| license: apache-2.0 | |
| datasets: | |
| - pierreguillou/DocLayNet-small | |
| language: | |
| - en | |
| pipeline_tag: image-segmentation | |
| tags: | |
| - SAM Fine-tune | |
| I have Fine tuned https://huggingface.co/facebook/sam-vit-base using Doclaynet-small dataset. | |
| My focus was to detect structure from the documents like paragraph, header, tabel using SOTA model Segment Anything Model (SAM). | |