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
3
votes
2 answers

Different results on Google colab than local

I am training a unet model. I started training with my pc, but it was too slow as it didn't run with GPU. Therefore I started using Google colab for faster training (using GPU). I have the same dataset saved locally and in Google Drive and I also…
IVR
  • 43
  • 1
  • 6
3
votes
3 answers

How UNET is different from simple autoencoders?

UNET architecture is like first half encoder and second half decoder . There are different variations of autoencoders like sparse , variational etc. They all compress and decompress the data But the UNET is also same used for compressing and…
Hamza
  • 530
  • 5
  • 27
3
votes
3 answers

Implementing Multiclass Dice Loss Function

I am doing multi class segmentation using UNet. My input to the model is HxWxC and my output is, outputs = layers.Conv2D(n_classes, (1, 1), activation='sigmoid')(decoder0) Using SparseCategoricalCrossentropy I can train the network fine. Now I…
Hamza Yerlikaya
  • 49,047
  • 44
  • 147
  • 241
3
votes
1 answer

CNN: Normal that the validation loss decreases much slower than training loss?

i'm training a CNN U-net model for semantic segmentation of images, however the training loss seems to decrease in a much faster rate than the validation loss, is this normal? I'm using a loss of 0.002 The training and validation loss can be seen in…
darvida
  • 51
  • 7
3
votes
2 answers

Transforming images and masks together (Keras example)

This code snippet has been taken from Keras API reference/Data Preprocessing. Section : Example of transforming images and masks together. link : https://keras.io/api/preprocessing/image/ # we create two instances with the same…
Walker
  • 33
  • 5
3
votes
1 answer

Multiclass semantic segmentation model evaluation

I am doing a project on multiclass semantic segmentation. I have formulated a model that outputs pretty descent segmented images by decreasing the loss value. However, I cannot evaluate the model performance in metrics, such as meanIoU or Dice…
James Black
  • 61
  • 2
  • 7
3
votes
0 answers

how to use ImageDataGenerator for semantic segmentation labels?

I'm performing semantic segmentation and I would like to use the ImageDataGenerator class to augment my data. On the keras docs I read about using a generator for the image as well as for the masks however, I was wondering how this would work? My…
AdishRao
  • 163
  • 1
  • 1
  • 12
3
votes
0 answers

What is Deep Supervision?

I am relatively new to deep learning and currently working in biomedical applications of deeply networking. I came across this term "Deep Supervision" in few papers like here UNet++: A Nested U-Net Architecture for Medical Image Segmentation I…
Soumil Kumar
  • 53
  • 4
3
votes
1 answer

What is the relationship between instance segmentation and semantic segmentation from the perspective of neural networks?

I am clear with the tasks of instance segmentation and semantic segmentation. However, from the perspective of the neural networks, what is the relationship between them? Namely, is it feasible to realize instance segmentation by improving or…
JJTT
  • 123
  • 1
  • 8
3
votes
1 answer

How to to drop a specific labeled pixels in semantic segmentation

I am new to semantic segmentation. I used the FCN to train my dataset. In the data set there are some pixels for the unknown class. I would like to exclude this class from my loss. So I defined a weight based on the class distribution of whole…
Arb
  • 91
  • 10
3
votes
1 answer

tensorflow deeplabv3+ class weights

I use the latest version of deeplab(v3+) to train my own dataset consisting of 6 classes. I am able to train my dataset but as my labels are strongly imbalanced I would like to weight each class with a class specific value. Here is how I realized…
Alexander Werthmann
  • 31
  • 4
3
votes
1 answer

How can I load a pre-trained model on COCO dateset for image segmentation?

I want to do semantic segmentation of objects in my video file. I prefer to use a pre-trained model on the COCO dataset (or COCO stuff dataset) and start using it for semantic segmentation and object detection on my own video files. Most of the…
Pradip Gupta
  • 539
  • 1
  • 9
  • 21
3
votes
2 answers

Read image in tensorflow with indexed color value for semantic segmentation task

I'm creating FCN for semantic segmentation. I'm having a difficult time with converting the labeled png image to indexed color value on PascalVOC dataset. I want the value to be range between 0 and 20. As I can achieve such operation with PIL in the…
Kousuke Kuzuoka
  • 125
  • 1
  • 10
3
votes
1 answer

encounter error during deeplab v3+ training on Cityscapes Semantic Segmentation Dataset

all, I start the training process using deeplab v3+ following this guide. However, after step 1480, I got the error: Error reported to Coordinator: Nan in summary histogram for: image_pooling/BatchNorm/moving_variance_2 The detailed train log is…
Milton Wong
  • 139
  • 2
  • 5
3
votes
1 answer

how to apply multi input image to Unet for segmentation?

I am a newbie in machine learning. Actually, I used my unet code for image segmentation using one input image slice (192x912) and one output mask image (192x192) My Unet code is contained several CNN layer and I usually used one input image…
Tom
  • 531
  • 4
  • 7
  • 19
1 2 3
…
35 36