Update app.py

app.py

@@ -1,43 +1,54 @@
-import requests
 import tensorflow as tf
-import gradio as gr
-from PIL import Image
+import efficientnet.tfkeras as efn
+from tensorflow.keras.layers import Input, GlobalAveragePooling2D, Dense
 import numpy as np
+import gradio as gr
+
+# Dimensões da imagem
+IMG_HEIGHT = 224
+IMG_WIDTH = 224
+
+# Função para construir o modelo
+def build_model(img_height, img_width, n):
+    inp = 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)
+    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)
+    model.compile(optimizer=opt, loss=loss, metrics=['accuracy'])
+    return model
+
+# Carregue o modelo treinado
+loaded_model = build_model(IMG_HEIGHT, IMG_WIDTH, 3)
+loaded_model.load_weights('modelo_treinado.h5')
+
+# Função para fazer previsões usando o modelo treinado
+def predict_image(input_image):
+    # Realize o pré-processamento na imagem de entrada, se necessário
+    # input_image = preprocess_image(input_image)
+
+    # Faça uma previsão usando o modelo carregado
+    input_image = tf.image.resize(input_image, (IMG_HEIGHT, IMG_WIDTH))
+    input_image = tf.expand_dims(input_image, axis=0)
+    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]])
+    return prediction
+
+# Crie uma interface Gradio para fazer previsões
+iface = gr.Interface(
+    fn=predict_image,
+    inputs="image",
+    outputs="text",
+    interpretation="default"
+)
 
-# Load your custom TensorFlow model. Update 'modelo_treinado.h5' with the path to your model.
-tf_model_path = 'modelo_treinado.h5'
-tf_model = tf.keras.models.load_model(tf_model_path)
-
-# Define your class labels.
-class_labels = ["Normal", "Cataract"]
-
-def preprocess_image(image):
-    # Resize the image to the input size required by the model (e.g., 224x224).
-    image = image.resize((224, 224))
-    # Convert the PIL image to a NumPy array and normalize pixel values.
-    image = np.array(image) / 255.0
-    # Add a batch dimension to the image.
-    image = np.expand_dims(image, axis=0)
-    return image
-
-def predict(inp):
-    # Preprocess the input image.
-    inp = preprocess_image(inp)
-    # Make predictions using your custom TensorFlow model.
-    predictions = tf_model.predict(inp)
-    # Get the class label with the highest confidence.
-    predicted_class = class_labels[np.argmax(predictions)]
-    # Get the confidence score of the predicted class.
-    confidence = float(predictions[0][np.argmax(predictions)])
-    
-    # Create a dictionary with the predicted class and its confidence.
-    result = {predicted_class: confidence}
-    
-    return result
-
-# Create a Gradio interface.
-gr.Interface(
-    fn=predict,
-    inputs=gr.inputs.Image(type="pil"),
-    outputs=gr.outputs.Label(num_top_classes=1)
-).launch()
+# Execute a interface Gradio
+iface.launch()