Update pages/model_1.py

pages/model_1.py

@@ -1,30 +1,23 @@
-# Trained on 80 epochs at Batch size 256 with Learning Rate of 0.001 under 50 seconds!!
-from PIL import Image, ImageOps
-import numpy as np
-import pandas as pd
 import streamlit as st
 import tensorflow as tf
+import cv2
+from PIL import Image, ImageOps
+import numpy as np
 
 # Suppress warnings
 import warnings
 warnings.filterwarnings('ignore', category=UserWarning)
 warnings.filterwarnings('ignore', category=FutureWarning)
 
-# Disable scientific notation for clarity
-np.set_printoptions(suppress=True)
-
-def load_model_teachable():
-    # Load the model
-    model = tf.keras.models.load_model("pages/cnn_model.h5")
+def load_model():
+    model = tf.keras.models.load_model('pages/cnn_model.h5')
     return model
 
+
 with st.spinner('Model is being loaded..'):
-    model = load_model_teachable()
+    model = load_model()
 
-st.write("""
-         # Teachable Machine Model 
-         """
-         )
+st.write("# ResNet50 Model")
 
 st.sidebar.info("You should be happy if it classifies as - Healthy plant 🙂")
 
@@ -32,30 +25,17 @@ file = st.file_uploader("Upload the image to be classified", type=["jpg", "png"]
 st.set_option('deprecation.showfileUploaderEncoding', False)
 
 
-def upload_predict_teachable(image, model, class_names):
-
-    # Create the array of the right shape to feed into the keras model
-    # The 'length' or number of images you can put into the array is
-    # determined by the first position in the shape tuple, in this case 1
-    data = np.ndarray(shape=(1, 224, 224, 3), dtype=np.float32)
-
-    # Replace this with the path to your image
-    image_RGB = image.convert("RGB")
-
-    # resizing the image to be at least 224x224 and then cropping from the center
-    image_resized = image_RGB.resize((224, 224), resample=Image.LANCZOS)
-
-    # turn the image into a numpy array
-    image_array = np.asarray(image_resized)
+def upload_predict(upload_image, model):
+    size = (180, 180)
+    image = ImageOps.fit(upload_image, size, Image.LANCZOS)
+    image = np.asarray(image)
+    img = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+    img_resize = cv2.resize(img, dsize=(224, 224), interpolation=cv2.INTER_CUBIC)
 
-    # Normalize the image
-    normalized_image_array = (image_array.astype(np.float32) / 127.5) - 1
+    img_reshape = img_resize[np.newaxis, ...]
 
-    # Load the image into the array
-    data[0] = normalized_image_array
-
-    # Predicts the model
-    prediction = model.predict(data)
+    prediction = model.predict(img_reshape)
+    print(prediction)
     return prediction
 
 
@@ -65,39 +45,16 @@ else:
     image = Image.open(file)
     st.image(image, use_column_width=True)
     
-    # Load the labels
-    class_names = open("pages/labels.txt", "r").readlines()
-    prediction = upload_predict_teachable(image, model,class_names)
-    index = np.argmax(prediction)
-    class_name = class_names[index]
-    confidence_score = prediction[0][index]
+    prediction = upload_predict(image, model)
+    predicted_result = np.argmax(prediction)
+    
+    classfiers = ['bacterial_leaf_blight','bacterial_leaf_streak','bakanae','brown_spot','grassy_stunt_virus','healthy_rice_plant',
+    'narrow_brown_spot','ragged_stunt_virus','rice_blast','rice_false_smut','sheath_blight','sheath_rot','stem_rot','tungro_virus']
+    image_class = classfiers[predicted_result]
+    confidence_score = prediction[0][predicted_result]
 
-    # Print prediction and confidence score
-    result = f"Your plant is suffering from: {class_name[2:]}"
+    # Results
+    result = f"Your plant is suffering from: *{image_class}*"
     result_score = "✅ Accurate prediction score is: {} / 100".format("%.2f"  %  confidence_score)
     st.success(result)
-    st.info(result_score)
-
-
-st.markdown("""
-    #### Know more about this disease and suggestions to prevent them from spreading.
-
-    - *Just copy the disease name (result) from above & paste it in the below input box as it is!*
-""")
-
-# Loading diseases info & management strategies
-df = pd.read_csv('pages/Disease_solutions.csv')
-disease = st.text_input('Enter the disease name below 👇', '')
-
-# Selecting rows based on condition
-about = df.loc[df['Diseases'] == disease, ['Type', 'Description']]
-strategies = df.loc[df['Diseases'] == disease, 'Management Strategies']
-
-# Print diseases' other info
-tab1, tab2 = st.tabs(["👀 Description", "⭐ Solution"])
-
-with tab1:
-    st.dataframe(about, use_container_width=True)
-        
-with tab2:
-    st.dataframe(strategies, use_container_width=True)
+    st.info(result_score)