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
2
votes
0 answers

IOU Measure Implementation in Keras

i have implemented IOU like this: import numpy as np EPS = 1e-12 def get_iou( gt , pr , n_classes ): class_wise = np.zeros(n_classes) for cl in range(n_classes): intersection = np.sum(( gt == cl )*( pr == cl )) union =…
Clever
  • 107
  • 1
  • 11
2
votes
0 answers

Converting .xml image annotations to masks (.jpg or .png)

I'm using the LabelMe annotation tool, after annotating the labels are in .xml format. But my neural network takes annotations as .png. How to convert from .xml to .jpg or .png? The .xml file has information of bounding boxes of objects.
Komms
  • 93
  • 8
2
votes
1 answer

Keras: Pixelwise class imbalance in binary image segmentation

I have a task in which I input a 500x500x1 image and get out a 500x500x1 binary segmentation. When working, only a small fraction of the 500x500 should be triggered (small "targets"). I'm using a sigmoid activation at the output. Since such a…
Mastiff
  • 2,101
  • 2
  • 23
  • 38
2
votes
1 answer

Imbalanced data for semantic segmentation in Keras?

I am new with keras and have been learning it for about 3 weeks now. I apologies if my question sounds a bit stupid. I am currently doing semantic medical image segmentation of 512x512. I'm using UNet from this link https://github.com/zhixuhao/unet…
ErickYA
  • 31
  • 6
2
votes
2 answers

training loss decrease at first several epochs but jump to a high value suddenly

I am training a 3D Unet on a medical dataset. I am trying to overfit the model on small dataset which only has one instance. The loss decrease firstly, but suddenly jump up to a high value. I attached the loss curve below. I add batch normalization…
SiliangZ
  • 77
  • 6
2
votes
1 answer

How to handle the mean Intersection Over Union (mIOU) for unknown class in semantic segmentation?

I implemented a FCN network to do semantic segmentation. I am using Cityscapes as my dataset. As you know, there are some classes in Cityscapes that you ignore during the training and it is labeled as 255. I used weighted loss to ignore the loss for…
Arb
  • 91
  • 10
2
votes
1 answer

How should be a labelled image for semantic segmentation?

As I understand from the below explanation, there will be two types of images for semantic segmentation which are inputs and masks. Mask images are the images that contain a 'label' in pixel value which could be some integer (0 for ROAD, 1 for TREE…
saki
  • 117
  • 3
  • 8
2
votes
1 answer

How to use mscoco stuff dataset with "counts" in binary?

I would like to train my model on MSCOCO semantic segmentation (only stuff) by using the json file but the key "counts" contains binary characters. Did I miss something? I'm using MXNet and the dataloader is directly looking for the json files. Not…
dhassault
  • 91
  • 6
2
votes
2 answers

Tensorflow-lite - Getting bitmap from quantized model output

We are working on semantic segmentation application in android using tensorflow-lite.The '.tflite' deeplabv3 model used has input of type (ImageTensor) uint8[1,300,300,3] and ouput of type (SemanticPredictions) uint8[300,300].We were successfully…
anilsathyan7
  • 1,423
  • 17
  • 25
2
votes
1 answer

How to visualize a matrix of categories as an RGB image?

I am using neural network to do semantic segmentation(human parsing), something like taking a photo of people as input and the neural network tells that every pixel is most likely to be head, leg, background or some other parts of human. The…
Jerry Yang
  • 509
  • 4
  • 11
2
votes
1 answer

Check failed: top_shape[j] == bottom[i]->shape(j): for Concat layer in 3D data

I am trying to train 3D-Unet in caffe. The width, height and depth of different volumes is different. The input shape of the first volume in HDF5 dataset is 1 1 104 281 389 (NxCxDxHxW), when it reaches to the Concat layer (concat_d2c_u2a-b), it is…
sc241
  • 189
  • 17
2
votes
0 answers

Deep Learning U-net keras patch making from source image.(code python)

I have problem with preprocessing data set for deep learning. I am using U-net. I have training data, label data, test data size of 512x512. I want patch based learning so i am trying to change 512x512 slices to multiple 64x64 slices so that I can…
doyle
  • 101
  • 3
2
votes
1 answer

Tensorflow tf.metrics.mean_iou returns 0

I want to use the function tf.metrics.mean_iou for an FCN for semantic segmentation. It only works, if the confusion matrix is calculated before the IoU, otherwise it returns 0. Here my examples: This example returns the correct value…
golden96371
  • 350
  • 6
  • 19
2
votes
1 answer

Upsampling in Semantic Segmentation using dilated Convolution

I am working on a project for semantic segmentation using dilated (atrous) convolution network. I am using caffe framework. My input data and label sizes are: data (1 3 1158 1544 ) label (1 1 1158 1544) I am using softmax with loss for…
Kangkan Bharadwaj
  • 77
  • 1
  • 5
2
votes
2 answers

Multiclass semantic segmentation - output activation?

I am trying out multiclass semantic segmentation in Keras. Right now i'm using the Unet architecture, and have a model similar to this (but deeper): inputs = Input(shape=(512,512,3)) # 128 down1 = Conv2D(32, (3, 3), activation='relu',…
Kay Raymond Oskal
  • 21
  • 4
1 2 3
…
35 36