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
0
votes
1 answer

How to do object detection on high resolution images?

I have images of around 2000 X 2000 pixels. The objects that I am trying to identify are of smaller sizes (typically around 100 X 100 pixels), but there are lot of them. I don't want to resize the input images, apply object detection and rescale the…
exAres
  • 4,806
  • 16
  • 53
  • 95
0
votes
2 answers

Training Image Size Faster-RCNN

I will train my dataset with faster-rcnn for one class. All my images are 1920x1080 sizes. Should I resize or crop the images or I can train with this size? Also my objects are really small (around 60x60). In the config file there are dimensions…
Emre Tatbak
  • 103
  • 3
  • 11
0
votes
0 answers

Calculate AUC using sensitivity and specificity values

How to calculate AUC, if I have values of sensitivity and specificity for various threshold cutoffs? I have sensitivity and specificity values for 100 thresholds. sensitivity: c(0.649193548387097, 0.649193548387097, 0.649193548387097,…
Dhwani Dholakia
  • 171
  • 7
0
votes
1 answer

How to prepare training data for MATLAB inbuilt multiclass Faster R-CNN function?

I am training Faster-RCNN for multiclass object detection. I am using matlab inbuilt function trainFasterRCNNObjectDetector along with alexnet. The code works fine for single object but when tried for multiple objects it shows "Warning: Invalid…
Yoo
  • 11
  • 3
0
votes
1 answer

Multiple Object Tracking (MOT) benchmark data-set format for ground truth tracking

I am trying to evaluate the performance of my object detection+tracking on the standard dataset used in the industry in the 2DMOT Challenge 2015. I have downloaded the dataset but I am unable to understand the data fields in the labelled ground…
rishabh700
  • 92
  • 9
0
votes
1 answer

Faster-RCNN Pytorch problem at prediction time with image dimensions

I am finetuning Faster-RCNN using PyTorch according to this tutorial: https://pytorch.org/tutorials/intermediate/torchvision_tutorial.html The results are pretty good but making predictions only work when feeding a single tensor to the model. For…
Guillem
  • 2,376
  • 2
  • 18
  • 35
0
votes
1 answer

Errors while implementing mask rcnn (OverflowError: Python int too large to convert to C ssize_t)

I'm trying to implementing Mask R-CNN for my project. I've been trying to detect motorbike from the images. I've annotated images using supervise.ly https://supervise.ly . after various changes in the code an error File "skimage/draw/_draw.pyx",…
saba javad
  • 13
  • 2
0
votes
1 answer

Reducing the Spatial Dimensions of a Neural Network Feature Map

Given a feature map of dimensionality MxNxC (for example, the output of a predicted Region of Interest from a Faster-RCNN), how would one reduce the spatial dimensions to be 1x1xC? I.e. reduce the feature map to be a vector like quantity summarizing…
Jack H
  • 2,440
  • 4
  • 40
  • 63
0
votes
1 answer

Tensorflow Object Detection API Untrained Faster-RCNN Model

I am currently trying to build an Object Detector using the the Tensorflow Object Detection API with python. I have managed to retrain the faster-rcnn model by following the instructions posted here and here However, training time is considerably…
marco
  • 656
  • 2
  • 6
  • 22
0
votes
0 answers

Training frcnn on pytorch 1.0 with cuda: Segmentation fault (core dumped)

I try to use this repo to train FRCNN on my custom VOC dataset: ~/miniconda3/bin/python3 trainval_net.py --dataset pascal_voc --net res101 --cag --bs 1 --nw 1 --lr 1e-3 --lr_decay_step 5 Called with args: Namespace(batch_size=1, checkepoch=1,…
Stepan Yakovenko
  • 8,670
  • 28
  • 113
  • 206
0
votes
1 answer

Need help regarding Transfer Learning a Faster RCNN ResNet50FPN in PyTorch

I am new to PyTorch. I'm trying to use a pre-trained Faster RCNN torchvision.models.detection.fasterrcnn_resnet50_fpn() for object detection project. I have created a CustomDataset(Dataset) class to handle the custom dataset. Here is the custom…
Razin Tailor
  • 13
  • 1
  • 4
0
votes
1 answer

Can't change the Anchors in Faster RCNN

I'm a newbie in pytorch and I was trying to put some custom anchors on my Faster RCNN network in pytorch. Basically, I'm using a resnet50 backbone and when I try to put the anchors, I got a mismatch error. This is the code that I have: backbone =…
mCalado
  • 121
  • 1
  • 19
0
votes
1 answer

OOM when changing batch size (Faster R-CNN Inception v2)

I am a beginner with tensorflow and ML, pardon any obvious mistakes or noob questions. I'm currently working on an object detection problem and experience issues with memory capacity on GPU when training with a batch size which is not equal to 1.…
fendrbud
  • 89
  • 1
  • 11
0
votes
2 answers

Detect tiny objects in tensorflow api object detection model

I have a oject detection model made using tensorflow object detection api and faster rcnn model. This model is able to detect objects which are clearly visible but fails to detect the objects which are tiny/smaller in size or are at a larger…
Ankit
  • 203
  • 3
  • 14
0
votes
1 answer

RCNN vs Fast-RCNN algorithm - how are "Regions of Interest" generated?

I got the below image from the blog post here which was very informative. RCNN In RCNN I get that selective search is used to select Regions of Interest ("proposals") and these are passed into a convNet which produces a feature vector of 4096…
Simon Kiely
  • 5,880
  • 28
  • 94
  • 180
1 2 3
…
22 23