Update app.py

app.py

@@ -146,7 +146,7 @@ sar_file = st.file_uploader("Upload SAR Image", type=["tiff"])
 optic_file = st.file_uploader("Upload Optical Image", type=["tiff"])
 mask_file = st.file_uploader("Upload Mask Image", type=["tiff"])
 
-num_samples = st.slider("Number of test samples to visualize", 1, 10, 3)
+num_samples = st.slider("Number of test samples to visualize", 1, 10, 1)
 
 if sar_file is not None and optic_file is not None and mask_file is not None:
     st.success("All files uploaded successfully!")
@@ -154,123 +154,116 @@ if sar_file is not None and optic_file is not None and mask_file is not None:
     sar_path = save_uploaded_file(sar_file, suffix=".tif")
     optic_path = save_uploaded_file(optic_file, suffix=".tif")
     mask_path = save_uploaded_file(mask_file, suffix=".tif")
-
-    st.write("Temporary paths created for inference:")
-    st.code(f"SAR Path: {sar_path}")
-    st.code(f"Optic Path: {optic_path}")
-    st.code(f"Mask Path: {mask_path}")
+ 
+    sarImages = [sar_path]
+    opticImages = [optic_path]
+    masks = [mask_path]
+    model_path = "Residual_UNET_Bilinear.keras"
+    
+    
+    if st.button("Run Inference"):
+        with st.spinner("Loading data and model..."):
+    
+            sar_images = readImages(sarImages, typeData='s', width=WIDTH, height=HEIGHT)
+            optic_images = readImages(opticImages, typeData='o', width=WIDTH, height=HEIGHT)
+            masks = readImages(masks, typeData='m', width=WIDTH, height=HEIGHT)
+    
+            sar_images = normalizeImages(sar_images, 's')
+            optic_images = normalizeImages(optic_images, 'i')
+    
+            # Load model
+            model = tf.keras.models.load_model(model_path,
+                                      custom_objects={"cce_dice_loss": cce_dice_loss, "dice_score": dice_score})
+    
+            pred_masks = model.predict([optic_images, sar_images], verbose=0)
+            is_multiclass = pred_masks.shape[-1] > 1
+    
+            num_samples = min(num_samples, len(sar_images))
+    
+            # Plotting
+            fig, axes = plt.subplots(num_samples, 4, figsize=(21, 6 * num_samples))
+    
+            for i in range(num_samples):
+                ax = axes[i] if num_samples > 1 else axes
     
+                ax[0].imshow(sar_images[i].squeeze(), cmap='gray')
+                ax[0].set_title(f"SAR Image {i+1}")
+                ax[0].axis('off')
     
