Create app.py

app.py

@@ -0,0 +1,45 @@
+import gradio as gr
+
+import tensorflow as tf
+from matplotlib import pyplot as plt
+import numpy as np
+
+num_objects =  tf.keras.datasets.mnist
+(training_images, training_labels), (test_images, test_labels) = num_objects.load_data()
+
+for i in range(9):
+ #define subplot
+ plt.subplot(330 + 1 + i)
+ #plot of raw pixel data
+ plt.imshow(training_images[i])
+ 
+ training_images  = training_images / 255.0
+test_images = test_images / 255.0
+
+from tensorflow.keras.layers import Flatten, Dense     
+model = tf.keras.models.Sequential([Flatten(input_shape=(28,28)), 
+                                    Dense(256, activation='relu'),
+                                    Dense(256, activation='relu'),
+                                    Dense(128, activation='relu'), 
+                                    Dense(10, activation=tf.nn.softmax)])
+
+model.compile(optimizer = 'adam',
+              loss = 'sparse_categorical_crossentropy',
+              metrics=['accuracy'])
+
+model.fit(training_images, training_labels, epochs=10)  #how many times u go through the dataset
+
+test=test_images[0].reshape(-1,28,28)
+pred=model.predict(test)
+print(pred)
+
+def predict_image(img):
+  img_3d=img.reshape(-1,28,28)
+  im_resize=img_3d/255.0
+  prediction=model.predict(im_resize)
+  pred=np.argmax(prediction)
+  return pred
+  
+  iface = gr.Interface(predict_image, inputs="sketchpad", outputs="label")
+  
+  iface.launch(debug='True')