Deploy FastAPI animal classification to HF Space

README.md

@@ -1,12 +1,39 @@
 ---
-title: Fastapi
-emoji: 🏆
-colorFrom: indigo
-colorTo: indigo
-sdk: gradio
-sdk_version: 5.49.1
+title: Animal Classification API
+emoji: 🐾
+colorFrom: blue
+colorTo: green
+sdk: fastapi
+sdk_version: "0.115.4"
 app_file: app.py
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Animal Classification API
+
+A FastAPI inference service for classifying images of animals (Cat, Dog, Panda).
+
+## Features
+
+- **FastAPI** REST API with automatic documentation
+- **TensorFlow** model for image classification
+- **Swagger UI** at `/docs` for interactive testing
+- Supports JPG, PNG image uploads
+
+## Usage
+
+1. Open the Space URL
+2. Navigate to `/docs` endpoint
+3. Try the `POST /upload/image` endpoint
+4. Upload an image of a Cat, Dog, or Panda
+5. Get instant classification results!
+
+## API Endpoints
+
+- `POST /upload/image` - Upload an image for classification
+- `GET /docs` - Interactive API documentation
+- `GET /redoc` - Alternative API documentation
+
+## Model
+
+Uses a CNN trained on animal images with 64x64 input resolution.

app.py

@@ -0,0 +1,35 @@
+from fastapi import FastAPI
+app = FastAPI()
+
+from fastapi.middleware.cors import CORSMiddleware
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+from tensorflow import keras
+import tensorflow as tf
+import os
+ANIMALS = ['Cat', 'Dog', 'Panda'] # Animal names here, these represent the labels of the images that we trained our model on.
+
+# It would've been better to use an environment variable to fix this line actually...
+model_path = os.path.join("animal-classification", "INPUT_model_path", "animal-cnn", "model.keras")
+model = tf.keras.models.load_model(model_path)
+
+from fastapi import File, UploadFile
+import numpy as np
+from PIL import Image
+
+@app.post('/upload/image')
+async def uploadImage(img: UploadFile = File(...)):
+    original_image = Image.open(img.file) # Read the bytes and process as an image
+    resized_image = original_image.resize((64, 64)) # Resize
+    images_to_predict = np.expand_dims(np.array(resized_image), axis=0) # Our AI Model wanted a list of images, but we only have one, so we expand it's dimension
+    predictions = model.predict(images_to_predict) # The result will be a list with predictions in the one-hot encoded format: [ [0 1 0] ]
+    prediction_probabilities = predictions
+    classifications = prediction_probabilities.argmax(axis=1) # We try to fetch the index of the highest value in this list [ [1] ]
+
+    return ANIMALS[classifications.tolist()[0]] # Fetch the first item in our classifications array, format it as a list first, result will be e.g.: "Dog"

requirements.txt

@@ -0,0 +1,6 @@
+fastapi==0.101.1
+uvicorn[standard]==0.30.6
+tensorflow==2.16.1
+pillow==10.1.0
+numpy==1.26.0
+python-multipart==0.0.9