Duplicate from akdeniz27/pix2struct-DocVQA

Co-authored-by: Taner Akdeniz <akdeniz27@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Pix2struct DocVQA
+emoji: 🏢
+colorFrom: yellow
+colorTo: blue
+sdk: gradio
+sdk_version: 3.23.0
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: akdeniz27/pix2struct-DocVQA
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,28 @@
+import gradio as gr
+# from PIL import Image
+from transformers import Pix2StructForConditionalGeneration, Pix2StructProcessor
+
+model = Pix2StructForConditionalGeneration.from_pretrained("google/pix2struct-docvqa-large")
+processor = Pix2StructProcessor.from_pretrained("google/pix2struct-docvqa-large")
+
+def process_document(image, question):
+    # image = Image.open(image)
+    inputs = processor(images=image, text=question, return_tensors="pt")
+    predictions = model.generate(**inputs)
+    return processor.decode(predictions[0], skip_special_tokens=True)
+ 
+description = "Demo for pix2struct fine-tuned on DocVQA (document visual question answering). To use it, simply upload your image and type a question and click 'submit', or click one of the examples to load them. Read more at the links below."
+article = "<p style='text-align: center'><a href='https://arxiv.org/pdf/2210.03347.pdf' target='_blank'>PIX2STRUCT: SCREENSHOT PARSING AS PRETRAINING FOR VISUAL LANGUAGE UNDERSTANDING</a></p>"
+
+demo = gr.Interface(
+    fn=process_document,
+    inputs=["image", "text"],
+    outputs="text",
+    title="Demo: pix2struct for DocVQA",
+    description=description,
+    article=article,
+    enable_queue=True,
+    examples=[["example_1.png", "When is the coffee break?"], ["example_2.jpeg", "What's the population of Stoddard?"]],
+    cache_examples=False)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,2 @@
+torch
+git+https://github.com/huggingface/transformers