Upload 4 files

app.py

@@ -0,0 +1,98 @@
+# Imporiting Necessary Libraries
+import streamlit as st
+from PIL import Image
+import io
+import numpy as np
+import tensorflow as tf
+from utils import clean_image, get_prediction, make_results
+
+# Loading the Model and saving to cache
+@st.cache(allow_output_mutation=True)
+def load_model(path):
+    
+    # Xception Model
+    xception_model = tf.keras.models.Sequential([
+    tf.keras.applications.xception.Xception(include_top=False, weights='imagenet', input_shape=(512, 512, 3)),
+    tf.keras.layers.GlobalAveragePooling2D(),
+    tf.keras.layers.Dense(4,activation='softmax')
+    ])
+
+
+    # DenseNet Model
+    densenet_model = tf.keras.models.Sequential([
+        tf.keras.applications.densenet.DenseNet121(include_top=False, weights='imagenet',input_shape=(512, 512, 3)),
+    tf.keras.layers.GlobalAveragePooling2D(),
+    tf.keras.layers.Dense(4,activation='softmax')
+    ])
+
+    # Ensembling the Models
+    inputs = tf.keras.Input(shape=(512, 512, 3))
+
+    xception_output = xception_model(inputs)
+    densenet_output = densenet_model(inputs)
+
+    outputs = tf.keras.layers.average([densenet_output, xception_output])
+
+
+    model = tf.keras.Model(inputs=inputs, outputs=outputs)
+
+    # Loading the Weights of Model
+    model.load_weights(path)
+    
+    return model
+
+
+# Removing Menu
+hide_streamlit_style = """
+            <style>
+            #MainMenu {visibility: hidden;}
+            footer {visibility: hidden;}
+            </style>
+            """
+st.markdown(hide_streamlit_style, unsafe_allow_html=True) 
+
+# Loading the Model
+model = load_model('model.h5')
+
+# Title and Description
+st.title('Plant Diesease Detection')
+st.write("Just Upload your Plant's Leaf Image and get predictions if the plant is healthy or not")
+
+# Setting the files that can be uploaded
+uploaded_file = st.file_uploader("Choose a Image file", type=["png", "jpg"])
+
+# If there is a uploaded file, start making prediction
+if uploaded_file != None:
+    
+    # Display progress and text
+    progress = st.text("Crunching Image")
+    my_bar = st.progress(0)
+    i = 0
+    
+    # Reading the uploaded image
+    image = Image.open(io.BytesIO(uploaded_file.read()))
+    st.image(np.array(Image.fromarray(
+        np.array(image)).resize((700, 400), Image.ANTIALIAS)), width=None)
+    my_bar.progress(i + 40)
+    
+    # Cleaning the image
+    image = clean_image(image)
+    
+    # Making the predictions
+    predictions, predictions_arr = get_prediction(model, image)
+    my_bar.progress(i + 30)
+    
+    # Making the results
+    result = make_results(predictions, predictions_arr)
+    
+    # Removing progress bar and text after prediction done
+    my_bar.progress(i + 30)
+    progress.empty()
+    i = 0
+    my_bar.empty()
+    
+    # Show the results
+    st.write(f"The plant {result['status']} with {result['prediction']} prediction.")
+
+    
+        

model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8640ee5f4430338106102c031d535efdb1e5f0cf5bb52d7ba89eec7ad4f9f65
+size 336021776

requirements.txt

@@ -0,0 +1,5 @@
+tensorflow
+streamlit
+Pillow==9.5.0
+numpy
+scipy

utils.py

@@ -0,0 +1,54 @@
+# Imporiting Necessary Libraries
+import tensorflow as tf
+import numpy as np
+from PIL import Image
+
+
+# Cleanig image    
+def clean_image(image):
+    image = np.array(image)
+    
+    # Resizing the image
+    image = np.array(Image.fromarray(
+        image).resize((512, 512), Image.ANTIALIAS))
+        
+    # Adding batch dimensions to the image
+    # YOu are seeting :3, that's becuase sometimes user upload 4 channel image,
+    image = image[np.newaxis, :, :, :3]
+    # So we just take first  3 channels
+    
+    return image
+    
+    
+def get_prediction(model, image):
+
+    datagen = tf.keras.preprocessing.image.ImageDataGenerator(
+        rescale=1./255)
+    
+    # Inputting the image to keras generators
+    test = datagen.flow(image)
+    
+    # Predict from the image
+    predictions = model.predict(test)
+    predictions_arr = np.array(np.argmax(predictions))
+    
+    return predictions, predictions_arr
+    
+
+# Making the final results 
+def make_results(predictions, predictions_arr):
+    
+    result = {}
+    if int(predictions_arr) == 0:
+        result = {"status": " is Healthy ",
+                    "prediction": f"{int(predictions[0][0].round(2)*100)}%"}
+    if int(predictions_arr) == 1:
+        result = {"status": ' has Multiple Diseases ',
+                    "prediction": f"{int(predictions[0][1].round(2)*100)}%"}
+    if int(predictions_arr) == 2:
+        result = {"status": ' has Rust ',
+                    "prediction": f"{int(predictions[0][2].round(2)*100)}%"}
+    if int(predictions_arr) == 3:
+        result = {"status": ' has Scab ',
+                    "prediction": f"{int(predictions[0][3].round(2)*100)}%"}
+    return result