pip install ikomia
About
Training process for DeepLabv3+ model of Detectron2.
Train DeepLabV3+ model for semantic segmentation. Implementation from Detectron2 (Meta Research).
🚀 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.
2. Create your workflow
from ikomia.dataprocess.workflow import Workflow
# Init your workflow
wf = Workflow()
# Add data loader
coco = wf.add_task(name="dataset_coco")
coco.set_parameters({
"json_file": "path/to/json/annotation/file",
"image_folder": "path/to/image/folder",
"task": "semantic_segmentation",
})
# Add train algorithm
train = wf.add_task(name="train_detectron2_deeplabv3plus", auto_connect=True)
# Launch your training on your data
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
- epochs (int) - default '1000': Number of complete passes through the training dataset.
- max_iter (int) - default '1000': Maximum number of iterations.
- classes (int) - default '2': Number of classes
- input_width (int) - default '800': Size width of the input image.
- input_height (int) - default '800': Size height of the input image.
- batch_size (int) - default '4': Number of samples processed before the model is updated.
- learning_rate (float) - default '0.02': Step size at which the model's parameters are updated during training.
- eval_period (int) - default '100: Interval between evaluations.
- dataset_split_ratio (float) – default '90': Divide the dataset into train and evaluation sets ]0, 100[.
- output_folder (str, optional): path to where the model will be saved.
- config_file (str, optional): path to the training config file .yaml.
- warmupFactor (float) - default '0.001':
- warmupIters (int) - default '200':
- polyLRFactor (float) - default '0.9':
- polyLRConstantFactor (float) - default '0.0':
- resnetDepth (int) - default '50':
- batchNorm (str) - default 'BN':
- early_stopping (bool) - default 'False':
- patience (int) - default '10':
- numGPU (int) - default '1':
Parameters should be in strings format when added to the dictionary.
from ikomia.dataprocess.workflow import Workflow
# Init your workflow
wf = Workflow()
# Add data loader
coco = wf.add_task(name="dataset_coco")
coco.set_parameters({
"json_file": "path/to/json/annotation/file",
"image_folder": "path/to/image/folder",
"task": "semantic_segmentation",
})
# Add train algorithm
train = wf.add_task(name="train_detectron2_deeplabv3plus", auto_connect=True)
train.set_parameters({
"batch_size": "4",
"epochs": "50",
"learning_rate": "0.02",
"dataset_split_ratio": "80",
"max_iter": "1000",
"classes": "2",
"warmupFactor": "0.001",
"warmupIters": "200",
"polyLRFactor": "0.9",
"batchNorm": "BN",
"early_stopping": "False"
})
# Launch your training on your data
wf.run()
Developer
Ikomia
License
Apache License 2.0
A permissive license whose main conditions require preservation of copyright and license notices. Contributors provide an express grant of patent rights. Licensed works, modifications, and larger works may be distributed under different terms and without source code.
Permissions | Conditions | Limitations |
---|---|---|
Commercial use | License and copyright notice | Trademark use |
Modification | State changes | Liability |
Distribution | Warranty | |
Patent use | ||
Private use |
This is not legal advice: this description is for informational purposes only and does not constitute the license itself. Provided by choosealicense.com.