Upload 5 files

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 AI Anytime
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -1,12 +1,2 @@
----
-title: ImageTest
-emoji: 🐨
-colorFrom: indigo
-colorTo: purple
-sdk: streamlit
-sdk_version: 1.38.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Visual-Question-Answering-API-and-App
+Visual Question Answering API and App using ViLT, Fast API, and Streamlit.

api.py

@@ -0,0 +1,44 @@
+from fastapi import FastAPI, File, UploadFile
+from fastapi.responses import JSONResponse, RedirectResponse
+from transformers import ViltProcessor, ViltForQuestionAnswering
+from PIL import Image
+import requests
+import io
+
+app = FastAPI(title="Visual Question and Answering API", version="0.0.1")
+
+#Loading the model and tokenizer
+processor = ViltProcessor.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
+model = ViltForQuestionAnswering.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
+
+def get_answer(image, text):
+    try:
+        # Load and process the image
+        img = Image.open(io.BytesIO(image)).convert("RGB")
+
+        # Prepare inputs
+        encoding = processor(img, text, return_tensors="pt")
+
+        # Forward pass
+        outputs = model(**encoding)
+        logits = outputs.logits
+        idx = logits.argmax(-1).item()
+        answer = model.config.id2label[idx]
+
+        return answer
+
+    except Exception as e:
+        return str(e)
+
+@app.get("/", include_in_schema=False)
+async def index():
+    return RedirectResponse(url="/docs")
+
+@app.post("/answer")
+async def process_image(image: UploadFile = File(...), text: str = None):
+    try:
+        answer = get_answer(await image.read(), text)
+        return JSONResponse({"Answer": answer})
+
+    except Exception as e:
+        return JSONResponse({"Sorry, please reach out to the Admin!": str(e)})

app.py

@@ -0,0 +1,60 @@
+import streamlit as st
+from PIL import Image
+import requests
+from io import BytesIO
+from transformers import ViltProcessor, ViltForQuestionAnswering
+
+# Set page layout to wide
+st.set_page_config(layout="wide")
+
+processor = ViltProcessor.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
+model = ViltForQuestionAnswering.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
+
+def get_answer(image, text):
+    try:
+        # Load and process the image
+        img = Image.open(BytesIO(image)).convert("RGB")
+
+        # Prepare inputs
+        encoding = processor(img, text, return_tensors="pt")
+
+        # Forward pass
+        outputs = model(**encoding)
+        logits = outputs.logits
+        idx = logits.argmax(-1).item()
+        answer = model.config.id2label[idx]
+
+        return answer
+
+    except Exception as e:
+        return str(e)
+
+# Set up the Streamlit app
+st.title("Visual Question Answering")
+st.write("Upload an image and enter a question to get an answer.")
+
+# Create columns for image upload and input fields
+col1, col2 = st.columns(2)
+
+# Image upload
+with col1:
+    uploaded_file = st.file_uploader("Upload Image", type=["jpg", "jpeg", "png"])
+    st.image(uploaded_file, use_column_width=True)
+
+# Question input
+with col2:
+    question = st.text_input("Question")
+
+    # Process the image and question when both are provided
+    if uploaded_file and question is not None:
+        if st.button("Ask Question"):
+            image = Image.open(uploaded_file)
+            image_byte_array = BytesIO()
+            image.save(image_byte_array, format='JPEG')
+            image_bytes = image_byte_array.getvalue()
+
+            # Get the answer
+            answer = get_answer(image_bytes, question)
+
+            # Display the answer
+            st.success("Answer: " + answer)

requirements.txt

@@ -0,0 +1,8 @@
+transformers
+torch
+requests
+Pillow
+fastapi
+uvicorn
+streamlit
+python-multipart