final touches

Introduction.md

@@ -7,7 +7,6 @@ For example
 
 Conformal prediction is a technique for quantifying such uncertainties for AI systems. In particular, given an input, conformal prediction estimates a prediction interval in regression problems and a set of classes in classification problems. Both the prediction interval and sets are guaranteed to cover the true value with high probability.
 
---- 
 
 # Theory
 

app.py

@@ -57,10 +57,11 @@ if __name__ == '__main__':
     st.markdown(css, unsafe_allow_html=True)
 
     with intro_tab:
-
+        st.write("", "", "")
         f = open("Introduction.md",'r')
         st.markdown(f.read())
 
+        st.write("---")
 
     with reg_tab:
         with st.container():
@@ -110,13 +111,13 @@ if __name__ == '__main__':
                 ax1.patch.set_alpha(0.0)
                 st.pyplot(fig1)
 
-
+        st.write("---")
 
     with class_tab:
-        
-        st.write("For Classification we are using Fashion-MNIST dataset. Fashion-MNIST is a dataset of Zalando's article images. Zalando intends Fashion-MNIST to serve as a direct drop-in for benchmarking machine learning algorithms. Each example is assigned to one of the following labels: 0 T-shirt/top, 1 Trouser,2 Pullover, 3 Dress, 4 Coat, 5 Sandal, 6 Shirt, 7 Sneaker, 8 Bag, 9 Ankle boot") 
 
-        st.write("---")
+        st.write("", "", "")
+        
+        st.write("For Classification we are using Fashion-MNIST dataset. Fashion-MNIST is a dataset of Zalando's article images. Zalando intends Fashion-MNIST to serve as a direct drop-in for benchmarking machine learning algorithms. Each example is assigned to one of the following labels: 0 T-shirt/top, 1 Trouser,2 Pullover, 3 Dress, 4 Coat, 5 Sandal, 6 Shirt, 7 Sneaker, 8 Bag, 9 Ankle boot")
 
         st.write("Lets assume you have a model trained for Object detection but you cant just rely on the softmax output for that model. This is where conformal prediction comes into play. We can use the alpha value to pick up a threshold. When softmax scores go beyond this threshold score then onlt that label is considered as the predicted class.") 
 
@@ -133,7 +134,7 @@ if __name__ == '__main__':
 
         with st.container():
             
-            c1,col1, col2, col3,c2 = st.columns([0.2,0.3,0.3,0.3,0.2])
+            c1,col1, col2, col3,c2 = st.columns([0.3,0.3,0.3,0.3,0.3])
 
             with col1:
                 fig1, ax1 = plt.figure(), plt.gca()
@@ -146,8 +147,11 @@ if __name__ == '__main__':
                 ax1.set_yticks([])
                 st.pyplot(fig1)
 
+                out_pred = pred[0]>sigma
+                c = ['C2' if pred==1 else 'C0' for pred in out_pred]
+
                 fig1, ax1 = plt.figure(), plt.gca()
-                ax1.bar(range(10),pred[0])
+                ax1.bar(range(10),pred[0],color=c)
                 ax1.axhline(y=sigma,linestyle='dashed',c='r')
                 ax1.set_xlabel("Classe Labels")
                 ax1.set_ylabel("SoftMax Probabilities")
@@ -155,7 +159,8 @@ if __name__ == '__main__':
                 ax1.set_xticks([i for i in range(10)])
                 st.pyplot(fig1)
 
-                out_labels = labels[pred[0]>sigma]
+                out_labels = labels[out_pred]
+                
                 if len(out_labels)==0:
                     out_labels = ["None"]
                 out_labels = ",".join(out_labels)
@@ -174,8 +179,11 @@ if __name__ == '__main__':
                 ax1.set_yticks([])
                 st.pyplot(fig1)
 
+                out_pred = pred[1]>sigma
+                c = ['C2' if pred==1 else 'C0' for pred in out_pred]
+
                 fig1, ax1 = plt.figure(), plt.gca()
-                ax1.bar(range(10),pred[1])
+                ax1.bar(range(10),pred[1],color = c)
                 ax1.axhline(y=sigma,linestyle='dashed',c='r')
                 ax1.set_xlabel("Classe Labels")
                 ax1.set_ylabel("SoftMax Probabilities")
@@ -183,7 +191,7 @@ if __name__ == '__main__':
                 ax1.set_xticks([i for i in range(10)])
                 st.pyplot(fig1)
 
-                out_labels = labels[pred[1]>sigma]
+                out_labels = labels[out_pred]
                 if len(out_labels)==0:
                     out_labels = ["None"]
                 out_labels = ",".join(out_labels)
@@ -201,8 +209,11 @@ if __name__ == '__main__':
                 ax1.set_yticks([])
                 st.pyplot(fig1)
 
+                out_pred = pred[2]>sigma
+                c = ['C2' if pred==1 else 'C0' for pred in out_pred]
+
                 fig1, ax1 = plt.figure(), plt.gca()
-                ax1.bar(range(10),pred[2])
+                ax1.bar(range(10),pred[2],color=c)
                 ax1.axhline(y=sigma,linestyle='dashed',c='r')
                 ax1.set_xlabel("Classe Labels")
                 ax1.set_ylabel("SoftMax Probabilities")
@@ -210,13 +221,14 @@ if __name__ == '__main__':
                 ax1.set_xticks([i for i in range(10)])
                 st.pyplot(fig1)
 
-                out_labels = labels[pred[2]>sigma]
+                out_labels = labels[out_pred]
                 if len(out_labels)==0:
                     out_labels = ["None"]
                 out_labels = ",".join(out_labels)
                 st.write("Ouput Labels : "+out_labels)
                 st.write("True Label : Bag")
-
+    
+        st.write("---")