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
1
vote
2 answers

How to evaluate Tensorflow Object Detection API on only one particular class?

I have trained an object detection model from Tensorflow Object Detection API faster_rcnn_inception_resnet_v2_atrous_coco on about 10 classes. When I run the model_main.py file to evaluate the model, it seems to only give the mean Average Precision…
Kien Pham
  • 13
  • 9
1
vote
0 answers

Can deep learning determine if two samples of handwriting are by the same person?

I have dabbled using Tesseract CNN OCR on handwriting records before and was surprised by the accuracy. I am wondering, is it possible to use it, or something else, to determine if a sample of handwriting is written by the same person? I have…
Overstacker72
  • 11
  • 1
1
vote
0 answers

Train Pnet of mtcnn, the bounding box regression acc is very low! How to increase it? or is my lebal wrong?

I use the FDDB face pic to train the mtcnn for face detection. In the pnet, for bounding box regression, the acc stay around the 60%. Is there something wrong? Epoch 397/400 1200/1200 [==============================] - 0s 131us/sample - loss: 0.5068…
user5671629
  • 11
  • 1
1
vote
1 answer

What image size is suitable for MaskRCnn?

I am training a MaskRcnn on document images with size (256,256,3) and unable to get a good accuracy. if I increase the image size the code throw GPU memory gull error. Should I increase the training image? What else can I do to improve the…
hR 312
  • 824
  • 1
  • 9
  • 22
1
vote
1 answer

Getting the x,y coordinates of the predicted masks from the images after model.detect() with MaskRcnn

How to extract the x,y coordinates of the polygons from the predicted masks with Mask Rcnn after detection. My implementation for object detection is this results = model.detect([image], verbose=1) I can get the ROIs, masks,class_ids,class names and…
Malathi
  • 350
  • 1
  • 11
1
vote
1 answer

Transfer Learning with a Faster RCNN Inception Resnet | Why new checkpoints get saved for each step after a first checkpoint?

I have ~24000 images in widescreen format 1920x384 and want to do transfer learning by training six classes of objects available in my image data set onto a faster_rcnn_inception_resnet_v2_atrous_coco network, pretrained on the COCO dataset, which I…
gehbiszumeis
  • 3,525
  • 4
  • 24
  • 41
1
vote
1 answer

Can't train faster rcnn

I want build my own Faster Rcnn model, I download an example from https://github.com/dBeker/Faster-RCNN-TensorFlow-Python3 I get an error when running the code, and I don't know why Traceback (most recent call last): File…
feng lin
  • 11
  • 1
1
vote
1 answer

should I create json annotation for validation images?

I am trying to implement mask rcnn for my own dataset but couldnt find any info about annotations for the val folder that contains the images for validattion. I created json annotations using Via 2.0.8 for my training set and that make senese. but…
FacelessVoid
  • 27
  • 1
  • 3
1
vote
1 answer

implementing mask-r-cnn with tensorflow-distributed

I'm training a mask-r-cnn network, which is built on tensorflow and keras. I'm searching for a way to reduce training time, so I thought implementing it with tensorflow-distributed. I've been working with mask-r-cnn for some time, but it seems what…
JavaNoobb
  • 11
  • 2
1
vote
1 answer

Object detection - Ignore specific image zones during training

Im trying to use the Faster R-CNN Algorithm for vehicle detection using keras. I have a dataset containing different folders with every folder containing multiple images. I've managed to transform the annotation files for the images into a CSV file…
Zouhair Elamrani Abou Elassad
  • 210
  • 1
  • 3
  • 9
1
vote
0 answers

Optimizing Faster R-CNN Inception Resnet v2 for my need

I'm using the Faster R-CNN Inception Resnet v2 model pre-trained on COCO to train my own object detector with the purpose of detecting objects from 3 classes. The objects are small compared to the size (resolution) of the image. I'm relatively new…
fendrbud
  • 89
  • 1
  • 11
1
vote
0 answers

Object Detection API: Faster-RCNN, issue on Image Dimensions

I have trained my model on Image Size: 720*700 pxs with a modification of the following two files. i. object detection / core / preprocessor.py: def resize_image(image, masks=None, new_height=4160, …
Waqar Ali
  • 11
  • 1
1
vote
0 answers

How and why we use CNN layer wrapped with time distributed layer?

I need to know how this code works. It's taking Embedding then it sends it into this model. model1 is CNN and moel2 is Time distributed layer. Why wrapping is done in this code, i didn't find article on this. model1 =…
Mayank Kumar Mittal
  • 11
  • 1
1
vote
0 answers

How do I train RPN in Tensorflow for faster-rcnn

I am trying to build the Faster-rcnn architecture defined here. There are three main parts, the feature extractor, region-proposal-network (rpn), and the detection/classification network. I was able to build the feature extractor with a Resnet…
Colin Steidtmann
  • 417
  • 1
  • 4
  • 10
1
vote
1 answer

What's the difference between "BB regression algorithms used in R-CNN variants" vs "BB in YOLO" localization techniques?

Question: What's the difference between the bounding box(BB) produced by "BB regression algorithms in region-based object detectors" vs "bounding box in single shot detectors"? and can they be used interchangeably if not why? While understanding…
Anu
  • 3,198
  • 5
  • 28
  • 49
1 2 3
…
22 23