Update app.py

app.py

@@ -36,7 +36,7 @@ enhancement_type = st.sidebar.selectbox(
 H = 224
 W = 224
 
-@st.cache(allow_output_mutation=True)
+@st.cache_resource(allow_output_mutation=True)
 def load_model():
     model = tf.keras.models.load_model("model-detection.h5", compile=False)
     model.compile(
@@ -76,7 +76,7 @@ model = load_model()
 #     st.image(image, caption='Uploaded Image.', use_column_width=True)
 
 
-@st.cache(allow_output_mutation=True)
+@st.cache_resource(allow_output_mutation=True)
 def load_gradcam_model():
     model = keras.models.load_model('./model_renamed.h5', compile=False)
     model.compile(
@@ -198,7 +198,7 @@ def upload_folder_images(original_image_path, enhanced_image_path):
     upload_to_gcs(enhanced_dicom_bytes, folder_name + '/' + enhancement_name + '.dcm', content_type='application/dicom')
 
 
-def get_mean_std_per_batch(image_path, df, H=320, W=320):
+def get_mean_std_per_batch(image_path, H=320, W=320):
     sample_data = []
     for idx, img in enumerate(df.sample(100)["Image Index"].values):
         # path = image_dir + img
@@ -209,9 +209,8 @@ def get_mean_std_per_batch(image_path, df, H=320, W=320):
     std = np.std(sample_data[0])
     return mean, std
 
-def load_image(img_path, df, preprocess=True, height=320, width=320):
-    df_xray = ('./xray_dataset.csv')
-    mean, std = get_mean_std_per_batch(img_path, df_xray, height, width)
+def load_image(img_path, preprocess=True, height=320, width=320):
+    mean, std = get_mean_std_per_batch(img_path, height, width)
     x = keras.utils.load_img(img_path, target_size=(height, width))
     x = keras.utils.img_to_array(x)
     if preprocess:
@@ -251,7 +250,7 @@ def grad_cam(input_model, img_array, cls, layer_name):
 
 
 # Compute Grad-CAM
-def compute_gradcam(model_gradcam, img_path, df, layer_name='bn'):
+def compute_gradcam(model_gradcam, img_path, layer_name='bn'):
     # base_model  = keras.applications.DenseNet121(weights = './densenet.hdf5', include_top = False)
     # x = base_model.output
     # x = keras.layers.GlobalAveragePooling2D()(x)
@@ -264,9 +263,7 @@ def compute_gradcam(model_gradcam, img_path, df, layer_name='bn'):
 
     # Now use this modified model in your application
     model_gradcam = load_gradcam_model()
-    df_xray = ('./xray_dataset.csv')
-    
-    preprocessed_input = load_image(img_path,df)
+    preprocessed_input = load_image(img_path)
     predictions = model_gradcam.predict(preprocessed_input)
 
     original_image = load_image(img_path, preprocess=False)
@@ -520,7 +517,6 @@ if uploaded_file is not None:
             # Compute and show Grad-CAM
             st.write("Generating Grad-CAM visualizations")
             try:
-                df_xray = ('./xray_dataset.csv')
-                compute_gradcam(model_gradcam, uploaded_file, df_xray)
+                compute_gradcam(model_gradcam, uploaded_file)
             except Exception as e:
                 st.error(f"Error generating Grad-CAM: {e}")