Data Science

Questions tagged [faster-rcnn]

Ask Question

The tag has no usage guidance.

43 questions
Newest
Active
Bountied
Unanswered
Filter by
Sorted by
Tagged with
0
votes
0answers
21 views

why does my model take 30 mins per epoch when on my GPU? [on hold]

I am training a model with around 200 images and it usually takes around 12 hours or more to complete. My colleagues' work only takes about a hour and a half to train. I am using windows 10 and ...
0
votes
0answers
5 views

What are different algorithms/methods of selecting triplet's for training a face recognition network?

I want to construct a siamese network using a triplet loss function. For which we need to select training samples( triplets ) for training the network, So how do we select hard triplet's for training ...
0
votes
0answers
7 views

MASK RCNN with multicalss classification

I want to create a model which solve a multiclass classification problem. The main concept is: every picture contain only one object the background is very simple all object is coming from the same ...
1
vote
0answers
31 views

How does a Faster R-CNN gets trained and how does the Region Proposal Network fits into that?

so a Faster R-CNN consists of 3 parts: -the Base CNN -the Region Proposal Network with RoIpooling -and the classification CNN at the end So I asked myself if all these three Networks are trained ...
0
votes
0answers
10 views

I have a question about the structure of Faster R-CNNs

So hi, I need some help to understand the whole structure of the Faster R-CNNs. Further i will list the steps of the structur with questions between them: Image -> CNN -> (is the output ONE or ...
0
votes
0answers
26 views

What image format are acceptable in the faster RCNN or YoLo model?

I want to scrape various images from the blogs, website and feed it to the Faster Region CNN or YoLo model. Is there any specific format of the image which are accepted in the model ? Some of the ...
0
votes
0answers
23 views

Can Faster CNN/YoLo be used for object as well as feature extraction from an Image?

I have an image and I want to find the objects present in the image using Deep learning, there can be many objects in an image. Once I find the object, I want to find the features of each object and ...
0
votes
0answers
12 views

How should i prepare my dataset for efficient object detection and multi class classification?

I am currently using faster RCNN inception v2 model for detection and classification of object of 2 different type which are very closely identical (eg. rip apple and partially stall apple). how ...
0
votes
0answers
15 views

Hardware recommendation for FRCNN deep fashion data

I am working a research project to build a FRCNN model for attributes detection using deepfashion data(300K images with 1k attributes). I am struggled on hardware issue with my current training box ...
0
votes
0answers
117 views

Pre trained dataset for Car damage detection

I'm making a Car Damage Detection model which would have 2 classes to detect upon. My dataset has a total of 300 images (out of which I'd be using some for testing), which are totally insufficient to ...
2
votes
1answer
22 views

How does R-CNN and AlexNet compare?

I know AlexNet does object classification in images [categories] and R-CNN does object localization [category and bounding box]. How does R-CNN and AlexNet compare? Are they used for the same purpose ...
1
vote
1answer
17 views

Saving images in a non-retraceable way, but still able to train R-CNN's on them

For a computer vision project I am working with images that the company only allows me to have on my computer for a maximum of 24 hours due to regulations. Every day a few hundred images come in via ...
0
votes
1answer
48 views

Object detection model using images which have single instance of class per image-can it detect multiple instances in a single image?

I tried to train Faster R-CNN to detect multiple instances of a single class (eg. pomegranate on a pomegranate tree) but the training data consisted of 200 images where each image had only one object ...
0
votes
1answer
18 views

Extract segment from document scan

I need to extract some "valuable" information from document scan. For example, document's number, incoming date, organizations, persons, etc. Example document: I'm trying to extract highlighted ...
1
vote
1answer
80 views

Is Faster RCNN the same thing as VGG-16, RESNET-50, etc… or not?

My understanding is that Faster RCNN is an architecture for performing object detection. It finds objects in an image and classifies them. My understanding is also that VGG-16, RESNET-50, etc... also ...
0
votes
0answers
67 views

Optimal Size of base anchor size in Faster RCNN

Suppose that we have image size of $224x224$ and our feature map is size $7x7x512$. Now, we have to draw anchor boxes over input images. What is the initial size of that anchor box? $3x3$? We have $...
0
votes
0answers
23 views

What is the initial size of anchor in Faster R-CNN?

So we generate anchors for input images which will be later used for classification and then regression for bounding box. If we have image size of 224*224*3 and our feature map is of size 7*7*512. ...
0
votes
0answers
17 views

Object Detection using Faster R-CNN conundrum

So we have our image right? We use some pre-trained model like VGG or Inception which will predict the feature_map. Suppose to a shape of (7,7,512) from the original of (224,224,3). We use this ...
0
votes
0answers
19 views

Can anyone please guide me how to find the accuracy, presion and recall of a tensorflow objectdetection api trained model

I have trained a tensorflow object detection api model named faster-RCNN, but I am not able to find its accuracy, precision and recall on test dataset. Kindly guide me on how to find them. I have ...
1
vote
1answer
111 views

Tensorflow F-RCNN first stage input and output strides

Trying to optimize performances on Tensorflow's faster_rcnn_resnet50 (from the model zoo), I'm currently working on understanding the full .config file they provide, and I'm having a hard time with ...
1
vote
0answers
52 views

matterport mask-r-cnn transfer learning on own dataset using VGG annotator ver.1

The code I used was taken from shapes.py, balloon.py, inspect_balloon_data.ipynb but mostly ...
5
votes
2answers
108 views

