create app

README.md

@@ -1,8 +1,8 @@
 ---
-title: Soils Class
-emoji: 🐨
-colorFrom: red
-colorTo: purple
+title: Soil Classification
+emoji: 🌍
+colorFrom: blue
+colorTo: red
 sdk: streamlit
 sdk_version: 1.25.0
 app_file: app.py

app.py

@@ -0,0 +1,43 @@
+#Library imports
+import numpy as np
+import streamlit as st
+import cv2
+from keras.models import load_model
+
+
+#Loading the Model
+model = load_model('soils.h5')
+
+#Name of Classes
+CLASS_NAMES = ['Acrisols', 'Fluvisols', 'Ferrasols']
+
+#Setting Title of App
+st.title("Soils classification")
+st.markdown("Upload an image of the soil")
+
+#Uploading the soil image
+soil_image = st.file_uploader("Choose an image...", type="jpg")
+submit = st.button('Predict')
+#On predict button click
+if submit:
+
+
+    if soil_image is not None:
+
+        # Convert the file to an opencv image.
+        file_bytes = np.asarray(bytearray(soil_image.read()), dtype=np.uint8)
+        opencv_image = cv2.imdecode(file_bytes, 1)
+
+
+
+        # Displaying the image
+        st.image(opencv_image, channels="BGR")
+        st.write(opencv_image.shape)
+        #Resizing the image
+        opencv_image = cv2.resize(opencv_image, (256,256))
+        #Convert image to 4 Dimension
+        opencv_image.shape = (1,256,256,3)
+        #Make Prediction
+        Y_pred = model.predict(opencv_image)
+        result = CLASS_NAMES[np.argmax(Y_pred)]
+        st.title(str("This is "+result.split('-')[0]+ " leaf with " + result.split('-')[1]))

requirements.txt

@@ -0,0 +1,5 @@
+streamlit
+Keras
+numpy
+opencv_python
+tensorflow

soils.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba09daa7f91cebd8eac6a202f71939e174b304150fe8daa8f2eb0e9861f049e6
+size 2822224