made changes in ui and added barplot

app.py

@@ -5,6 +5,7 @@ from tensorflow.keras.layers import Dense, Flatten
 import matplotlib.pyplot as plt
 import gradio as gr
 import numpy as np
+import pandas as pd
 #%matplotlib inline
 
 
@@ -15,46 +16,195 @@ print(X_train.shape)
 
 print(y_train)
 
-for i in range(9):
-    plt.subplot(330+1+i)
-    plt.imshow(X_train[i])
-    plt.show()
+# for i in range(9):
+#     plt.subplot(330+1+i)
+#     plt.imshow(X_train[i])
+#     plt.show()
 
 X_train=X_train/255.0
 X_test=X_test/255.0
 
-model=tf.keras.models.Sequential([Flatten(input_shape=(28,28)),
+# model=tf.keras.models.Sequential([Flatten(input_shape=(28,28)),
                                         
-                                        Dense(650,activation='relu'),
+#                                         Dense(650,activation='relu'),
                                         
-                                        Dense(450,activation='relu'),
+#                                         Dense(450,activation='relu'),
                                         
-                                        Dense(250,activation='relu'),
+#                                         Dense(250,activation='relu'),
                                         
-                                        Dense(150,activation='relu'),
+#                                         Dense(150,activation='relu'),
                                         
-                                        Dense(10,activation=tf.nn.softmax)])
+#                                         Dense(10,activation=tf.nn.softmax)])
 
-model.compile(optimizer='adam',
-              loss='sparse_categorical_crossentropy',
-              metrics=['accuracy'])
-model.fit(X_train,y_train, epochs=10)
-model.save("keras_digit_temp.h5")
-test=X_test[0].reshape(-1,28,28)
-predicted=model.predict(test)
-print(predicted)
+# model.compile(optimizer='adam',
+#               loss='sparse_categorical_crossentropy',
+#               metrics=['accuracy'])
+# model.fit(X_train,y_train, epochs=10)
+# model.save("keras_digit_temp.h5")
+# test=X_test[0].reshape(-1,28,28)
+# predicted=model.predict(test)
+# print(predicted)
 
-def prdict_digit(img):
-    loaded_model = keras.models.load_model('keras_digit_temp.h5')
-    img_3d=img.reshape(-1,28,28)
-    img_resized=img_3d/255.0
-    pred_prob=loaded_model.predict(img_resized)
-    predicted_val=np.argmax(pred_prob)
-    return int(predicted_val)
+def predict_digit(img):
+    if img is not None:
 
-iface=gr.Interface(prdict_digit, inputs='sketchpad', outputs='label').launch()
+        loaded_model = keras.models.load_model('keras_digit_temp.h5')
+    
+        
+        img_3d=img.reshape(-1,28,28)
+        img_resized=img_3d/255.0
+        pred_prob=loaded_model.predict(img_resized)
+    
+        pred_prob=pred_prob*100
+
+        print((pred_prob))
+        # prob0= 100*pred_prob[0]
+        # prob1= 100*pred_prob[1]
+        # prob2= 100*pred_prob[2]
+        # prob3= 100*pred_prob[3]
+        # prob4= 100*pred_prob[4]
+        # prob5= 100*pred_prob[5]
+        # prob6= 100*pred_prob[6]
+        # prob7= 100*pred_prob[7]
+        # prob8= 100*pred_prob[8]
+        # prob9= 100*pred_prob[9]
+
+        # print(prob2) 
+
+        simple = pd.DataFrame(
+        {
+        "a": ["0", "1", "2", "3", "4", "5", "6", "7", "8","9"],
+        "b": pred_prob[0], #[28, 55, 43, 91, 81, 53, 19, 87, 52,80],
+        }
+        )
+
+        predicted_val=np.argmax(pred_prob)
+        return int(predicted_val), gr.BarPlot.update(
+            simple,
+            x="a",
+            y="b",
+            x_title="Digits",
+            y_title="Identification Probabilities",
+            title="Identification Probability",
+            tooltip=["a", "b"],
+            vertical=False,
+            y_lim=[0, 100],
+        )
+        
+    else:
+        return " "
+        
+
+# iface=gr.Interface(prdict_digit, inputs='sketchpad', outputs=['label', gr.Slider(0,100, label='Probably 0'), gr.Slider(0,100, label='Probably 1')] ).launch()
+
+# iface.launch(debug='true')
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown("Digit Identify", elem_id='title_head')
+            gr.Markdown("By Alok")
+    with gr.Row():
+        with gr.Column():
+            with gr.Row():
+                skch=gr.Sketchpad()
+            with gr.Row():
+                with gr.Column():
+                    clear=gr.ClearButton(skch)
+                with gr.Column():
+                    btn=gr.Button("Identify")
+                    
+        with gr.Column():
+            gr.Markdown("Identified digit")
+            label=gr.Label("")
+            gr.Markdown("Other possible values")
+            bar = gr.BarPlot()
+    btn.click(predict_digit,inputs=skch,outputs=[label,bar])
+
+           
+        
+    
+demo.launch()
+    
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+# import tensorflow as tf
+# from tensorflow import keras
+# from tensorflow.keras import Sequential
+# from tensorflow.keras.layers import Dense, Flatten
+# import matplotlib.pyplot as plt
+# import gradio as gr
+# import numpy as np
+# %matplotlib inline
+
+
+# objt=tf.keras.datasets.mnist
+# (X_train, y_train), (X_test,y_test)=objt.load_data()
+
+# print(X_train.shape)
+
+# print(y_train)
+
+# for i in range(9):
+#     plt.subplot(330+1+i)
+#     plt.imshow(X_train[i])
+#     plt.show()
+
+# X_train=X_train/255.0
+# X_test=X_test/255.0
+
+# model=tf.keras.models.Sequential([Flatten(input_shape=(28,28)),
+                                        
+#                                         Dense(650,activation='relu'),
+                                        
+#                                         Dense(450,activation='relu'),
+                                        
+#                                         Dense(250,activation='relu'),
+                                        
+#                                         Dense(150,activation='relu'),
+                                        
+#                                         Dense(10,activation=tf.nn.softmax)])
+
+# model.compile(optimizer='adam',
+#               loss='sparse_categorical_crossentropy',
+#               metrics=['accuracy'])
+# model.fit(X_train,y_train, epochs=10)
+# model.save("keras_digit_temp.h5")
+# test=X_test[0].reshape(-1,28,28)
+# predicted=model.predict(test)
+# print(predicted)
+
+# def prdict_digit(img):
+#     loaded_model = keras.models.load_model('keras_digit_temp.h5')
+#     img_3d=img.reshape(-1,28,28)
+#     img_resized=img_3d/255.0
+#     pred_prob=loaded_model.predict(img_resized)
+#     predicted_val=np.argmax(pred_prob)
+#     return int(predicted_val)
+
+# iface=gr.Interface(prdict_digit, inputs='sketchpad', outputs='label').launch()
 
-iface.launch(debug='true')
+# iface.launch(debug='true')
     
 
 

flagged/log.csv

@@ -0,0 +1,2 @@
+img,output,flag,username,timestamp
+D:\Projects\alok-digit-identify\flagged\img\2230c2787153e177b50659d8d00542de6771f0ff\tmptde5e2ko.png,D:\Projects\alok-digit-identify\flagged\output\tmp11i68aun.json,,,2023-09-11 00:52:06.273490

flagged/output/tmp11i68aun.json

@@ -0,0 +1 @@
+{"label": "2"}

keras_digit_temp.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:381032914c5af60afcaa0aaf305475fd6d9228ef6496bb56c3153913b1974d5c
+size 11511128