Update app.py

app.py

@@ -1,20 +1,58 @@
 import streamlit as st
-from transformers import pipeline
+import seaborn as sns
+import matplotlib.pyplot as plt
+import os, random
+import cv2
+from tensorflow.keras.models import load_model
 from PIL import Image
 
-pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
+def main():
+    st.title('Sudoku Solver')
 
-st.title("Hot Dog? Or Not?")
+    uploaded_file = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
 
-file_name = st.file_uploader("Upload a hot dog candidate image")
+    if uploaded_file is not None:
+        # Importing puzzle to be solved
+        puzzle = cv2.imread(uploaded_file) 
+        
+        # Resizing puzzle to be solved
+        puzzle = cv2.resize(puzzle, (450,450))
+        # Preprocessing Puzzle 
+        su_puzzle = preprocess(puzzle)
+        
+        # Finding the outline of the sudoku puzzle in the image
+        su_contour_1= su_puzzle.copy()
+        su_contour_2= sudoku_a.copy()
+        su_contour, hierarchy = cv2.findContours(su_puzzle,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
+        cv2.drawContours(su_contour_1, su_contour,-1,(0,255,0),3)
+        
+        black_img = np.zeros((450,450,3), np.uint8)
+        su_biggest, su_maxArea = main_outline(su_contour)
+        if su_biggest.size != 0:
+            su_biggest = reframe(su_biggest)
+            cv2.drawContours(su_contour_2,su_biggest,-1, (0,255,0),10)
+            su_pts1 = np.float32(su_biggest)
+            su_pts2 = np.float32([[0,0],[450,0],[0,450],[450,450]])
+            su_matrix = cv2.getPerspectiveTransform(su_pts1,su_pts2)  
+            su_imagewrap = cv2.warpPerspective(puzzle,su_matrix,(450,450))
+            su_imagewrap =cv2.cvtColor(su_imagewrap, cv2.COLOR_BGR2GRAY)
 
-if file_name is not None:
-    col1, col2 = st.columns(2)
+        sudoku_cell = splitcells(su_imagewrap)
+        sudoku_cell_croped= CropCell(sudoku_cell)
 
-    image = Image.open(file_name)
-    col1.image(image, use_column_width=True)
-    predictions = pipeline(image)
+        grid = read_cells(sudoku_cell_croped, model)
+        grid = np.asarray(grid)
+        grid = np.reshape(grid,(9,9))
+        solve(grid)    
+    
 
-    col2.header("Probabilities")
-    for p in predictions:
-        col2.subheader(f"{ p['label'] }: { round(p['score'] * 100, 1)}%")
+
+        # Display the solution or appropriate message
+        if solve(grid):
+            st.header("Sudoku Solved:")
+            st.write(Solved(grid))
+        else:
+            st.write("No solution found.")
+
+if __name__ == '__main__':
+    main()