Stack Overflow
Stack Overflow

Questions tagged [semantic-segmentation]

Semantic segmentation is the task of classifying every pixel in the image to a category or class label.

Semantic segmentation is the task of classifying every pixel in the image to a category. It refers to the process of linking each pixel in an image to a class label. Some of its primary applications are in autonomous vehicles, human-computer interaction & robotics.

532 questions
0
votes
1 answer

Semantic Image Segmentation with colored masks

So i have a set of pictures with their masks in color for example color blue is for chair, red for lamps, etc. As I am new to all of this i have tried doing doing this with the unet model, i have processed the images with keras and like this. def…
Jaime Cuellar
  • 464
  • 1
  • 5
  • 20
0
votes
1 answer

How to fix input shape error in keras model

I tried to perform semantic segmentation using this tutorial: https://github.com/nikhilroxtomar/UNet-Segmentation-in-Keras-TensorFlow/blob/master/unet-segmentation.ipynb I modified a bit his notebook but I successfully trained the model with a 50%…
tudor opran
  • 27
  • 1
  • 7
0
votes
3 answers

Why Reshape and Permute for segmentation with unet?

I am doing the image semantic segmentation job with unet. I am confused with the last layers for pixel classification. The Unet code is like this: ... reshape = Reshape((n_classes,self.img_rows * self.img_cols))(conv9) permute =…
tidy
  • 4,747
  • 9
  • 49
  • 89
0
votes
1 answer

Deployment of keras layer UpSampling2D to tensorRT

Kears/TensorFlow layer UpSampling2D() cannot be deployed to TensorRT (known behavior). I am trying to find a solution by replacing the layer UpSampling2D() by other Keras layer with parallel behaviour. Theoretically Conv2DTranspose() should do the…
YoavEtzioni
  • 85
  • 10
0
votes
1 answer

Semantic segmentation with amazon AWS and S3 instance

This is probably a easy question but I have been stuck now for a time. I want to train an FCN an Amazon AWS. For this I want to use the procedure used in this example (…
sminize
  • 11
  • 3
0
votes
1 answer

What is the meaning of the result of model.predict() function for semantic segmentation?

I use Segmentation Models library for multi-class (in my case 4 class) semantic segmentation. The model (UNet with 'resnet34' backbone) is trained with 3000 RGB (224x224x3) images. The accuracy is around 92.80%. 1) Why model.predict() function…
saki
  • 117
  • 3
  • 8
0
votes
1 answer

How to read the label(annotation) file from Synthia Dataset?

I am new to Synthia dataset. I would like to read the label file from this datset. I expect to have one channel matrix with size of my RGB image, but when I load the data I got 3x760x1280 and it is full of zeros. I tried to read as belows: label =…
Arb
  • 91
  • 10
0
votes
1 answer

'No Module named Tensorflow' error while running 'sh local_test.sh' command while running the deeplab code

I am trying to install Deeplab and run it on my machine. I am following this I am able to run the initial test 'python3 deeplab/model_test.py' but I am getting No module named Tensorflow error while running the next step, sh…
Sree
  • 973
  • 2
  • 14
  • 32
0
votes
1 answer

Multi-class semantic segmentation difficulty with RGB images

Could anyone help me with this problem of multi-class semantic segmentation. I have modified a code to accept RGB images and RGB labels as masks. I am using the following model…
rahulgomes19
  • 21
  • 4
0
votes
0 answers

keras image semantic segmentation giving repetitive output(SEGNET basic model)

I am trying to do semantic segmentation on satellite images using keras with tensorflow backend. I am using a SEGNET basic model for image segmentation. I am using python 3.6 My question is regarding repetitive patterns that I am getting in output…
Ankit Sharma
  • 65
  • 1
  • 11
0
votes
3 answers

Deeplab to TensorRT conversion

Converting Deeplab Tensorflow model to TensorRT model increases inference time dramatically, what am I doing wrong in my code? Here I am doing the conversion from Tensorflow graph to TensorRT graph and saving this new TRT model: OUTPUT_NAME =…
Pedram
  • 97
  • 3
  • 14
0
votes
1 answer

Annotation value 21 found in labels. This is greater than number of classes

from the item it seems to be a pretty obvious issue right? But for the life of me I swear I have 21 labels and 21 classes. So just as a sanity check I thought i'd ask! I have a load of training images (640,640) I've gone through them and used…
Jack
  • 2,891
  • 11
  • 48
  • 65
0
votes
1 answer

Metric for evaluating predicted bounding boxes from semantic segmentation on an object level outside of training

Context For simplicity let us pretend we are performing semantic segmentation on a series of one pixel high images of width w with three channels (r, g, b) with n label classes. In other words, a single image might look like: img = [ [r1, r2,…
SumNeuron
  • 4,850
  • 5
  • 39
  • 107
0
votes
1 answer

Combine two neural networks with different inputs through element-wise summation of certain layers

I am looking at combining two Convolutional Neural Networks into one through element-wise summation of activation functions. Both these networks have different inputs, but are similar in their architecture. I have seen from certain papers and github…
Isa El Doori
  • 19
  • 2
1 2 3
…
35 36