revert back to keras 2

app.py

@@ -1,26 +1,27 @@
 import gradio as gr
 import numpy as np
 import tensorflow as tf
-import keras
 
 def softmax(vector):
     e = np.exp(vector)
     return e / e.sum()
 
 
-def image_to_output(input_img):
-    # Preprocess the image as before
-    img2 = tf.image.resize(tf.cast([input_img], tf.float32)/255., [224, 224])
-    
-    # Run inference
-    output = infer(tf.constant(img2))
+def image_to_output (input_img):
+    gr_img = []
+    gr_img.append(input_img)
+    img2 = tf.image.resize(tf.cast(gr_img, tf.float32)/255. , [224, 224])
 
-    print(output)
-    
-    # Process the output
-    prediction = output['output_0'].numpy().flatten()
+    # print(img2)
+
+    x_test = np.asarray(img2)
+
+    prediction = model2.predict(x_test,batch_size=1).flatten()
     prediction = softmax(prediction)
+
     confidences = {labels[i]: float(prediction[i]) for i in range(102)}
+    # confidences = {labels[i]:float(top[i]) for i in range(num_predictions)}
+
     return confidences
 
 # Download the model checkpoint
@@ -47,10 +48,8 @@ for item in [
     
 
 # Load the SavedModel
-loaded = tf.saved_model.load(pretrained_repo)
+model2=tf.keras.models.load_model(pretrained_repo)
 
-# Get the inference function
-infer = loaded.signatures["serving_default"]
 
 # Read the labels
 with open('flower_names.txt') as f: