Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://diffengine.readthedocs.io/en/latest/user_guides/dataset_prepare.html below:

Website Navigation

• diffengine

Prepare Dataset — diffengine 1.0.0 documentation

1. Prepare metadata.csv and images.

The folder structure is

data/example
├── color.jpg
├── ...
└── metadata.csv

Example of metadata.csv.

file_name,text
color.jpg,"a dog"

1. Fix dataset config.

train_dataloader = dict(
    ...
    dataset=dict(
        ...
        dataset="data/example",
        image_column="file_name",
        csv="metadata.csv",
        ...
        )
    ...
)

1. Run training.

1. Prepare images.

The folder structure is

data/example
├── dog1.jpg
├── ...
└── dog5.jpg

1. Fix dataset config.

train_dataloader = dict(
    ...
    dataset=dict(
        ...
        dataset="data/example",
        )
    ...
)

1. Run training.

1. Prepare metadata.csv and images.

The folder structure is

data/example
├── images
|   └──  color.jpg
├── condition_images
|   └──  color_keypoint.jpg
└── metadata.csv

Example of metadata.csv.

file_name,conditioning_image,text
images/color.jpg,condition_images/color_keypoint.jpg,"a dog"

1. Fix dataset config.

train_dataloader = dict(
    ...
    dataset=dict(
        ...
        dataset="data/example",
        image_column="file_name",
        condition_column="conditioning_image",
        caption_column="text",
        csv="metadata.csv",
        ...
        )
    ...
)

1. Run training.

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4