Menu
Here's my folder structure
image-folders/
├── class_0/
| ├── 001.jpg
| ├── 002.jpg
└── class_1/
| ├── 001.jpg
| └── 002.jpg
└── class_2/
├── 001.jpg
└── 002.jpg
By using ImageFolder from torchvision, I can create dataset with this syntax :dataset = ImageFolder("image-folders",...)
But this will read the entire subfolder and create 3 target classes. I don't want to include the class_2 folder, I want my dataset to only contains class_0 and class_1 only, is there any way to achieve this besides delete/move the class_2 folder?
570
Let’s go over the PyTorch ImageFolder class in brief. It’s a fairly easy concept to grasp. module. We can easily access it using the following syntax: This class helps us to easily create PyTorch training and validation datasets without writing custom classes. Then we can use these datasets to create our iterable data loaders. class.
When it comes to loading image data with PyTorch, the ImageFolder class works very nicely, and if you are planning on collecting the image data yourself, I would suggest organizing the data so it can be easily accessed using the ImageFolder class. However, life isn’t always easy.
Show activity on this post. ImageFolder expects the data folder (the one that you pass as root) to contain subfolders representing the classes to which its images belong. Something like this:
The training and validation functions are going to be pretty simple. Let’s take a look. functions contain pretty standard code for what we generally write in PyTorch for image classification. In both cases, we are returning the loss and accuracy values after each epoch. The last thing we need to start the training is the training loop.
You can do this by using torch.utils.data.Subset of the original full ImageFolder dataset:
from torchvision.datasets import ImageFolder
from torch.utils.data import Subset
# construct the full dataset
dataset = ImageFolder("image-folders",...)
# select the indices of all other folders
idx = [i for i in range(len(dataset)) if dataset.imgs[i][1] != dataset.class_to_idx['class_s']]
# build the appropriate subset
subset = Subset(dataset, idx)
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With
