Skip to content

fix required instance_column and image_column cast #10175

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 6 commits into
base: main
Choose a base branch
from
Open

fix required instance_column and image_column cast #10175

Changes from 2 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
2c1cbb3
fix required instance_column and image_column cast
davidberenstein1957 Dec 10, 2024
c9fedf1
Apply suggestions from code review
davidberenstein1957 Dec 10, 2024
ab6961e
Update examples/dreambooth/train_dreambooth_lora_flux.py
davidberenstein1957 Dec 10, 2024
4a7e3f9
Merge branch 'main' into main
sayakpaul Dec 11, 2024
b9e1ccf
Update examples/dreambooth/train_dreambooth_lora_flux.py
davidberenstein1957 Dec 11, 2024
cd6bea5
Merge branch 'main' into main
linoytsaban Dec 11, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions examples/dreambooth/train_dreambooth_lora_flux.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -308,7 +308,7 @@ def parse_args(input_args=None):
"--instance_prompt",
type=str,
default=None,
required=True,
required=False,
help="The prompt with identifier specifying the instance, e.g. 'photo of a TOK dog', 'in the style of TOK'",
)
parser.add_argument(
Expand Down Expand Up @@ -714,7 +714,7 @@ def __init__(
# we load the training data using load_dataset
if args.dataset_name is not None:
try:
from datasets import load_dataset
from datasets import load_dataset, Image
except ImportError:
raise ImportError(
"You are trying to load your data using the datasets library. If you wish to train using custom "
Expand Down Expand Up @@ -742,6 +742,7 @@ def __init__(
raise ValueError(
f"`--image_column` value '{args.image_column}' not found in dataset columns. Dataset columns are: {', '.join(column_names)}"
)
dataset["train"] = dataset["train"].cast_column(image_column, Image(decode=True))
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why is this needed?

Copy link
Contributor Author

@davidberenstein1957 davidberenstein1957 Dec 11, 2024 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@sayakpaul fix to force casting and image column to decode to ensure this is done for feature sets where decoding automatically is not the default

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Okay let's have that as a comment too. Thanks for explaining!

instance_images = dataset["train"][image_column]

if args.caption_column is None:
Expand All @@ -768,7 +769,6 @@ def __init__(

instance_images = [Image.open(path) for path in list(Path(instance_data_root).iterdir())]
self.custom_instance_prompts = None

self.instance_images = []
for img in instance_images:
self.instance_images.extend(itertools.repeat(img, repeats))
Expand Down
Loading