Instructions to use YufeiWeng/donut-base-beans with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use YufeiWeng/donut-base-beans with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="YufeiWeng/donut-base-beans") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("YufeiWeng/donut-base-beans") model = AutoModelForImageClassification.from_pretrained("YufeiWeng/donut-base-beans") - Notebooks
- Google Colab
- Kaggle
File size: 951 Bytes
d8b9019 | 1 | python run_image_classification_val_test.py --train_dir /trunk/shared/eebo_data/images_cropped/ --validation_dir /trunk/shared/eebo_data/images_cropped/ --output_dir ./test_microsoft_dit/ --remove_unused_columns False --label_column_name labels --do_train --do_eval --push_to_hub --push_to_hub_model_id donut-base-beans --learning_rate 3e-5 --num_train_epochs 5 --per_device_train_batch_size 32 --per_device_eval_batch_size 32 --logging_strategy steps --logging_steps 10 --eval_strategy epoch --save_strategy epoch --load_best_model_at_end True --save_total_limit 5 --seed 1337 --ignore_mismatched_sizes --image_column_name image_url --label_column_name label --model_name_or_path microsoft/dit-base-finetuned-rvlcdip --resume_from_checkpoint /trunk2/yufei/summer24/transformers/examples/pytorch/image-classification/test_microsoft_dit/checkpoint-9905 |