Initial commit with LFS

.dockerignore

@@ -0,0 +1,6 @@
+__pycache__
+*.ipynb
+.ipynb_checkpoints
+.git
+.env
+.DS_Store

.gitattributes

@@ -0,0 +1,35 @@
+*.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
+*.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

.gitignore

@@ -0,0 +1,6 @@
+__pycache__/
+*.ipynb
+.ipynb_checkpoints/
+.git/
+.env
+.DS_Store

Dockerfile

@@ -0,0 +1,22 @@
+FROM python:3.9-slim
+
+# Set up a new user named "user" with user ID 1000
+RUN useradd -m -u 1000 user
+
+# Switch to the "user" user
+USER user
+
+# Set home to the user's home directory
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+# Copy the current directory contents into the container at /app setting the owner to the user
+COPY --chown=user requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+
+EXPOSE 7860
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -0,0 +1,10 @@
+---
+title: Fruits API
+emoji: 🌖
+colorFrom: pink
+colorTo: pink
+sdk: docker
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,138 @@
+# import base64 # Not needed
+from fastapi import FastAPI, File, UploadFile, HTTPException
+from fastapi.responses import StreamingResponse
+from PIL import Image, ImageDraw, ImageFont
+import numpy as np
+import tensorflow as tf
+import io
+from typing import List
+
+app = FastAPI(title="Fruit Classifier API")
+
+# Load the model
+# Assuming the model is in the same directory
+MODEL_PATH = "fruit_classifier_model.h5"
+try:
+    model = tf.keras.models.load_model(MODEL_PATH)
+    print(f"Model loaded successfully from {MODEL_PATH}")
+except Exception as e:
+    print(f"Error loading model: {e}")
+    # We allow the app to start even if model fails, but predict will fail
+    model = None
+
+# Class names extracted from the training notebook
+CLASS_NAMES = [
+    'Apple', 'Apricots', 'Avocado', 'Banana', 'Blackberries', 'Blueberry', 
+    'Cantaloupe', 'Cherry', 'Coconut', 'Dates', 'Dragon fruit', 'Fig', 
+    'Grapes', 'Guava', 'Jackfruit', 'Kiwi', 'Lemons', 'Lychee', 'Mango', 
+    'Olive', 'Orange', 'Papaya', 'Pear', 'Persimmon', 'Pineapple', 'Plum', 
+    'Pomegranate', 'Rambutan', 'Raspberry', 'Salak', 'Sapodilla', 'Soursop', 
+    'Starfruit', 'Strawberry', 'Watermelon'
+]
+
+def preprocess_image(image: Image.Image) -> np.ndarray:
+    """
+    Preprocess the image to match the model's expected input.
+    EfficientNet usually expects (224, 224, 3) and values in [0, 255] 
+    if using the internal preprocessing layer, or pre-scaled if not.
+    The notebook showed:
+    tf.keras.utils.image_dataset_from_directory(..., image_size=(224, 224), ...)
+    and the model used Rescaling/Normalization layers inside it (efficientnetb0 usually has it or we saw Rescaling layer in summary).
+    The provided summary showed: 
+     rescaling (Rescaling) ...
+     normalization (Normalization) ...
+    So we just need to resize to (224, 224) and provide inputs as they are (0-255 usually for uint8, but converting to float32 is safer).
+    """
+    if image.mode != "RGB":
+        image = image.convert("RGB")
+    
+    image_resized = image.resize((224, 224))
+    image_array = np.array(image_resized)
+    image_array = np.expand_dims(image_array, axis=0) # Add batch dimension
+    return image_array
+
+@app.get("/")
+def read_root():
+    return {"message": "Welcome to the Fruit Classifier API"}
+
+@app.post("/predict")
+async def predict(file: UploadFile = File(...)):
+    if model is None:
+        raise HTTPException(status_code=500, detail="Model not loaded")
+    
+    try:
+        contents = await file.read()
+        image = Image.open(io.BytesIO(contents))
+        processed_image = preprocess_image(image)
+        
+        predictions = model.predict(processed_image)
+        predicted_class_index = np.argmax(predictions[0])
+        confidence = float(predictions[0][predicted_class_index])
+        predicted_class = CLASS_NAMES[predicted_class_index]
+        
+        return {
+            "prediction": predicted_class,
+            "confidence": confidence,
+            "filename": file.filename
+        }
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.post("/predict_image")
+async def predict_image(file: UploadFile = File(...)):
+    if model is None:
+        raise HTTPException(status_code=500, detail="Model not loaded")
+    
+    try:
+        contents = await file.read()
+        original_image = Image.open(io.BytesIO(contents))
+        
+        # Ensure RGB
+        if original_image.mode != "RGB":
+            original_image = original_image.convert("RGB")
+            
+        processed_image = preprocess_image(original_image)
+        
+        predictions = model.predict(processed_image)
+        predicted_class_index = np.argmax(predictions[0])
+        confidence = float(predictions[0][predicted_class_index])
+        predicted_class = CLASS_NAMES[predicted_class_index]
+        
+        # Draw on the original image
+        draw = ImageDraw.Draw(original_image)
+        
+        # Try to load a nice font, otherwise default
+        try:
+            # Try loading a system font (Windows usually has arial)
+            font = ImageFont.truetype("arial.ttf", size=int(original_image.height / 20))
+        except IOError:
+            font = ImageFont.load_default()
+            
+        text = f"{predicted_class} ({confidence:.2f})"
+        
+        # Calculate text position (top-left or centered-top)
+        text_position = (10, 10)
+        
+        # Draw text with outline for better visibility
+        x, y = text_position
+        outline_color = "black"
+        text_color = "red"
+        
+        draw.text((x-1, y-1), text, font=font, fill=outline_color)
+        draw.text((x+1, y-1), text, font=font, fill=outline_color)
+        draw.text((x-1, y+1), text, font=font, fill=outline_color)
+        draw.text((x+1, y+1), text, font=font, fill=outline_color)
+        draw.text(text_position, text, font=font, fill=text_color)
+        
+        # Save to bytes
+        img_byte_arr = io.BytesIO()
+        original_image.save(img_byte_arr, format='JPEG')
+        img_byte_arr.seek(0)
+        
+        return StreamingResponse(img_byte_arr, media_type="image/jpeg")
+        
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=7860)

fruit_classifier_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ac2a906652b32c4f0852ce291d45ec14188ae57ce3205926bb797a8f7f03a3
+size 17467592

requirements.txt

@@ -0,0 +1,6 @@
+fastapi
+uvicorn
+python-multipart
+pillow
+numpy
+tensorflow