Upload 3 files

app.py

@@ -0,0 +1,71 @@
+import streamlit as st
+from PIL import Image
+import numpy as np
+from ultralytics import YOLO
+import inference
+from langchain.chat_models import AzureChatOpenAI
+import os
+from langchain.schema import HumanMessage
+import json
+
+
+yolo_model = YOLO('best.pt')
+roboflow_model = inference.get_model("web-icon-classification/1")
+chat4 = AzureChatOpenAI(
+    openai_api_base=os.environ['BASE_URL'],
+    openai_api_version="2024-02-15-preview",
+    deployment_name="gpt-4",
+    openai_api_key=os.environ["OPENAI_API_KEY"],
+    openai_api_type="azure",
+    temperature=0,
+    request_timeout=30,
+    max_retries=3
+) 
+
+def initiate_prompt(icon_name):
+    prompt =  '''Given the name of an app icon, return a list of alternative names that represent similar functionality in the context of a web or mobile app.
+
+    User Input: "Settings"
+
+    Expected Output: Generate a list of alternative names that convey the same or similar functionality as "Settings" in the context of web or mobile apps. 
+
+    Model Response: {
+    "alternatives": ["Preferences", "Options", "Controls", "Configuration", "Setup"]
+    }
+
+    User Input:''' + icon_name +'\n'+ "    Model Response:" 
+
+    return prompt
+
+st.title("App/Web Icon Classification Comparison")
+
+uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
+if uploaded_file is not None:
+    image = Image.open(uploaded_file)
+    st.image(image, caption='Uploaded Image', use_column_width=True)
+    
+    if st.button("Classify Image"):
+        with st.spinner('Classifying...'):
+            try:
+                prediction = yolo_model(image)
+                class_id_1 = prediction[0].names[prediction[0].probs.top1]
+                classes_1 = json.loads(chat4.predict_messages(messages=[HumanMessage(content=initiate_prompt(class_id_1))]).content)['alternatives']
+                classes_1.insert(0, class_id_1)
+            except:
+                classes_1 = "None"
+
+            try:
+                prediction = roboflow_model.infer(image)
+                class_id_2 =  prediction[0].predicted_classes[0]
+                classes_2 = json.loads(chat4.predict_messages(messages=[HumanMessage(content=initiate_prompt(class_id_2))]).content)['alternatives']
+                classes_2.insert(0, class_id_2)
+            except:
+                classes_2 = "None"
+
+            col1, col2 = st.columns(2)
+            with col1:
+                st.subheader("Yolov8-x Prediction")
+                st.write(f"Predicted Class: {classes_1}")
+            with col2:
+                st.subheader("ViT Prediction")
+                st.write(f"Predicted Class: {classes_2}")

best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60bbffada39a6907f8cd6592ace509782cbaecac253bf006fd28f85dc72c20e8
+size 112752945

requirements.txt

@@ -0,0 +1,149 @@
+aiohttp==3.9.5
+aioresponses==0.7.6
+aiosignal==1.3.1
+altair==5.3.0
+annotated-types==0.6.0
+anyio==4.3.0
+APScheduler==3.10.1
+async-timeout==4.0.3
+attrs==23.2.0
+awscli==1.29.54
+backoff==2.2.1
+blinker==1.7.0
+boto3==1.28.23
+botocore==1.31.54
+cachetools==5.3.3
+certifi==2024.2.2
+cffi==1.16.0
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.4
+coloredlogs==15.0.1
+contourpy==1.2.1
+cryptography==42.0.5
+cycler==0.12.1
+Cython==3.0.0
+dataclasses-json==0.6.4
+defusedxml==0.7.1
+distro==1.9.0
+docker==6.1.3
+docutils==0.16
+exceptiongroup==1.2.1
+fastapi==0.110.2
+filelock==3.13.4
+flatbuffers==24.3.25
+fonttools==4.51.0
+frozenlist==1.4.1
+fsspec==2024.3.1
+gitdb==4.0.11
+GitPython==3.1.43
+GPUtil==1.4.0
+h11==0.14.0
+httpcore==1.0.5
+httpx==0.27.0
+humanfriendly==10.0
+idna==3.7
+imageio==2.34.1
+inference==0.9.22
+iniconfig==2.0.0
+Jinja2==3.1.3
+jmespath==1.0.1
+jsonpatch==1.33
+jsonpointer==2.4
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+kiwisolver==1.4.5
+langchain==0.1.16
+langchain-community==0.0.34
+langchain-core==0.1.46
+langchain-text-splitters==0.0.1
+langsmith==0.1.51
+lazy_loader==0.4
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+marshmallow==3.21.1
+matplotlib==3.8.4
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.0.5
+mypy-extensions==1.0.0
+networkx==3.3
+numpy==1.25.2
+onnxruntime==1.15.1
+openai==1.23.6
+opencv-python==4.8.0.76
+opencv-python-headless==4.9.0.80
+orjson==3.10.1
+packaging==23.2
+pandas==2.2.2
+pendulum==3.0.0
+piexif==1.1.3
+pillow==10.3.0
+pluggy==1.5.0
+prettytable==3.10.0
+prometheus-fastapi-instrumentator==6.0.0
+prometheus_client==0.20.0
+protobuf==4.25.3
+psutil==5.9.8
+PuLP==2.8.0
+py-cpuinfo==9.0.0
+pyarrow==16.0.0
+pyasn1==0.6.0
+pybase64==1.3.2
+pycparser==2.22
+pydantic==2.7.1
+pydantic_core==2.18.2
+pydeck==0.9.0b1
+Pygments==2.17.2
+pyparsing==3.1.2
+pytest==8.1.2
+pytest-asyncio==0.21.1
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+pytz==2024.1
+PyYAML==6.0.1
+redis==5.0.4
+referencing==0.35.0
+requests==2.31.0
+requests-toolbelt==1.0.0
+rich==13.5.2
+rpds-py==0.18.0
+rsa==4.7.2
+s3transfer==0.6.2
+scikit-image==0.23.2
+scipy==1.13.0
+seaborn==0.13.2
+shapely==2.0.1
+six==1.16.0
+skypilot==0.4.1
+smmap==5.0.1
+sniffio==1.3.1
+SQLAlchemy==2.0.29
+starlette==0.37.2
+streamlit==1.33.0
+structlog==24.1.0
+supervision==0.20.0
+sympy==1.12
+tabulate==0.9.0
+tenacity==8.2.3
+thop==0.1.1.post2209072238
+tifffile==2024.4.24
+time-machine==2.14.1
+toml==0.10.2
+tomli==2.0.1
+toolz==0.12.1
+torch==2.3.0
+torchvision==0.18.0
+tornado==6.4
+tqdm==4.66.2
+typer==0.9.0
+typing-inspect==0.9.0
+typing_extensions==4.11.0
+tzdata==2024.1
+tzlocal==5.2
+ultralytics==8.2.3
+urllib3==1.26.18
+wcwidth==0.2.13
+websocket-client==1.8.0
+yarl==1.9.4
+zxing-cpp==2.2.0