menambahkan keras load model from jso

Model_Load.py

@@ -1,4 +1,6 @@
+import keras
 from keras.models import model_from_json
+print("keras versio:", keras.__version__)
 
 def load_model_from_files(json_path, weights_path):
     with open(json_path, "r") as json_file:

app.py

@@ -1,7 +1,7 @@
 import os
-# Suppress info logs from TensorFlow (Point 1)
-os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' 
-
+os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
+import keras
+print("keras versio:", keras.__version__)
 import gradio as gr
 import numpy as np
 from keras.preprocessing import image
@@ -12,12 +12,21 @@ from fastapi import FastAPI, File, UploadFile
 from fastapi.responses import JSONResponse
 from io import BytesIO
 from PIL import Image
-import uvicorn
-from fastapi.middleware.cors import CORSMiddleware
+from tensorflow.keras.models import model_from_json
 import tensorflow as tf
-tf.config.set_visible_devices([], 'GPU')
 import logging
+from fastapi.middleware.cors import CORSMiddleware
+from keras.models import model_from_json
 
+def load_model_from_files(json_path, weights_path):
+    with open(json_path, "r") as json_file:
+        loaded_model_json = json_file.read()
+    model = model_from_json(loaded_model_json) 
+    model.load_weights(weights_path)
+    return model
+
+# Nonaktifkan GPU (jika tidak digunakan)
+tf.config.set_visible_devices([], 'GPU')
 
 # Inisialisasi logger
 logging.basicConfig(level=logging.INFO)
@@ -66,48 +75,48 @@ def classify_image(img):
 
     return label_output, deskripsi, lokasi, akurasi
 
-
-# FastAPI instance
-app = FastAPI()
-
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["http://localhost:9000"],  # atau sesuaikan dengan asal frontend
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
-@app.post("/api/predict")
-async def predict(file: UploadFile = File(...)):
-    contents = await file.read()
-    img = Image.open(BytesIO(contents)).convert("RGB")
-    label_output, deskripsi, lokasi, akurasi = classify_image(img)
-    return JSONResponse(content={
-        "label_output": label_output,
-        "deskripsi": deskripsi,
-        "lokasi" : lokasi,
-        "confidence": akurasi
-    })
-
-
-# Gradio antarmuka (opsional tetap ditampilkan)
-gradio_app = gr.Interface(
-    fn=classify_image,
-    inputs=gr.Image(type="pil", label="Upload Gambar"),
-    outputs=[
-        gr.Textbox(label="Output Klasifikasi"),
-        gr.Textbox(label="Deskripsi Lengkap", lines=20, max_lines=50),
-        gr.HTML(label="Link Lokasi"),
-    ],
-    flagging_mode="never",
-    title="Klasifikasi Gambar",
-    description="Upload gambar, sistem akan mengklasifikasikan dan memberikan deskripsi mengenai gambar tersebut."
-)
-
-# Mount Gradio ke FastAPI
-app = gr.mount_gradio_app(app, gradio_app, path="/gradio")
-
-# Jalankan app
+# Fungsi untuk membuat FastAPI app
+def create_app():
+    app = FastAPI()
+
+    app.add_middleware(
+        CORSMiddleware,
+        allow_origins=["http://localhost:9000"],  # atau sesuaikan dengan asal frontend
+        allow_credentials=True,
+        allow_methods=["*"],
+        allow_headers=["*"],
+    )
+
+    @app.post("/api/predict")
+    async def predict(file: UploadFile = File(...)):
+        contents = await file.read()
+        img = Image.open(BytesIO(contents)).convert("RGB")
+        label_output, deskripsi, lokasi, akurasi = classify_image(img)
+        return JSONResponse(content={
+            "label_output": label_output,
+            "deskripsi": deskripsi,
+            "lokasi": lokasi,
+            "confidence": akurasi
+        })
+
+    gradio_app = gr.Interface(
+        fn=classify_image,
+        inputs=gr.Image(type="pil", label="Upload Gambar"),
+        outputs=[
+            gr.Textbox(label="Output Klasifikasi"),
+            gr.Textbox(label="Deskripsi Lengkap", lines=20, max_lines=50),
+            gr.HTML(label="Link Lokasi"),
+        ],
+        flagging_mode="never",
+        title="Klasifikasi Gambar",
+        description="Upload gambar, sistem akan mengklasifikasikan dan memberikan deskripsi mengenai gambar tersebut."
+    )
+
+    app = gr.mount_gradio_app(app, gradio_app, path="/gradio")
+    return app
+
+# Hanya jalan jika dijalankan langsung, bukan import
 if __name__ == "__main__":
-    uvicorn.run(app, host="127.0.0.1", port=8000)
+    import uvicorn
+    app = create_app()
+    uvicorn.run(app, host="127.0.0.1", port=8000)