Skip to main content

IrisML tasks to use timm library

Project description

irisml-tasks-timm

Timm-related tasks for IrisML pipeline.

Please visit IrisML repository for the details.

Installation

pip install irisml-tasks-timm

Tasks

create_timm_model

Create a timm model. Please use timm.list_models() method to find available model names.

class Config:
    name: str
    num_classes: int
    pretrained: bool = False
    task_type: typing.Literal['multiclass_classification', 'multilabel_classification'] = 'multiclass_classification'

create_timm_transform

Create a timm transform. The task output contains train_transform and val_transform.

class Config:
    input_size: int
    crop_pct: float = 0.875  # Center crop the image with this ratio.
    interpolation: typing.Literal['bilinear', 'bicubic'] = 'bilinear'

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

irisml-tasks-timm-0.0.1.tar.gz (4.0 kB view hashes)

Uploaded Source

Built Distribution

irisml_tasks_timm-0.0.1-py3-none-any.whl (4.4 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page