infer_detectron2_instance_segmentation

Run Detectron2 instance segmentation models. It can detect and segment objects in image.

🚀 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

[Change the sample image URL to fit algorithm purpose]

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_detectron2_instance_segmentation", auto_connect=True)

# Run on your image
wf.run_on(url="https://cdn.nba.com/teams/legacy/www.nba.com/bulls/sites/bulls/files/jordan_vs_indiana.jpg")

# Display the results
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 "COCO-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_3x": Name of the pretrained model. Should be one of:
  • COCO-InstanceSegmentation/mask_rcnn_R_101_DC5_3x
  • COCO-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_3x
  • COCO-InstanceSegmentation/mask_rcnn_R_101_C4_3x
  • COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x
  • COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x
  • COCO-InstanceSegmentation/mask_rcnn_R_101_FPN_3x
  • COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x
  • COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_3x
  • COCO-InstanceSegmentation/mask_rcnn_R_50_C4_3x
  • COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_1x
  • LVISv0.5-InstanceSegmentation/mask_rcnn_R_101_FPN_1x
  • LVISv0.5-InstanceSegmentation/mask_rcnn_R_50_FPN_1x
  • LVISv0.5-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_1x
  • Cityscapes/mask_rcnn_R_50_FPN
• conf_thres (float) - Default 0.5: Box threshold for the prediction [0,1].
• cuda (bool) - Default True: If True, CUDA-based inference (GPU). If False, run on CPU.
• config_file (str): Path to the .yaml config file. Overwrite model_name if both are provided.
• model_weight_file (str): Path to the .pth weight file. Overwrite model_name if both are provided.

Note: parameter key and value should be in string 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_detectron2_instance_segmentation", auto_connect=True)

# Set parameters
algo.set_parameters({
    "model_name": "COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x",
})

# Run on your image
wf.run_on(url="https://cdn.nba.com/teams/legacy/www.nba.com/bulls/sites/bulls/files/jordan_vs_indiana.jpg")

# Display the results
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_detectron2_instance_segmentation", auto_connect=True)

# Run on your image  
wf.run_on(url="example_image.png")

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