GrapeVineClassification / src /streamlit_app.py
EnYa32's picture
Update src/streamlit_app.py
a324b62 verified
Raw History Blame Contribute Delete
2.98 kB
# app.py --- Grapevine Leaf Disease Classifier using CNN (without Transfer Learning)
import streamlit as st
import numpy as np
from PIL import Image
import tensorflow as tf
from tensorflow.keras.models import load_model
import warnings
warnings.filterwarnings("ignore", category=DeprecationWarning)
st.set_page_config(
page_title="Grapevine CNN Classifier (No Transfer Learning)",
layout="centered"
)
# ------------------ SETTINGS ------------------
MODEL_PATH = "src/grape_cnn_final_optionA.keras" # CNN model (trained from scratch)
IMG_SIZE = (224, 224) # Based on your training setup
# Class labels (same order as during training)
CLASS_NAMES = [
"Black Rot",
"Esca (Black Measles)",
"Leaf Blight (Isariopsis Leaf Spot)",
"Healthy"
]
# ------------------ LOAD MODEL ------------------
@st.cache_resource
def load_model_cached():
return load_model(MODEL_PATH)
model = load_model_cached()
# ------------------ IMAGE PREPROCESSING ------------------
def preprocess_image(image: Image.Image) -> np.ndarray:
image = image.convert("RGB")
image = image.resize(IMG_SIZE)
img_array = np.array(image) / 255.0 # Normalization (used during training)
return np.expand_dims(img_array, axis=0)
# ------------------ PREDICTION ------------------
def predict(image: Image.Image):
processed_img = preprocess_image(image)
preds = model.predict(processed_img)
probs = tf.nn.softmax(preds[0]).numpy() # In case final layer used raw logits
top_idx = np.argmax(probs)
return CLASS_NAMES[top_idx], probs[top_idx], probs
# ------------------ STREAMLIT UI ------------------
st.title("πŸ‡ Grapevine Leaf Disease Classifier (CNN – No Transfer Learning)")
st.write(
"This app uses your custom Convolutional Neural Network trained **from scratch** "
"to classify grapevine leaf images into disease categories."
)
# --- Model Info ---
st.sidebar.header("πŸ”§ Model Details")
st.sidebar.write(f"**Model file:** `{MODEL_PATH}`")
st.sidebar.write(f"**Input size:** {IMG_SIZE[0]} Γ— {IMG_SIZE[1]}")
st.sidebar.write("**Class labels:**")
for cls in CLASS_NAMES:
st.sidebar.write(f"- {cls}")
# --- File Upload ---
uploaded_file = st.file_uploader("πŸ“€ Upload a grapevine leaf image", type=["jpg", "jpeg", "png"])
if uploaded_file is not None:
image = Image.open(uploaded_file)
st.image(image, caption="πŸ“Έ Uploaded Image", use_container_width=True)
if st.button("πŸ” Predict Disease"):
with st.spinner("Analyzing image..."):
top_class, top_prob, probabilities = predict(image)
st.subheader("πŸ”Ž Prediction Result")
st.write(f"**Predicted Disease:** `{top_class}`")
st.write(f"**Confidence:** {top_prob:.2%}")
st.subheader("πŸ“Š Probability per Class")
for cls, prob in zip(CLASS_NAMES, probabilities):
st.write(f"- **{cls}** β†’ {prob:.2%}")
else:
st.info("Please upload a grapevine leaf image to start the prediction.")