flowvision 0.0.21

oneflow vision codebase

vision

Datasets, Transforms and Models specific to Computer Vision

Installation

• install oneflow0.5.0+cu102 and other requirements

python3 -m pip install -f https://release.oneflow.info oneflow==0.5.0+cu102
pip install rich

• install latest version of flowvision

pip install flowvision==0.0.2

Usage

Quick Start

• list supported model

from flowvision import ModelCreator
ModelCreator.model_table()

• search supported model by wildcard

from flowvision import ModelCreator
ModelCreator.model_table("*vit*", pretrained=True)
ModelCreator.model_table("*vit*", pretrained=False)
ModelCreator.model_table('alexnet')

• create model use ModelCreator

from flowvision import ModelCreator
model = ModelCreator.create_model('alexnet', pretrained=True)

ModelCreator

• Create model in a simple way

from flowvision.models import ModelCreator
model = ModelCreator.create_model('alexnet', pretrained=True)

the pretrained weight will be saved to ./checkpoints

• Supported model table

from flowvision.models import ModelCreator
ModelCreator.model_table()

           Models            
┏━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Name         ┃ Pretrained ┃
┡━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ alexnet      │ true       │
│ vit_b_16_224 │ false      │
│ vit_b_16_384 │ true       │
│ vit_b_32_224 │ false      │
│ vit_b_32_384 │ true       │
│ vit_l_16_384 │ true       │
│ vit_l_32_384 │ true       │
└──────────────┴────────────┘

show all of the supported model in the table manner

• List models with pretrained weights

from flowvision.models import ModelCreator
ModelCreator.model_table(pretrained=True)

           Models            
┏━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Name         ┃ Pretrained ┃
┡━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ alexnet      │ true       │
│ vit_b_16_384 │ true       │
│ vit_b_32_384 │ true       │
│ vit_l_16_384 │ true       │
│ vit_l_32_384 │ true       │
└──────────────┴────────────┘

• Search for model by Wildcard

from flowvision.models import ModelCreator
ModelCreator.model_table('vit*')

           Models            
┏━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Name         ┃ Pretrained ┃
┡━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ vit_b_16_224 │ false      │
│ vit_b_16_384 │ true       │
│ vit_b_32_224 │ false      │
│ vit_b_32_384 │ true       │
│ vit_l_16_384 │ true       │
│ vit_l_32_384 │ true       │
└──────────────┴────────────┘

• Search for model with pretrained weights by Wildcard

from flowvision.models import ModelCreator
ModelCreator.model_table('vit*', pretrained=True)

           Models            
┏━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Name         ┃ Pretrained ┃
┡━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ vit_b_16_384 │ true       │
│ vit_b_32_384 │ true       │
│ vit_l_16_384 │ true       │
│ vit_l_32_384 │ true       │
└──────────────┴────────────┘

Model Zoo

We did all our tests under the same setting, please check the model page here for more details.