nielsr/funsd
Viewer • Updated • 199 • 3.61k • 18
How to use SimaoQuintela/LayoutLMv3-FUNSD with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("document-question-answering", model="SimaoQuintela/LayoutLMv3-FUNSD") # Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SimaoQuintela/LayoutLMv3-FUNSD", dtype="auto")This notebook trains the LayoutLMv3 layout model (on kagggle to take advantage of the GPU accelerators) on the FUNSD dataset. It also provides an inference phase where you can store your results on google drive
Base model
microsoft/layoutlmv3-base