Added base code from ViLT model

.gitignore

@@ -0,0 +1,5 @@
+venv
+venv/
+*.ipynb
+flagged
+*.jpg

README.md

@@ -0,0 +1,37 @@
+---
+title: Image Information Retrieval 
+emoji: 🌍
+colorFrom: indigo
+colorTo: gray
+sdk: gradio
+app_file: app.py
+pinned: false
+---
+
+# Configuration
+
+`title`: _string_  
+Display title for the Space
+
+`emoji`: _string_  
+Space emoji (emoji-only character allowed)
+
+`colorFrom`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`colorTo`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`sdk`: _string_  
+Can be either `gradio` or `streamlit`
+
+`sdk_version` : _string_  
+Only applicable for `streamlit` SDK.  
+See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
+
+`app_file`: _string_  
+Path to your main application file (which contains either `gradio` or `streamlit` Python code).  
+Path is relative to the root of the repository.
+
+`pinned`: _boolean_  
+Whether the Space stays on top of your list.

app.py

@@ -0,0 +1,39 @@
+import gradio as gr
+from transformers import ViltProcessor, ViltForQuestionAnswering
+import torch
+
+torch.hub.download_url_to_file('http://images.cocodataset.org/val2017/000000039769.jpg', 'cats.jpg')
+
+processor = ViltProcessor.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
+model = ViltForQuestionAnswering.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
+
+def answer_question(image, text):
+    encoding = processor(image, text, return_tensors="pt")
+    
+    # forward pass
+    with torch.no_grad():
+     outputs = model(**encoding)
+     
+    logits = outputs.logits
+    idx = logits.argmax(-1).item()
+    predicted_answer = model.config.id2label[idx]
+   
+    return predicted_answer
+   
+image = gr.Image(type="pil")
+question = gr.Textbox(label="Question")
+answer = gr.Textbox(label="Predicted answer")
+examples = [["cats.jpg", "How many cats are there?"]]
+
+title = "Interactive demo: ViLT"
+description = "Gradio Demo for ViLT (Vision and Language Transformer), fine-tuned on VQAv2, a model that can answer questions from images. 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/abs/2102.03334' target='_blank'>ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision</a> | <a href='https://github.com/dandelin/ViLT' target='_blank'>Github Repo</a></p>"
+
+interface = gr.Interface(fn=answer_question, 
+                         inputs=[image, question], 
+                         outputs=answer, 
+                         examples=examples, 
+                         title=title,
+                         description=description,
+                         article=article)
+interface.launch(debug=True)

gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

requirements.txt

@@ -0,0 +1,3 @@
+gradio
+torch
+git+https://github.com/huggingface/transformers.git