Feeding 3 consecutive video frames to a CNN to track a tennis ball

I want to use CNN transfer learning to track a tennis ball from TV broadcasts of tennis matches. I used VGG annotating tool annotation tool link (use version 1 of the tool for compatibility with ...
0
votes
0answers
13 views

number of images vs num of annotations per image

I am training a fasterRCNN with ResNet-50 as backbone feature extractor, for 2 classes(OBJECT OF INTEREST & background). Below is the information about my data: Big and medium sized objects of ...
1
vote
0answers
45 views

Understanding Faster R-CNN

I'm having some trouble understanding the way the Faster R-CNN algorithm works. Specifically, the way the authors describe the concept of anchors. In their paper from here they describe anchors in ...
0
votes
0answers
65 views

Bead detection in a necklace using TensorFlow Object detection

I want to detect and show the count of beads in a necklace. For this purpose, I am using a TensorFlow object detection API. I have the images dataset similar to this image, I want to know what kind ...
0
votes
0answers
19 views

How is R-FCN faster than FRCNN?

During my first pass through the architecture for R-FCN, I believed that it was because their region proposal network generated regions of interest without performing the "small network slide" over ...
0
votes
0answers
53 views

How to set 2 GPU in Mask RCNN? TypeError: __init__() missing 2 required positional arguments: 'inputs' and 'outputs'

I found this: 'https://github.com/matterport/Mask_RCNN/issues/511' pip install keras==2.1.3 - done. change code in parallel_model - done. ...
1
vote
0answers
290 views

Bounding box regression in R-CNN

In R-CNN paper, they give the definition of the target values for bounding box regression Given that $(P, G)$ is a (prediction box, ground-truth box) pair of the form $(x, y, w, h)$ where $x, y$ is ...
0
votes
1answer
35 views

Building Image Dataset In a Studio

I'm currently working in a problem of Object Detection, more specifically we want to count and differentiate similar species of moths. We are already testing some ...
1
vote
1answer
54 views

Can I load my own weights?

full code source: https://www.kaggle.com/hmendonca/mask-rcnn-and-coco-transfer-learning-lb-0-155 ...
2
votes
1answer
71 views

what is the best approach to detect small objects with similar shape?

I'm working a model which detect different products in supermarket shelf. In the training data, there are a lot of objects with similar shape placed very close to or stacked to each others.(eg: milks ...
1
vote
0answers
66 views

Mask RCNN detecting object but mask is inaccurate

I am trying to detect the inner region of a object. Currently I am using the mask rcnn implementation provided by tensorflow in the models zoo. The object is similar to a hula hoop that is square in ...
0
votes
0answers
191 views

How to project a bounding box on feature map?

I'm trying to implement a custom ROI pooling layer in Keras. According to the Fast-RCNN publication, ROI pooling is done this way: RoI max pooling works by dividing the $h \times w$ RoI window into ...
0
votes
1answer
136 views

Mask RCNN: Random predictions during inference for the same image

I recently trained the Mask RCNN (matterport's implementation) on some satellite images, but during inference mode, I'm getting random predictions for the same set of weights for the same image. That ...
0
votes
0answers
79 views

How is Stochastic Gradient Descent done in Faster RCNN?

In Tenosrflow Object Detection API, you can choose different pretrained models such as Faster RCNN, SSD. Then you can specify the batch size during training. I know that for Stochastic Gradient ...
1
vote
0answers
100 views

with tf.device(DEVICE): model = modellib.MaskRCNN(mode = “inference”, model_dir = LOGS_DIR, config = config) [closed]

ValueError Traceback (most recent call last) /miniconda/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py in _apply_op_helper(self, op_type_name, name, **keywords) 509 as_ref=...
3
votes
1answer
96 views

Get bounding boxes for adjacent instances of a single class in image

I have a dataset with thousands of music score pages and manually annotated bounding boxes for the individual bars: My objective is now to train a DNN that should ultimately be able to get these ...
1
vote
0answers
59 views

Query about Landmark pooling layer in Fashionnet paper

I have gone through Deepfashion paper.I have query regarding Landmark pooling layer. 1) Image has 4,6 or 8 landmark points depending on cloth type. So how do you decide size of last FC layer in ...
1
vote
1answer
56 views

Faster R-CNN wrapper for the number of RPNs in the layer dimensions?

When I intialize Faster R-CNN in the deployment phase, the number of samples per image (parameter from config file: TEST.RPN_POST_NMS_TOP_N) is set to 300, that's the number of predicted bounding ...
6
votes
2answers
6k views

How does the bounding box regressor work in Fast R-CNN?

In the fast R-CNN paper (https://arxiv.org/abs/1504.08083) by Ross Girshick, the bounding box parameters are continuous variables. These values are predicted using regression method. Unlike other ...
1
vote
0answers
208 views

Backpropagation in Faster R-CNN

I understand how the convolution layers are applied after selective search finds the regions of interest in vanilla R-CNN and so the back-propagation or any weight updating is done in the individual ...
1
vote
0answers
1k views

How to perform Instance Segmentation using Tensorflow?

I used Tensorflow Object Detection API for a custom dataset based on the instructions at this help document.As required , collected the dataset,annotated it in PASCAL VOC XML format,split into ...
3
votes
3answers
2k views

Faster-RCNN how anchor work with slider in RPN layer?

I am trying to understand the whole Faster-RCNN, From https://www.quora.com/How-does-the-region-proposal-network-RPN-in-Faster-R-CNN-work Then a sliding window is run spatially on these feature ...