Spaces:
Sleeping
Sleeping
| import numpy as np | |
| import streamlit as st | |
| from tensorflow.keras.preprocessing import image | |
| from tensorflow.keras.models import load_model | |
| from tensorflow.keras.applications.resnet50 import preprocess_input | |
| # Load the trained model | |
| model_path = 'my_cnn.h5' # or '/content/my_model.keras' | |
| model = load_model(model_path) | |
| # Preprocess the image | |
| def preprocess_image(img): | |
| img_array = image.img_to_array(img) | |
| img_array = np.expand_dims(img_array, axis=0) # Add batch dimension | |
| img_array = preprocess_input(img_array) # Ensure correct preprocessing for ResNet50 | |
| return img_array | |
| # Make predictions and map to class labels | |
| def classify_image(img): | |
| img_array = preprocess_image(img) | |
| predictions = model.predict(img_array) | |
| predicted_class = np.argmax(predictions, axis=1) # Get the index of the highest probability | |
| class_labels = {0: 'Aedes Aegypti', 1: 'Anopheles Stephensi', 2: 'Culex Quinquefasciatus'} | |
| species = class_labels.get(predicted_class[0], "Unknown") | |
| return species, predictions | |
| # Streamlit application | |
| def main(): | |
| st.title("Mosquito Species Classification") | |
| st.write("Upload a mosquito image or select an example image to classify its species.") | |
| # Example images | |
| example_images = { | |
| "Aedes Aegypti": "Aedes_aegypti_1_0_832.jpg", | |
| "Anopheles Stephensi": "Anopheles_stephensi_1_0_364.jpg", | |
| "Culex Quinquefasciatus": "Culex_quinquefasciatus_1_0_1307.jpg", | |
| } | |
| # Select an example image | |
| selected_example = st.selectbox("Or select an example image:", list(example_images.keys())) | |
| if selected_example: | |
| img_path = example_images[selected_example] | |
| img = image.load_img(img_path, target_size=(224, 224)) | |
| st.image(img, caption=f'Selected Example Image: {selected_example}', width=224) | |
| # Classify the example image | |
| result, probabilities = classify_image(img) | |
| st.write(f'Predicted mosquito species: **{result}**') | |
| st.write(f'Prediction probabilities: {probabilities}') | |
| # File uploader for image input | |
| uploaded_file = st.file_uploader("Or upload your own image...", type=["jpg", "jpeg", "png"]) | |
| if uploaded_file is not None: | |
| # Load the image for display | |
| img = image.load_img(uploaded_file, target_size=(224, 224)) | |
| st.image(img, caption='Uploaded Image', width=224) | |
| # Classify the image | |
| result, probabilities = classify_image(img) | |
| st.write(f'Predicted mosquito species: **{result}**') | |
| st.write(f'Prediction probabilities: {probabilities}') | |
| # Run the app | |
| if __name__ == "__main__": | |
| main() | |