Update app.py

app.py

@@ -1,20 +1,45 @@
-from fastapi import FastAPI, File, UploadFile
-from predict_glaucoma import predict_glaucoma
+import math
 
-import tempfile
+import gradio as gr
+import tensorflow as tf
 
-app = FastAPI()
+configs = [
+    {
+        "model": "my_model_2.h5", "size": 512
+    },
+    {
+        "model": "my_model.h5", "size": 224
+    },
+]
 
-@app.post("/predict/")
-async def predict(file: UploadFile = File(...)):
-    model_path = "final_model.h5"
+config = configs[0]
 
-    # Salve a imagem em um arquivo temporário
-    with tempfile.NamedTemporaryFile(suffix=".jpg") as tmp_file:
-        tmp_file.write(await file.read())
-        tmp_file.flush()
+new_model = tf.keras.models.load_model(config["model"])
+
+def classify_image(inp):
+    inp = inp.reshape((-1, config["size"], config["size"], 3))
+    prediction = new_model.predict(inp).flatten()
+    print(prediction)
+    if len(prediction) > 1:
+        probability = 100 * math.exp(prediction[0]) / (math.exp(prediction[0]) + math.exp(prediction[1]))
+    else:
+        probability = round(100. / (1 + math.exp(-prediction[0])), 2)
+    if probability > 45:
+        return "Glaucoma", probability
+    if probability > 25:
+        return "Unclear", probability
+    return "Not glaucoma", probability
+
+
+gr.Interface(
+    fn=classify_image, 
+    inputs=gr.inputs.Image(shape=(config["size"], config["size"])),
+    outputs=[
+    gr.outputs.Textbox(label="Label"),
+    gr.outputs.Textbox(label="Glaucoma probability (0 - 100)"),
+    ],
+    examples=["001.jpg", "002.jpg", "225.jpg"],
+    flagging_options=["Correct label", "Incorrect label"],
+    allow_flagging="manual",
+).launch()
 
-        # Faça a previsão usando a função 'predict_glaucoma'
-        prediction = predict_glaucoma(tmp_file.name, model_path)
-    
-    return {"probabilidade_de_glaucoma": prediction * 100}