Category "object-detection"

inner holes in segmentation polygons -coco dataset

So to explain the problem I have a dataset with the coco format I want to reconstruct the binary mask from the segmentation information stored in the annotation

Tensorflow image too small to display results properly

Is there a possible way for me to resize or change the way the results are being displayed for my object detection? Any help would be greatly appreciated!

Can someone explain the output of forward() in DNN module?

when I learn YOLO using opencv, and I use 1 class. outs = net.forward(output_layers) if I print the output is as follows: [9.31552518e-03 7.26305973e-03 2.5157

object detection with YOLO in 2 stream cameras using multithread and opencv

I want to do object detection with YOLO in 2 stream cameras. I use multithread and the result is like in the video. So when 2 camera streams are used, object de

No such file or directory when using DataLoader.from_pascal_voc

I'm having trouble using DataLoader.from_pascal_voc from TFLite Model Maker. I've successfully mounted Google Drive into Google Colab and when I printed the len

Error when converting xml files to tfrecord files

I am following the TensorFlow 2 Object Detection API Tutorial on a Macbook Here's what I got when running the given script for converting xmls to TFrecords Trac

(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

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 p

Calculating YOLO mAP against test dataset

AFAIK YOLO calculates mAP against validation dataset during training. Now is it possible to calculate the same against unseen test dataset ? Command: ./darknet

Tensorflow2 object detection error when i am creating train.record and test.record

usage: generate_tfrecord.py [-h] [-i IMAGEDIR] [-o OUTPUTDIR] [-r RATIO] [-x] generate_tfrecord.py: error: unrecognized arguments: /content/training_demo/images

Understanding Detectron2 COCO Evaluator

I am evaluating Cityscapes dataset using COCOEvaluator from Detectron2. I want to know if COCO Evaluation metric implemented in Detectron2 takes into considerat

Print class name from tensorflow object detection api

PLEASE NOTE: I have tried other solutions accross the web and didnt find the working result. I am detecting objects from live feed using tensorflow object detec

I keep getting this error: TypeError: tuple indices must be integers or slices, not tuple

I am trying to do this tutorial: https://colab.research.google.com/drive/1d8PEeSdVlP0JogKwkytvFeyXXPu_qfXg?usp=sharing#scrollTo=sDixMreeUS_9 and this is https:/

Add new class to YOLOv3-tiny/v4-tiny in darknet

I'd like to ask you if it's possible to extend/add new class to pre-trained yolov3/v4-tiny model. I need to add shoe. Let's say it would be 81st object. My expe

Open CV snap points to a rectangle of a specific size

I am attempting to detect an image of a certain type on a page of degraded quality, that has rotational and translational variance. I need to "cropped" the dete

Tensorflow object detection "Use fn_output_signature instead" warning

I am following this tutorial to train my own models. https://tensorflow-object-detection-api-tutorial.readthedocs.io/en/latest/ I followed all the steps exactly

Transfer learning using tensorflow object detection api

I'm trying to train the model using pretrained faster_rcnn_inception_v2_coco. I'm using the following config file: model { faster_rcnn { num_classes: 37

How to plot ROC-AUC figures without using scikit-learn

I have the following list containing multiple tuples of (TP, FP, FN): [(12, 0, 0), (5, 2, 2), (10, 0, 1), (7, 1, 1), (13, 0, 0), (7, 2, 2), (11, 0, 2)] each tu

How to transfer learning or fine tune YOLOv4-darknet with freeze some layers?

I'm a beginner in object detection field. First, I followed YOLOv4 custom-train from here, I have successfully followed the tutorial. Then I started to think th

One box object detection

I am using a faster rcnn model to predict one object in an image. There can only be one object in each image. Is it possible to force Faster Rcnn to train and p