Update app.py

app.py

@@ -1,7 +1,5 @@
 import tensorflow as tf
 import efficientnet.tfkeras as efn
-from tensorflow.keras.layers import Input, GlobalAveragePooling2D, Dense
-import numpy as np
 import gradio as gr
 
 # Dimensões da imagem
@@ -10,15 +8,15 @@ IMG_WIDTH = 224
 
 # Função para construir o modelo
 def build_model(img_height, img_width, n):
-    inp = Input(shape=(img_height, img_width, n))
+    inp = tf.keras.layers.Input(shape=(img_height, img_width, n))
     efnet = efn.EfficientNetB0(
         input_shape=(img_height, img_width, n),
         weights='imagenet',
         include_top=False
     )
     x = efnet(inp)
-    x = GlobalAveragePooling2D()(x)
-    x = Dense(2, activation='softmax')(x)
+    x = tf.keras.layers.GlobalAveragePooling2D()(x)
+    x = tf.keras.layers.Dense(2, activation='softmax')(x)
     model = tf.keras.Model(inputs=inp, outputs=x)
     opt = tf.keras.optimizers.Adam(learning_rate=0.000003)
     loss = tf.keras.losses.CategoricalCrossentropy(label_smoothing=0.01)
@@ -42,7 +40,7 @@ def preprocess_image(input_image):
     return input_image
 
 # Função para fazer previsões usando o modelo treinado
-def predict_image(input_image):
+def predict(input_image):
     # Realize o pré-processamento na imagem de entrada
     input_image = preprocess_image(input_image)
 
@@ -51,22 +49,19 @@ def predict_image(input_image):
     prediction = loaded_model.predict(input_image)
 
     # A saída será uma matriz de previsões (no caso de classificação de duas classes, será algo como [[probabilidade_classe_0, probabilidade_classe_1]])
-    class_names = ["Normal", "Cataract"]
-    probabilities = prediction[0]
+    class_names = ["Not Hot Dog", "Hot Dog"]
 
-    # Use o Gradio para criar um gráfico de barras horizontais
-    bars = []
-    for class_name, probability in zip(class_names, probabilities):
-        bars.append(gr.outputs.Bar(label=class_name, confidence=probability))
+    # Determine a classe mais provável
+    predicted_class = class_names[np.argmax(prediction)]
 
-    return bars
+    return predicted_class
 
 # Crie uma interface Gradio para fazer previsões
 iface = gr.Interface(
-    fn=predict_image,
-    inputs="image",
-    outputs="text",
-    interpretation="default"
+    predict,
+    inputs=gr.inputs.Image(label="Upload hot dog candidate", type="file"),
+    outputs=gr.outputs.Label(num_top_classes=2),
+    title="Hot Dog? Or Not?",
 )
 
 # Execute a interface Gradio