python (65.1k questions)

javascript (44.2k questions)

reactjs (22.7k questions)

java (20.8k questions)

c# (17.4k questions)

html (16.3k questions)

r (13.7k questions)

android (12.9k questions)

Questions - data-augmentation

How to use detectron2's augmentation with datasets loaded using register_coco_instances

I've trained a detectron2 model on custom data I labeled and exported in the coco format, but I now want to apply augmentation and train using the augmented data. How can I do that if I'm not using a ...
test-img

Ramon Griffo

python

pytorch

computer-vision

data-augmentation

detectron

Votes: 0

Answers: 1

Latest Answer

From my experience, how you register your datasets (i.e., tell Detectron2 how to obtain a dataset named "my_dataset") has no bearing on what dataloader to use during training (i.e., how to l...
test-img

zepman

Tensor error using DiffAugment for data augmentation in my own dataset . data efficient gans

I'm trying to create synthetic data from pics within a folder called Bathroom using this colab example => https://colab.research.google.com/gist/zsyzzsoft/5fbb71b9bf9a3217576bebae5de46fc2/data-eff...
test-img

albertovpd

python-3.x

tensorflow

generative-adversarial-network

data-augmentation

Votes: 0

Answers: 1

Latest Answer

I was trying to use this repo => https://github.com/mit-han-lab/data-efficient-gans At the end I got it running in Colab, with the pytorch version: Having installed torch v1.10 cuda 11.1 Creating ...
test-img

albertovpd

On the fly augmentation for segmentation

Hi I am trying to do 2D prostate segmentation using U-net. I want to apply data augmentation to both prostate and label images (X,y), for this I am currently using Torch.io which applies the same rand...
test-img

Beg

keras

pytorch

image-segmentation

data-augmentation

Votes: 0

Answers: 1

Latest Answer

You should look at libraries such as albuminations that extend the torchvision.transforms to work also on segmentation masks etc.
test-img

Shai

No val_loss and val_accuracy keys when I've already had validation_data in model.fit()'s argument

Here's the image augmentation code: batch_size = 16 train_datagen = ImageDataGenerator(rescale=1./255, validation_split=0.2) # test_datagen = ImageDataGenerator(rescale=1./255) # Use flow from data...
test-img

Teerapad Pipadboonyarat

python

tensorflow

keras

deep-learning

data-augmentation

Votes: 0

Answers: 1

Latest Answer

First: Make sure your model is running without your validation_generator. Second: Make sure your validation_generator really does have data by iterating through a few samples. Here is a working exampl...
test-img

AloneTogether

Posts

Questions

Blogs

Jobs