Deploying to HF

app.py

@@ -62,7 +62,7 @@ class Explainer:
                                             ["all", "absolute_value"],
                                             cmap=self.default_cmap,
                                             show_colorbar=True)
-        fig.suptitle(self.fig_title, fontsize=12)
+        fig.suptitle("SHAP | " + self.fig_title, fontsize=12)
         return self.convert_fig_to_pil(fig)
 
     def occlusion(self):
@@ -82,7 +82,7 @@ class Explainer:
                                             titles=["Original", "Positive Attribution", "Negative Attribution", "Masked"],
                                             fig_size=(18, 6)
                                             )
-        fig.suptitle(self.fig_title, fontsize=12)
+        fig.suptitle("Occlusion | " + self.fig_title, fontsize=12)
         return self.convert_fig_to_pil(fig)
     
     def gradcam(self):
@@ -101,6 +101,7 @@ class Explainer:
                                             show_colorbar=True,
                                             titles=["Original", "Positive Attribution", "Masked"],
                                             fig_size=(18, 6))
+        fig.suptitle("GradCAM layer3[1].conv2 | " + self.fig_title, fontsize=12)
         return self.convert_fig_to_pil(fig)
     
     def integrated_gradients(self):
@@ -114,7 +115,7 @@ class Explainer:
                                             show_colorbar=True,
                                             titles=["Original", "Attribution", "Masked"],
                                             fig_size=(18, 6))
-        fig.suptitle(self.fig_title, fontsize=12)
+        fig.suptitle("Integrated gradients | " + self.fig_title, fontsize=12)
         return self.convert_fig_to_pil(fig)
 
 def create_model_from_checkpoint():
@@ -130,10 +131,10 @@ labels = [ "benign", "malignant", "normal" ]
 
 def predict(img):
     explainer = Explainer(model, img, labels)
-    return [explainer.confidences, explainer.shap(), explainer.occlusion(), explainer.gradcam(), explainer.integrated_gradients()] 
+    return [explainer.confidences, explainer.shap(), explainer.occlusion(), explainer.gradcam()] 
 
 ui = gr.Interface(fn=predict, 
                 inputs=gr.Image(type="pil"),
-                outputs=[gr.Label(num_top_classes=3), gr.Image(type="pil"), gr.Image(type="pil"), gr.Image(type="pil"), gr.Image(type="pil")],
+                outputs=[gr.Label(num_top_classes=3), gr.Image(type="pil"), gr.Image(type="pil"), gr.Image(type="pil")],
                 examples=["benign (52).png", "benign (243).png", "malignant (127).png", "malignant (201).png", "normal (81).png", "normal (101).png"]).launch()
 ui.launch(share=True)