dataset_wgisd

Load Wine Grape Instance Segmentation Dataset (WGISD) into Ikomia dataset format. Then, any compatible training algorithms from the Ikomia HUB can be connected to this converter.

In Ikomia Studio, once dataset is loaded, all images can be visualized with their respective annotations.

This dataset was created to provide images and annotations to study object detection, instance or semantic segmentation for image-based monitoring and field robotics in viticulture. It provides instances from five different grape varieties taken on field. These instances shows variance in grape pose, illumination and focus, including genetic and phenological variations such as shape, color and compactness.

🚀 Use with Ikomia API

1. Install Ikomia API

We strongly recommend using a virtual environment. If you're not sure where to start, we offer a tutorial here.

pip install ikomia

2. Create your workflow

from ikomia.dataprocess.workflow import Workflow

# Init your workflow
wf = Workflow()

# Add dataset loader:auto_connect is set to False because dataset algorithms don't have any input
dataset_loader = wf.add_task(name="dataset_wgisd", auto_connect=False)

dataset_loader.set_parameters({
    "dataset_folder": "wgisd/data/",
    "class_file": "wgisd/classes.txt",
    "seg_mask_mode": "None",
})

# Add object detection training algorithm (pick one from Ikomia HUB)
train_algo = wf.add_task(name="train_yolo_v7", auto_connect=True)

# Run the training workflow
wf.run()

☀️ Use with Ikomia Studio

Ikomia Studio offers a friendly UI with the same features as the API.

• If you haven't started using Ikomia Studio yet, download and install it from this page.

• For additional guidance on getting started with Ikomia Studio, check out this blog post.

📝 Set algorithm parameters

dataset_loader.set_parameters({
    "dataset_folder": "wgisd/data/",
    "class_file": "wgisd/classes.txt",
    "seg_mask_mode": "None",
})

• dataset_folder (str): path to the folder containing dataset images.
• class_file (str): path to the file where classes are listed.
• seg_mask_mode (str): type of training task
  • object detection: "seg_mask_mod": "None"
  • instance segmentation: "seg_mask_mod": "Instance"
  • semantic segmentation: any other value

Note: parameter key and value should be in string format when added to the dictionary.