Stack Overflow
Stack Overflow

Questions tagged [faster-rcnn]

Faster-RCNN is a very common Regional Convolutional Neural Network architecture that detects and recognizes objects in images in a single forward pass

332 questions
3
votes
1 answer

Are anchor box sizes in torchvision's AnchorGenerator with respect to the input image, feature map, or something else?

This is not a generic question about anchor boxes, or Faster-RCNN, or anything related to theory. This is a question about how anchor boxes are implemented in pytorch, as I am new to it. I have read this code, along with a lot of other stuff in the…
millivolt9
  • 56
  • 5
3
votes
0 answers

Mutiple backgrounds for object detection with mask r cnn

I'm trying to train a mask r cnn algorithm for object detection. Right now I have 21 classes with the corresponding annotations but my task is to detect only 13 of them, the other 8 classes should be recognize as background. For the CustomConfig…
Dvd
  • 117
  • 3
  • 7
3
votes
1 answer

Extract object features from Detectron2

I am really new to object detection, so sorry if this question seems too obvious. I have a trained FasterRCNN model on detectron2 that detects objects, and I am trying to extract the features of each detected object for the output of my model's…
nkay4321
  • 31
  • 1
3
votes
1 answer

The result is empty when prediction of Faster RCNN model (Pytorch)

I'm trying to train Faster RCNN model. After training, I try to predict the result of image but the result is empty. My data is w: 1600, h: 800, c: 3, classes: 7, bounding boxes:(x1, y1, x2, y2) My model is below. My model import torchvision from…
Steven
  • 31
  • 2
3
votes
2 answers

Replace instance of a class with new instance

I am working on detectron2 object detection. I am facing a problem in filtering the objects detected. Here is the detectron2 predicted output: Instances(num_instances=9, image_height=547, image_width=820, fields=[pred_boxes:…
Rathish Kumar B
  • 1,271
  • 10
  • 21
3
votes
1 answer

(Faster R-CNN) ROI Pooling layer is not differentiable w.r.t the box coordinates

The paper reports that "having an RoI pooling layer that is differentiable w.r.t the box coordinates is a nontrivial problem" and refers to "ROI Warping" (crops and resizes the features to a fixed shape) that makes it fully differentiable w.r.t the…
Austin
  • 31
  • 1
3
votes
0 answers

RuntimeError: input and output sizes should be greater than 0, but got input (H: 1024, W: 1) output (H: 800, W: 0)

when I try to finetune the pytorcfaster-rcnn following the official tutorial: https://pytorch.org/tutorials/intermediate/torchvision_tutorial.html with the Wider-Face dataset. I got: RuntimeError: input and output sizes should be greater than 0, but…
Loay Sharaky
  • 227
  • 1
  • 2
  • 7
3
votes
1 answer

Mean Average Precision interpretation

I have a question about how to interpret this mAP metric, for example, if an object detector gets a mAP of 48. Is this a good result? or if you have an AP of 50, is it different? He went back to the IoU, could it be that if it is mAP50, it means…
Sebastián
  • 437
  • 5
  • 19
3
votes
1 answer

Object Detection Model (PyTorch) to ONNX:empty output by ONNX inference

I try to convert my PyTorch object detection model (Faster R-CNN) to ONNX. I have two setups. The first one is working correctly but I want to use the second one for deployment reasons. The difference lies in the example image which I use for the…
Tom
  • 91
  • 7
3
votes
2 answers

After finetuning Faster RCNN object detection model, how to visualize bbox prediction?

I finetuned pytorch torchvision model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True) on my own custom dataset. I followed this guide…
adam l
  • 33
  • 1
  • 4
3
votes
1 answer

Reduce the size of fasterRCNN array output, using Gluon, python

I'm using a faster rcnn model to run some object detection. The wrapper I'm using is gluon and the code is below: net = model_zoo.get_model('faster_rcnn_resnet50_v1b_coco', pretrained=True) im_fname =…
Dave
  • 454
  • 1
  • 7
  • 17
3
votes
1 answer

Is it necessary to label every object of a class on an image?

I labeled a bunch of Images for training a Faster-RCNN network for object detection with one class. There are about hundrets or thousands of objects of this class on every Image. Do I have to label all of them? For now i labeled about 20 to 80…
DE2468
  • 33
  • 5
3
votes
1 answer

nvcc fatal : '--ptxas-options=-v': expected a number

Getting the nvcc fatal : '--ptxas-options=-v': expected a number error when I try to build a Windows port of Faster-RCNN. You may reach the setup file (which is a Python script) directly from here. Software Environment: - CUDA v10.1 - VS 2019 -…
talha06
  • 6,206
  • 21
  • 92
  • 147
3
votes
1 answer

What is scale-invariance and log-space translations of a bounding box?

In slow R-CNN paper, the bounding box regression's goal is to learn a transformation that maps a proposed bounding box P to a ground-truth box G and we parameterize the transformation in terms of four functions dx(P),dy(P),dw(P),dh(P). The first 2…
Anu
  • 3,198
  • 5
  • 28
  • 49
3
votes
2 answers

How to make tensorflow object detection faster-r cnn model work on Android?

I have a question about Tensorflows Object Detection API. I trained Faster R-CNN Inception v2 model with my own dataset for Traffic Sign Classification and I want to deploy it to Android but Tensorflows Object Detection API for Android and/or…
Yusuf Altıparmak
  • 456
  • 1
  • 6
  • 16
1
2
3
…
22 23