Update app.py

app.py

@@ -1,30 +1,30 @@
-import streamlit as st
-from tensorflow.keras.models import load_model
-from PIL import Image 
-import numpy as np 
-
-st.title("Skin Cancer Image Classification")
-st.write("Upload an image and let the model guess whether it is a cancer or not.")
-
-model = load_model("my_cnn_model.keras")
-
-def process_image(img):
-    img = img.resize((170,170)) # set the size as 170 x 170 pixel
-    img = np.array(img)
-    img = img / 255.0 # normalized
-    img = np.expand_dims(img, axis=0)
-    return img
-
-
-file = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
-
-if file is not None:
-    img = Image.open(file)
-    st.image(img, caption="Uploaded Image")
-    image = process_image(img)
-
-    prediction = model.predict(image)
-    predicted_class = np.argmax(prediction)
-
-    class_names = ["It is NOT Cancer!", "It is Cancer!"]
-    st.write(class_names[predicted_class])
+import streamlit as st
+from tensorflow.keras.models import load_model
+from PIL import Image 
+import numpy as np 
+
+st.title("Skin Cancer Image Classification")
+st.write("Upload an image and let the model guess whether it is a cancer or not.")
+
+model = load_model("my_cnn_model.keras")
+
+def process_image(img):
+    img = img.resize((170,170)) # set the size as 170 x 170 pixel
+    img = np.array(img)
+    img = img / 255.0 # normalized
+    img = np.expand_dims(img, axis=0)
+    return img
+
+
+file = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
+
+if file is not None:
+    img = Image.open(file)
+    st.image(img, caption="Uploaded Image")
+    image = process_image(img)
+
+    prediction = model.predict(image)
+    predicted_class = np.argmax(prediction)
+
+    class_names = ["It is NOT Cancer!", "A melanocytic nevus is usually a noncancerous condition where pigment-producing skin cells group together. It is a type of growth on the skin that contains nevus cells (a type of skin cell). "]
+    st.write(class_names[predicted_class])