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
0 answers

Find difference between 2 tensorflow view trained models (possible problem in pb file generation)

At the beginning of the year I started to look into Tensorflow and ML. A friend of mine with some code sample to train some classes for custom objects using FASTER_RCNN_RESNET_101. Because I had no GPU and the training was taking quite some time on…
Viorel Mirea
  • 371
  • 3
  • 6
1
vote
1 answer

Detecting object borders PRECISELY

I need to detect object (coin) in a photo, which is to draw a rectangle around it. I tried Mark-RCNN, Retina, Yolo, SSD - same result. The rectangles are not perfect. If you look at examples available online, you will see exactly what I mean: look…
Steve Brown
  • 369
  • 1
  • 3
  • 12
1
vote
1 answer

The bounding box's position and size is incorrect, how to improve it's accuracy?

I'm using detectron2 for solving a segmentation task, I'm trying to classify an object into 4 classes, so I have used COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml. I have applied 4 kind of augmentation transforms and after training I get…
JammingThebBits
  • 732
  • 11
  • 31
1
vote
1 answer

Output of Faster RCNN

is it possible to get 3 bounding box of a single class in Faster RCNN? In my work, I want to get 3 top suggestion from Faster RCNN. e.g. Suppose my model is looking for apples in a tree. So there could be so many apples in a tree but I want to get…
Red
  • 299
  • 1
  • 4
  • 16
1
vote
0 answers

Faster RCNN-RPN Network Training

I am trying to understand RPN network in Faster RCNN. I understand the concept of RPN network, Pass the input images to the pre trained CNN, and get the output as feature maps Make fixed size of the feature maps Extract anchors (3 different scales…
abdlp Komp
  • 11
  • 1
1
vote
0 answers

How to use MASK-RCNN?

I have a set of 2D images of lattice structures, which consists of normal images, and images with a broken lattice structure (a crack somewhere). I am starting a project to predict the images and label the cracks through instance segmentation. My…
Ong Shi Quan
  • 29
  • 7
1
vote
1 answer

my own implementation of FastRCNN cannot perform well on balanced data

2020.06.09 There are 700 images for training, each of them extract 64 rois and make a mini-batch, when batch-size is set to 2, it cast 350 steps to complete training, but for RCNN, each target is extracted as a single image resized to 224*224, there…
Scrooge Lin
  • 13
  • 3
1
vote
1 answer

Number of instances in training images MaskRCNN

I want to train a MaskRCNN model using the Object detection API Tensorflow. I'm currently annotating the images using the Pixel Annotation Tool. My question is: Should I create a training data set with ONE segmented feature per image, or can I…
pedro_galher
  • 334
  • 8
  • 18
1
vote
0 answers

prediction array is empty Mask RCNN

I am working on Mask RCNN and my prediction array is empty. I think it has to do with memory. This is what my code where I call for the predictions: model.eval() with torch.no_grad(): prediction = model([img.to(device)], [target]) When I am in…
E.W
  • 11
  • 2
1
vote
1 answer

How to generate background class in faster RCNN?

I have a medical image set and I am trying to train my network using faster rCNN. The idea is to detect tumors in image. My example image containing a tumor like below.. I have extracted all the tumor location coordinates and it is ready to be…
Mass17
  • 1,555
  • 2
  • 14
  • 29
1
vote
0 answers

Faster RCNN transfer learning Keras

I have implemented with my own custom dataset a faster RCNN in Keras following this very useful guide: https://medium.com/analytics-vidhya/a-practical-implementation-of-the-faster-r-cnn-algorithm-for-object-detection-part-2-with-cac45dada619 I would…
user3043636
  • 559
  • 6
  • 23
1
vote
0 answers

Classifying regions of a signal trace

I have a stack of signals that I'd like to perform an ML algorithm to chop them up into regions determined by their characteristics. The full signal looks a bit like this: And a fragment of it looks like this: In particular, I'd like to highlight…
JetSetJim
  • 68
  • 12
1
vote
0 answers

mxnet-gluon on colab: cudaMalloc retry failed: out of memory

I'm trying to train a faster RCNN on google-colab using mxnet gluon and VOC dataset. After training the net, when I try to analyze a new image to test it, I get the error below. This problem comes over regardless the number of epochs, the limit of…
JPabloFuenzalida
  • 81
  • 1
  • 10
1
vote
0 answers

TensorFlow Kitti-trained models: Detailed underlying training procedure

for my ML project I want to use the faster_rcnn_resnet101_kitti model from tensorflow model zoo. As the number of images in the Kitti dataset is extremely small (about 7000 images) for a deep learning practice, I was wondering how this small amount…
Ali Malek
  • 11
  • 1
1
vote
0 answers

Extract detected objects from a video/image

I have run Faster RCNN example and detect multiple objects. I want to extract these detected objects from image. Can anyone please let me know how can I do this? Below is the code. MODEL_NAME = 'inference_graph' IMAGE_NAME = 'abc.jpg' # Grab path…
Sohail
  • 21
  • 3
1 2 3
…
22 23