infer_hf_instance_seg

This algorithm proposes inference for instance segmentation using transformers models from Hugging Face.

🚀 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
from ikomia.utils.displayIO import display

# Init your workflow
wf = Workflow()

# Add algorithm
algo = wf.add_task(name="infer_hf_instance_seg", auto_connect=True)

# Run on your image  
wf.run_on(url="https://raw.githubusercontent.com/Ikomia-dev/notebooks/main/examples/img/img_LR.jpg")

# Inpect your result
display(algo.get_image_with_mask_and_graphics())

☀️ 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

• model_name (str) - default "facebook/maskformer-swin-base-coco": Name of the model. More models 'facebook/maskeformer' available on HF.
• conf_thres (float) - default '0.5': The probability score threshold to keep predicted instance masks.
• conf_mask_thres (float) - default '0.5': T Threshold to use when turning the predicted masks into binary values.
• conf_overlap_mask_area_thres (float) - default '0.8': The overlap mask area threshold to merge or discard small disconnected parts within each binary instance mask.
• cuda (bool): If True, CUDA-based inference (GPU). If False, run on CPU

Parameters should be in strings format when added to the dictionary.

from ikomia.dataprocess.workflow import Workflow
from ikomia.utils.displayIO import display

# Init your workflow
wf = Workflow()

# Add algorithm
algo = wf.add_task(name="infer_hf_instance_seg", auto_connect=True)

algo.set_parameters({
    'model_name': 'facebook/maskformer-swin-base-coco',
    'conf_thres': '0.5',
    "conf_mask_thres": "0.5",
    "conf_overlap_mask_area_thres": "0.8",
    'cuda': 'True',
})

# Run on your image  
wf.run_on(url="https://raw.githubusercontent.com/Ikomia-dev/notebooks/main/examples/img/img_LR.jpg")

# Inpect your result
display(algo.get_image_with_mask_and_graphics())

🔍 Explore algorithm outputs

Every algorithm produces specific outputs, yet they can be explored them the same way using the Ikomia API. For a more in-depth understanding of managing algorithm outputs, please refer to the documentation.

import ikomia
from ikomia.dataprocess.workflow import Workflow

# Init your workflow
wf = Workflow()

# Add algorithm
algo = wf.add_task(name="infer_hf_instance_seg", auto_connect=True)

# Run on your image  
wf.run_on(url="https://raw.githubusercontent.com/Ikomia-dev/notebooks/main/examples/img/img_LR.jpg")

# Iterate over outputs
for output in algo.get_outputs():
    # Print information
    print(output)
    # Export it to JSON
    output.to_json()