+                ax[1].imshow(optic_images[i])
+                ax[1].set_title(f"Optic Image {i+1}")
+                ax[1].axis('off')
+    
+                if is_multiclass:
+                    gt_color_mask = np.zeros((*masks[i].shape[:2], 3))
+                    for j, color in enumerate(CLASS_COLORS):
+                        gt_color_mask += masks[i][:,:,j][:,:,np.newaxis] * np.array(color)
+                    ax[2].imshow(gt_color_mask)
+                else:
+                    ax[2].imshow(masks[i], cmap='gray')
+                ax[2].set_title(f"Ground Truth Mask {i+1}")
+                ax[2].axis('off')
+    
+                if is_multiclass:
+                    pred_color_mask = np.zeros((*pred_masks[i].shape[:2], 3))
+                    for j, color in enumerate(CLASS_COLORS):
+                        pred_color_mask += pred_masks[i][:,:,j][:,:,np.newaxis] * np.array(color)
+                    ax[3].imshow(pred_color_mask)
+                else:
+                    ax[3].imshow(pred_masks[i], cmap='gray')
+                ax[3].set_title(f"Predicted Mask {i+1}")
+                ax[3].axis('off')
+    
+            st.pyplot(fig)
+    
+            # Define color for class 1: illegal mining
+            red_color = [255, 0, 0]
+            
+            # Convert optic_images to uint8 if needed
+            if optic_images.dtype != np.uint8:
+                optic_images = (optic_images * 255).astype(np.uint8)
+            
+            # Create figure with subplots
+            fig, axes = plt.subplots(num_samples, 4, figsize=(21, 6 * num_samples))
+            
+            for i in range(num_samples):
+                ax = axes[i] if num_samples > 1 else axes
+            
+                # SAR image
+                ax[0].imshow(sar_images[i].squeeze(), cmap='gray')
+                ax[0].set_title(f"SAR Image {i+1}")
+                ax[0].axis('off')
+            
+                # Optic image
+                ax[1].imshow(optic_images[i])
+                ax[1].set_title(f"Optic Image {i+1}")
+                ax[1].axis('off')
+            
+                # Ground truth overlay
+                gt_overlay = optic_images[i].copy()
+                if is_multiclass:
+                    gt_overlay[masks[i][:, :, 1] == 1] = red_color
+                else:
+                    gt_overlay[masks[i].squeeze() == 1] = red_color
+            
+                ax[2].imshow(optic_images[i])
+                ax[2].imshow(gt_overlay, alpha=0.4)
+                ax[2].set_title(f"Ground Truth Overlay {i+1}")
+                ax[2].axis('off')
+            
+                # Predicted mask overlay
+                pred_overlay = optic_images[i].copy()
+                if is_multiclass:
+                    pred_overlay[pred_masks[i][:, :, 1] > 0.5] = red_color
+                else:
+                    pred_overlay[pred_masks[i].squeeze() > 0.5] = red_color
+            
+                ax[3].imshow(optic_images[i])
+                ax[3].imshow(pred_overlay, alpha=0.4)
+                ax[3].set_title(f"Predicted Overlay {i+1}")
+                ax[3].axis('off')
+            
+            plt.tight_layout()
+            st.pyplot(fig)
 else:
     st.warning("Please upload all three .tiff files to proceed.")
-    
-sarImages = [sar_path]
-opticImages = [optic_path]
-masks = [mask_path]
-model_path = "Residual_UNET_Bilinear.keras"
-
-
-if st.button("Run Inference"):
-    with st.spinner("Loading data and model..."):
-
-        sar_images = readImages(sarImages, typeData='s', width=WIDTH, height=HEIGHT)
-        optic_images = readImages(opticImages, typeData='o', width=WIDTH, height=HEIGHT)
-        masks = readImages(masks, typeData='m', width=WIDTH, height=HEIGHT)
-
-        sar_images = normalizeImages(sar_images, 's')
-        optic_images = normalizeImages(optic_images, 'i')
-
-        # Load model
-        model = tf.keras.models.load_model(model_path,
-                                  custom_objects={"cce_dice_loss": cce_dice_loss, "dice_score": dice_score})
-
-        pred_masks = model.predict([optic_images, sar_images], verbose=0)
-        is_multiclass = pred_masks.shape[-1] > 1
-
-        num_samples = min(num_samples, len(sar_images))
-
-        # Plotting
-        fig, axes = plt.subplots(num_samples, 4, figsize=(21, 6 * num_samples))
-
-        for i in range(num_samples):
-            ax = axes[i] if num_samples > 1 else axes
-
-            ax[0].imshow(sar_images[i].squeeze(), cmap='gray')
-            ax[0].set_title(f"SAR Image {i+1}")
-            ax[0].axis('off')
-
-            ax[1].imshow(optic_images[i])
-            ax[1].set_title(f"Optic Image {i+1}")
-            ax[1].axis('off')
-
-            if is_multiclass:
-                gt_color_mask = np.zeros((*masks[i].shape[:2], 3))
-                for j, color in enumerate(CLASS_COLORS):
-                    gt_color_mask += masks[i][:,:,j][:,:,np.newaxis] * np.array(color)
-                ax[2].imshow(gt_color_mask)
-            else:
-                ax[2].imshow(masks[i], cmap='gray')
-            ax[2].set_title(f"Ground Truth Mask {i+1}")
-            ax[2].axis('off')
-
-            if is_multiclass:
-                pred_color_mask = np.zeros((*pred_masks[i].shape[:2], 3))
-                for j, color in enumerate(CLASS_COLORS):
-                    pred_color_mask += pred_masks[i][:,:,j][:,:,np.newaxis] * np.array(color)
-                ax[3].imshow(pred_color_mask)
-            else:
-                ax[3].imshow(pred_masks[i], cmap='gray')
-            ax[3].set_title(f"Predicted Mask {i+1}")
-            ax[3].axis('off')
-
-        st.pyplot(fig)
-
-        # Define color for class 1: illegal mining
-        red_color = [255, 0, 0]
-        
-        # Convert optic_images to uint8 if needed
-        if optic_images.dtype != np.uint8:
-            optic_images = (optic_images * 255).astype(np.uint8)
-        
-        # Create figure with subplots
-        fig, axes = plt.subplots(num_samples, 4, figsize=(21, 6 * num_samples))
-        
-        for i in range(num_samples):
-            ax = axes[i] if num_samples > 1 else axes
-        
-            # SAR image
-            ax[0].imshow(sar_images[i].squeeze(), cmap='gray')
-            ax[0].set_title(f"SAR Image {i+1}")
-            ax[0].axis('off')
-        
-            # Optic image
-            ax[1].imshow(optic_images[i])
-            ax[1].set_title(f"Optic Image {i+1}")
-            ax[1].axis('off')
-        
-            # Ground truth overlay
-            gt_overlay = optic_images[i].copy()
-            if is_multiclass:
-                gt_overlay[masks[i][:, :, 1] == 1] = red_color
-            else:
-                gt_overlay[masks[i].squeeze() == 1] = red_color
-        
-            ax[2].imshow(optic_images[i])
-            ax[2].imshow(gt_overlay, alpha=0.4)
-            ax[2].set_title(f"Ground Truth Overlay {i+1}")
-            ax[2].axis('off')
-        
-            # Predicted mask overlay
-            pred_overlay = optic_images[i].copy()
-            if is_multiclass:
-                pred_overlay[pred_masks[i][:, :, 1] > 0.5] = red_color
-            else:
-                pred_overlay[pred_masks[i].squeeze() > 0.5] = red_color
-        
-            ax[3].imshow(optic_images[i])
-            ax[3].imshow(pred_overlay, alpha=0.4)
-            ax[3].set_title(f"Predicted Overlay {i+1}")
-            ax[3].axis('off')
-        
-        plt.tight_layout()
-        st.pyplot(fig)