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
6
votes
3 answers

Runtime Error - element 0 of tensors does not require grad and does not have a grad_fn

I am using a Unet model for semantic segmentation - I have a custom dataset of images and their masks both in .png format. I have looked in the online forums and tried stuff, but not much works? Any suggestions in how to resolve the error or improve…
Namwa
  • 61
  • 1
  • 1
  • 2
6
votes
2 answers

How to resize image segmentation mask?

I have a binary mask for each image, with each mask pixel having value of either 0 or 255. Now because my image segmentation needs images of fixed size, I will have to resize the images and the masks. However, when I resize the image, then there…
Dang Manh Truong
  • 795
  • 2
  • 10
  • 35
6
votes
2 answers

How to get top k accuracy in semantic segmentation using PyTorch?

How do you compute the top k accuracy in semantic segmentation? In classification, we might compute the topk accuracy as: correct = output.eq(gt.view(1, -1).expand_as(output))
JJTT
  • 123
  • 1
  • 8
6
votes
2 answers

What is the best way to handle the background pixel classes (ignore_label), when training deep learning models for semantic segmentation?

I am trying to train a UNET model on the cityscapes dataset which has 20 'useful' semantic classes and a bunch of background classes that can be ignored (ex. sky, ego vehicle, mountains, street lights). To train the model to ignore these background…
Roshan Rane
  • 133
  • 2
  • 8
6
votes
2 answers

Too Much Memory Issue with Semantic Image Segmentation NN (DeepLabV3+)

I first explain my task: I have nearly 3000 images from two different ropes. They contain rope 1, rope 2 and the background. My Labels/Masks are images, where for example the pixel value 0 represents the background, 1 represents the first rope and 2…
Mob
  • 409
  • 1
  • 5
  • 14
6
votes
0 answers

Unable to load tflite deeplab segmentation model in android application. Error: ByteBuffer is not a valid flatbuffer model

Facing an issue in loading converted TFLite model into android application. Model: Deeplabv3 Mobilenetv2 (Trained on Pascal VOC) TFLite version: 1.10 Used tflite_convert for converting pb file into tflite. (Tensorflow version: 1.11.0) Code: private…
Sandi
  • 155
  • 9
6
votes
3 answers

Ground truth pixel labels in PASCAL VOC for semantic segmentation

I'm experimenting with FCN(Fully Convolutional Network), and trying to reproduce the results reported in the original paper (Long et al. CVPR'15). In that paper the authors reported results on PASCAL VOC dataset. After downloading and untarring the…
cccjjj
  • 91
  • 2
  • 6
5
votes
0 answers

Can't reduce loss in Semantic Segmentation(UNET) and Mean IOU isn't improving either

We are using greyscale eye images and ground truth of eye iris to train a CNN to segment the iris. Our dataset has about 2000 images with their corresponding masks, both are of size 224x224. We used a UNET architecture, as shown in the code below.…
Mohamad Omar
  • 51
  • 4
5
votes
3 answers

Multi-class weighted loss for semantic image segmentation in keras/tensorflow

Given batched RGB images as input, shape=(batch_size, width, height, 3) And a multiclass target represented as one-hot, shape=(batch_size, width, height, n_classes) And a model (Unet, DeepLab) with softmax activation in last layer. I'm looking for…
Mendi Barel
  • 3,350
  • 1
  • 23
  • 24
5
votes
2 answers

Keras `ImageDataGenerator` image and mask augments differently

I'm training a semantic segmentation model using Keras with TensorFlow backend. I adopted ImageDataGenerator to do the image augmentation, including rotation, flip and shift. By following the documentation, I created a dictionary maskgen_args and…
Frost-Lee
  • 420
  • 1
  • 5
  • 20
5
votes
5 answers

Importing COCO datasets to google colaboratory

The COCO dataset is very large for me to upload it to google colab. Is there any way I can directly download the dataset to google colab?
CleanPegasus
  • 53
  • 1
  • 1
  • 4
5
votes
1 answer

Why do all images resulting by DeepLabV3+ become black only?

I tried semantic segmentation with the DeepLab v3+ but I got results all black out. I deleted the original file and put original data in ImageSets/,JPEGImages/ and SegmentationClass/ corresponding to each. I prepared SegmentationClassRaw image…
y_ kani
  • 51
  • 2
5
votes
0 answers

My Image segmentation result map contains black lattice in in the white patch

I'm doing an image segmentation with UNet-like CNN architecture by Pytorch 0.4.0.It mark foreground as 1 and background as 0 in the final segmentation result.I use a pre-trained VGG's feature extractor as my encoder, so I need to upsampling the…
Kevin
  • 71
  • 5
5
votes
0 answers

How to improve miou for deeplabV3+ ?

Currently I’m struggling with improving the results on semantic segmentation problem using deeplabV3+ trained on my own dataset. I’ve trained deeplabV3+ successfully a few times using different pretrained models from the model zoo, all based on…
weehe91325
  • 51
  • 1
4
votes
1 answer

What is the fastest and easiest way to resample a set of CT scans to same pixel spacing and volume size?

I have to train a neural net for semantic segmentation of kidney and his tumor, starting from the dataset available from the kiTS 19 Challenge. In this dataset, I have 100 CT scans for the training set, with a great variety in terms of size and…
Saras
  • 41
  • 1
1
2
3
…
35 36