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
0 answers

keras - per-pixel, unnormalized, softmax loss for semantic segmentation

I'm troubleshooting a Keras/TensorFlow U-Net for semantic segmentation. One thing I keep coming across are claims like this.... "Now the problem is using the softmax in your case as Keras don't support softmax on each pixel." which is stated…
kmh
  • 1,516
  • 17
  • 33
3
votes
1 answer

Upsampling in Semantic Segmentation

I am trying to implement a paper on Semantic Segmentation and I am confused about how to Upsample the prediction map produced by my segmentation network to match the input image size. For example, I am using a variant of Resnet101 as the…
ethelion
  • 105
  • 6
3
votes
1 answer

Why could u-net mask image with smaller mask?

The input image size of u-net is 572*572, but the output mask size is 388*388. How could the image get masked with a smaller mask?
Ink
  • 845
  • 1
  • 13
  • 31
2
votes
1 answer

Training custom dataset on mmsegmentation

I am trying to do semantic segmentation on Freiburg Forest dataset using mmsegmentation repo on github. The link to the same is attached below. https://github.com/open-mmlab/mmsegmentation I have made config file for the Freiburg Forest dataset and…
programmer_04_03
  • 137
  • 8
2
votes
0 answers

Anomaly Detection in Farmland Images

Farmland Image w/ anomaly: In the picture above, the blue outline outlines the anomalous part of the farmland, where the plants are much more dense also known as "Double Planting". I'm looking for ideas, approaches, or algorithms I can try, to see…
crrystalz
  • 21
  • 2
2
votes
1 answer

How to use custom image sizes to train the segmentation models in Keras?

I am using the Qubvel segmentation models https://github.com/qubvel/segmentation_models repository to train an Inception-V3-encoder based model for a binary segmentation task. I am using (256 width x 256 height) images to train the models and they…
shiva
  • 1,177
  • 2
  • 14
  • 31
2
votes
1 answer

In need of a Labelencoder code to fix the InvalidArgumentError: Graph execution error when Using deeplabv3+ for a 4 class semantic segmentation

Am running a 4 class semantic segmentation problem using Deeplabv3+ and I get the graph execution error as soon as the training starts. I have identified the problem after searching the web for solutions. The problem is with the labels. My labels…
Enigma
  • 23
  • 4
2
votes
2 answers

PointCloud to image fed to UNet: How to map predicted image back to 3D PointCloud?

I have a .las file and I performed the following operations: Convert PointCloud to RGB Image Convert PointCloud to GroundTruth Matrix. Crop Images and corresponding GroundTruth Matrix to fixed size 256x256 Train UNet (image and groundtuth…
h612
  • 544
  • 2
  • 11
2
votes
1 answer

What should the input to DeepLabV3 be in training mode?

I am trying to train a deeplabv3_resnet50 model on a custom dataset, but get the error ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 256, 1, 1]) when trying to do the forward pass. The following…
user3221037
  • 77
  • 5
2
votes
1 answer

How to deal with images and masks using tf.dataset in a semantic segmentation task?

My data does not fit into memory so I need to use the equavalent to flow_from_directory of the ImageDataGenerator class, but that supports tensorflow_datasets. I found image_dataset_from_directory, a utility function of keras that generates a…
Ahmed
  • 111
  • 5
2
votes
2 answers

Tensorflow_io: ValueError: Cannot infer argument `num` from shape (None, None, None)

I am trying to read and decode tiff images in tensorflow. I am using tensrflow_io package as follows, I am getting this error that I cant figure out. import tensorflow as tf import tensorflow_io as tfio import os def process_image(image): image…
Gopal Bhattrai
  • 83
  • 6
2
votes
0 answers

Tensorflow 2.8 Image Segmentation with Custom Dataset

I am following this tutorial for image segmentation using Tensorflow 2.8. I have a dataset of images and their annotations which I want to use for semantic segmentation. How can I use this model with a custom dataset? They are using a sample dataset…
S_S
  • 1,276
  • 4
  • 24
  • 47
2
votes
1 answer

Keras loss is NaN when training for semantic segmentation

I am using the headsegmentation dataset. A single mask looks like this All mask images are a single channel. This is my code: image_size = 512 batch = 4 labels = 14 data_directory = "/content/headsegmentation_final/" sample_train_images =…
Onur-Andros Ozbek
  • 2,998
  • 2
  • 29
  • 78
2
votes
1 answer

Semantic segmentation with detectron2

I used Detectron2 to train a custom model with Instance Segmentation and worked well. There are several Tutorials on google colab with Detectron2 using Instance Segmentation, but nothing about Semantic Segmentation. So, to train the Custom Instance…
Curious G.
  • 838
  • 8
  • 23
2
votes
0 answers

plot confusion matrix for semantic segmentation ResNet model in fastai

I am using fatai v2 for classifying lands using satellite imageries, and I am struggling with plotting confusion matrix for my test dataset using fastai. This is the code I used: learn = unet_learner(dls,resnet34, metrics=accuracy,…
Shae
  • 21
  • 2
1 2 3
…
35 36