deploy app

app.py

@@ -0,0 +1,59 @@
+import gradio as gr
+from transformers import AutoImageProcessor, AutoModelForImageClassification
+from PIL import Image
+import torch
+
+# Load the feature extractor and model from Hugging Face
+feature_extractor = AutoImageProcessor.from_pretrained(
+    "microsoft/swinv2-base-patch4-window16-256"
+)
+model = AutoModelForImageClassification.from_pretrained(
+    "amaye15/SwinV2-Base-Image-Orientation-Fixer"
+)
+
+
+def predict_image(image):
+    # Convert the image to the required format and preprocess it
+    inputs = feature_extractor(images=image, return_tensors="pt")
+    # Perform the prediction
+    outputs = model(**inputs)
+    # Get the predicted class probabilities
+    logits = outputs.logits
+    # Calculate softmax to get probabilities
+    probabilities = torch.softmax(logits, dim=-1).squeeze()
+    # Create a dictionary of all class labels and their probabilities
+    result = {
+        model.config.id2label[idx]: prob.item()
+        for idx, prob in enumerate(probabilities)
+    }
+    # Sort the results by probability in descending order
+    sorted_result = dict(sorted(result.items(), key=lambda item: item[1], reverse=True))
+    return sorted_result
+
+
+# Enhanced description with a detailed overview of the app
+description = """
+### Overview
+This application is a web-based interface built using Gradio that allows users to upload images and receive class predictions with probabilities. 
+It utilizes a pre-trained SwinV2 model from Hugging Face.
+
+### How It Works
+1. **Image Upload**: Users upload an image which is then processed and classified by the model.
+2. **Feature Extraction**: The image is preprocessed using a feature extractor that converts it into a format suitable for the model.
+3. **Prediction**: The model predicts the class probabilities using a softmax function on the output logits.
+4. **Results**: The results are displayed as a sorted list of classes with their corresponding probabilities, showing the most likely class first.
+
+Enjoy exploring the capabilities of this advanced image classification model!
+"""
+
+# Create the Gradio interface using the updated components and enhanced description
+iface = gr.Interface(
+    fn=predict_image,  # The prediction function
+    inputs=gr.Image(type="pil"),  # Accepts images in PIL format
+    outputs=gr.Label(num_top_classes=None),  # Outputs all predicted classes
+    title="Image Orientation",  # Optional title
+    description=description,  # Enhanced description with detailed app overview
+)
+
+# Launch the Gradio app
+iface.launch()

requirements.txt

@@ -0,0 +1,66 @@
+aiofiles==23.2.1
+annotated-types==0.7.0
+anyio==4.4.0
+certifi==2024.8.30
+charset-normalizer==3.3.2
+click==8.1.7
+contourpy==1.3.0
+cycler==0.12.1
+fastapi==0.112.2
+ffmpy==0.4.0
+filelock==3.15.4
+fonttools==4.53.1
+fsspec==2024.6.1
+gradio==4.42.0
+gradio_client==1.3.0
+h11==0.14.0
+httpcore==1.0.5
+httpx==0.27.2
+huggingface-hub==0.24.6
+idna==3.8
+importlib_resources==6.4.4
+Jinja2==3.1.4
+kiwisolver==1.4.5
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.2
+mdurl==0.1.2
+mpmath==1.3.0
+networkx==3.3
+numpy==2.1.0
+orjson==3.10.7
+packaging==24.1
+pandas==2.2.2
+pdf2image==1.17.0
+pillow==10.4.0
+pydantic==2.8.2
+pydantic_core==2.20.1
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.2
+regex==2024.7.24
+requests==2.32.3
+rich==13.8.0
+ruff==0.6.3
+safetensors==0.4.4
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+starlette==0.38.4
+sympy==1.13.2
+tokenizers==0.19.1
+tomlkit==0.12.0
+torch==2.4.0
+tqdm==4.66.5
+transformers==4.44.2
+typer==0.12.5
+typing_extensions==4.12.2
+tzdata==2024.1
+urllib3==2.2.2
+uvicorn==0.30.6
+websockets==12.0