Update app.py

app.py

@@ -5,7 +5,7 @@ Created on Fri Nov 25 21:37:33 2022
 @author: Bharathraj C L
 """
 
-import deepdoctection
+
 import streamlit as st
 import mmcv
 import os
@@ -17,21 +17,35 @@ st.set_option('deprecation.showPyplotGlobalUse', False)
 
 st.title("Table Detection from Images")
 
-config_file = 'cascade_mask_rcnn_hrnetv2p_w32_20e.py'
-checkpoint_file = 'epoch_36.pth'
-model = init_detector(config_file, checkpoint_file, device='cuda:0')
-uploaded_file = st.file_uploader("Choose an image...", type="jpg")
-if uploaded_file is not None:
-    image = Image.open(uploaded_file)
-    st.image(image, caption='Uploaded Image.', use_column_width=True)
-    directory = "tempDir"
-    path = os.path.join(os.getcwd(), directory)
-    p = Path(path)
-    if not p.exists():
-        os.mkdir(p)
-    with open(os.path.join(path, uploaded_file.name),"wb") as f:
-        f.write(uploaded_file.getbuffer()) 
-    file_loc = os.path.join(path, uploaded_file.name)
-    result = inference_detector(model, file_loc)
-    st.pyplot(show_result_pyplot(file_loc, result,('Bordered', 'cell', 'Borderless'), score_thr=0.85))
 
+@st.cache
+def load_model():
+    # Make sure to pass `pretrained` as `True` to use the pretrained weights:
+    #new_model = tf.keras.models.load_model('mobilenetv2_100noise.h5')
+    config_file = 'cascade_mask_rcnn_hrnetv2p_w32_20e.py'
+    checkpoint_file = 'epoch_36.pth'
+    model = init_detector(config_file, checkpoint_file, device='cuda:0')
+    return new_model
+
+def main():
+    uploaded_file = st.file_uploader("Choose an image...", type="jpg")
+
+    model = load_model()
+    if uploaded_file is not None:
+        image = Image.open(uploaded_file)
+        st.image(image, caption='Uploaded Image.', use_column_width=True)
+        directory = "tempDir"
+        path = os.path.join(os.getcwd(), directory)
+        p = Path(path)
+        if not p.exists():
+            os.mkdir(p)
+        with open(os.path.join(path, uploaded_file.name),"wb") as f:
+            f.write(uploaded_file.getbuffer()) 
+        file_loc = os.path.join(path, uploaded_file.name)
+        result = inference_detector(model, file_loc)
+        st.pyplot(show_result_pyplot(file_loc, result,('Bordered', 'cell', 'Borderless'), score_thr=0.85))
+
+
+
+if __name__ == '__main__':
+    main()