blog-technique/dataset-generation-fine-tune-stable-diffusion-inpainting
I need to do it using detectron2 so as to use the capability of it panoptic…
0
votes
0 answers
Augmentation and transformations in Detectron2
I'm working on a custom Faster RCNN with Detectron2 framework and I have a doubt about transformation during training and inference. I created a custom Trainer inheriting from DefaultTrainer class and I overridden build_train_loader and…

Agostino Dorano
- 31
- 1
- 5
0
votes
0 answers
`ERROR: Failed building wheel for detectron2` when installing detectron2 through a docker image in a DigitalOcean droplet
I'm running into an error when installing detectron2 in a docker image in a digital ocean droplet but it works with no problems when I build the docker image in my local machine.
EDIT: Upon rebuilding with --no-cache the dockerfile below doesn't…

neil_ruaro
- 368
- 3
- 15
0
votes
0 answers
Getting RuntimeError : configs/COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml not available in Model Zoo! while Running Detectron2 for Object Detection
Want to train a custom Image Dataset by Detectron2 Faster_RCNN model . I am using a wsl2 ubuntu terminal and a VScode in my windows os. In my train.py, I initiate a config_file_path with "configs/COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml" for…

Ridoy Kanto Joy
- 1
- 1
0
votes
0 answers
Detectron2LayoutModel requires the detectron2 library but it was not found in your environment
I have Windows and went through installation for installing Detectron2 on Windows: [Detectron2 walkthrough (Windows)][1]
I write a code in jupyter notebook. If I change directory to where I installed detectron2 as mentioned above, import detectron2…

Anya Pilipentseva
- 117
- 10
0
votes
0 answers
ImportError: cannot import name ‘is_compiling’ from ‘torch._dynamo’
This is a repeat of the question from here
I have a jetson agx orin developer kit and I am following instructions from here to install cuda version of pytorch and torchvision. I successfully installed everything and the verification outputs are the…

ASH
- 31
- 1
- 5
0
votes
0 answers
How to generate same metrics as Yolo from detectron2?
Currently, by default detectron2 gives the following output
whereas I want to generate the F1 curve, precision-recall, precision-confidence curve, and confusion matrix among other metrics. Can anyone help me with this or point me in the right…

raj-kapil
- 177
- 1
- 15
0
votes
0 answers
How can I fix 'Non-existent config key: MODEL.DENSEPOSE_ON' error in Flask using detectron2-densepose?
I have made multiple attempts to reinstall it, but whenever I press the button to use DensePose on the uploaded image, I encounter the following error: "KeyError: 'Non-existent config key: MODEL.DENSEPOSE_ON'". You can view the error message…

Rokec
- 1
0
votes
0 answers
Heroku deploy detectron2 could not find a version
i'm trying to deploy my python flask app to heroku. when i'm pushing to repository to heroku that's occurs
remote: ERROR: Could not find a version that satisfies the requirement
detectron2==0.6 (from versions: none)
remote: ERROR: No…

ba_rt
- 85
- 2
- 9
0
votes
0 answers
How to use Densepose after successfully installing detectron2
I want to use densepose. For that I have successfully installed detectron2 in my windows and it is generating simple images fine. But I want to generate the image just like the one attached below and I am unable to generate it using densepose. enter…