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
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Close
Hashes for irisml_tasks_timm-0.0.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | d8fcbf15a5be49c55d66ab3eb0df4b49865df24231459bf69cd8c6304c459a17 |
|
MD5 | 087399fa41efc18a550c51689d0f9c9b |
|
BLAKE2b-256 | 3a7e3696e9b15f7e6090601701ee2a5a4a25cf12d9d8db1461696a29c5982588 |