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 Save & Reuse mask of panoptic segmentation ( detectron2 ) using opencv drawContours?
In detectron2 the output get the bellow output upon predection.
panoptic_seg, segments_info = predictor(im)["panoptic_seg"]
it can be drawn via draw_panoptic_seg_predictionsfunction, but we want to save the mask deatils & redraw using opencv how…
ArnabGhosh
- 35
- 6
0
votes
0 answers
Register custom RPN/ROI in detectron2 registry
I currently try to get EfficientPS (https://github.com/vincrichard/EfficientPS) running.
When I start the training, the initialisation of the net crashes due to a key error belonging to detectron2.
During execution of the init method of…
Marco
- 33
- 7
0
votes
2 answers
Installed C++ build tools via Visual Studio Installed, but pip install pycocotools still give me error
Installing pycotools via pip install gives the error
error log of failing to install pycotools
I have installed C++ build tools via Visual Studio Installed
image of installed C++ build tools
But, when I pip install pycocotools,
It still gives the…
Zhang Henry
- 1
- 2
0
votes
0 answers
How to do Semantic segmentation with detectron2
I'm using Detectron2 to do instance segmentation as in the tutorial. Below is the code:
from detectron2.config import CfgNode
import detectron2.data.transforms as T
from detectron2.data import build_detection_train_loader,…
Abdul Salama
- 1
- 1
0
votes
2 answers
detectron2: throws NotImplementedError: while using pre-trained model
I'm trying to use the pre-trained model of detectron2. While running the following code, it shows NotImplementedError.
import torch
torch.__version__
import torchvision
#torchvision.__version__
!pip install detectron2 -f…
0
votes
1 answer
How to implement a custom FastRCNNOutputLayers on Detectron2?
I need to implement a new architecture on the Faster-RCNN classifier on top of Faster-RCNN model implemented in Detectron2 framework. I need to implement both a new loss function on classification and a new inference logic.
As reported in the…
GLastrucci
- 1
- 1
0
votes
1 answer
Can't build Docker image with detectron2 on MacOS
Problem is that, I can't build image with detectron2 using Docker. I use official Dockerfile, that I found on GitHub:
FROM nvidia/cuda:11.1.1-cudnn8-devel-ubuntu20.04 # 18.04 didn't work also
ENV DEBIAN_FRONTEND noninteractive
RUN apt-get update &&…
dokichan
- 857
- 2
- 11
- 44
0
votes
1 answer
How to change the model parameter saving location when training with DefaultTrainer in detectron2
my code is like following:
cfg = get_cfg()
...
trainer = DefaultTrainer(cfg)
trainer.resume_or_load(resume=False)
trainer.train()
After training, the model is automatically saved in./output/model_final.pth. I found the folder where the model is…
0
votes
1 answer
Error converting Detectron2 torchscript model to CoreML using coremltools
I have a Detectron2 model that is trained to identify specific items on a backend server. I would like to make this model available on iOS devices and convert it to a CoreML model using coremltools v6.1. I used the export_model.py script provided…
Brooke Steele
- 1
- 1
0
votes
1 answer
Using detectron2 for training, pytorch's runtime error 'default process group has not been initialized'
Instructions To Reproduce the Issue:
Full runnable code or full changes you made:
I tried to train DeepLabV3+ architecture with a customized config having ResNet18 (converted to .pkl from https://download.pytorch.org/models/resnet18-f37072fd.pth)…
Mohammad Qodrati
- 45
- 1
- 10
0
votes
1 answer
How is it possible to have different input image sizes in Detectron2?
I am using Detectron2 (Mask-RCNN Model) and passed by:
_C.INPUT.MIN_SIZE_TEST = (800, 832, 864, 896)
_C.INPUT.MAX_SIZE_TEST = 1333
How is it possible to have different input image sizes?
How are they entered into the model and Shouldn't the model…
0
votes
0 answers
No module named 'densepose'
installing the following using pip in collab notebook :
pip install torch==1.10.1+cu102 \
torchvision==0.11.2+cu102 \
torchaudio==0.10.1 \
-f https://download.pytorch.org/whl/torch_stable.html \
detectron2==0.6 \
-f…
0
votes
1 answer
Detectron2 object detection
Do anyone know what is this error:
WARNING:root:Torch AMP is not available on this platform
Because I followed this detectron2 object detection tutorial:…
NJR11
- 41
- 4
0
votes
1 answer
detectron2 - how to verify the number of images after augmentation?
I can see that augmentations were applied but i can't see the resulted size of the training set. How can I check it? It's important because when calculating epochs, the dataset size after augmentation should be considered.
When I train a model using…
YonHar
- 11
- 1
0
votes
2 answers
Detectron 2 to Onnx
I want to convert a model into onnx
But when I import caffe2_export for exporting model to onnx I get this error
from detectron2.export import caffe2_export
ERROR
import onnx.optimizer
ModuleNotFoundError: No module named 'onnx.optimizer'
Eirini Kotzia
- 136
- 6