Upload 3 files

app.py

@@ -0,0 +1,39 @@
+import streamlit as st
+from detection import *
+
+def detect_on_image(x):
+    detector = Detector(model_type=x)
+    image_file = st.file_uploader("Upload An Image",type=['png','jpeg','jpg'])
+    if image_file is not None:
+        file_details = {"FileName":image_file.name,"FileType":image_file.type}
+        st.write(file_details)
+        img = Image.open(image_file)
+        st.image(img, caption='Uploaded Image.')
+        with open(image_file.name,mode = "wb") as f: 
+            f.write(image_file.getbuffer())         
+        st.success("Saved File")
+        detector.onImage(image_file.name)
+        img_ = Image.open("result.jpg")
+        st.image(img_, caption='Proccesed Image.')
+
+
+def main():
+    with st.expander("About the App"):
+        st.markdown( '<p style="font-size: 30px;"><strong>Welcome to my Instance Segmentation App!</strong></p>', unsafe_allow_html= True)
+        
+
+    option = st.selectbox(
+     'What Type of File do you want to work with?',
+     ('Images', ' '))
+
+    
+    if option == "Images":
+        st.title('Instance Segmentation for Images')
+        st.subheader("""
+    This takes an image as an input, and provides image with bounding box and mask as an output.
+    """)
+        detect_on_image('object_detection')
+
+
+if __name__ == '__main__':
+	main()

detection.py

@@ -0,0 +1,46 @@
+from detectron2.engine import DefaultPredictor
+import detectron2
+from detectron2.utils.logger import setup_logger
+setup_logger()
+from detectron2.utils.video_visualizer import VideoVisualizer
+from detectron2.config import get_cfg
+from detectron2.data import MetadataCatalog
+from detectron2.utils.visualizer import ColorMode, Visualizer
+from detectron2 import model_zoo
+from detectron2.data.datasets import register_coco_instances
+from PIL import Image 
+import PIL 
+import cv2
+import numpy as np
+import matplotlib.pyplot as plt
+
+
+class Detector:
+
+    def __init__(self, model_type = "object_detection"):
+        self.cfg=get_cfg()
+        self.cfg.merge_from_file(model_zoo.get_config_file("COCO-Detection/faster_rcnn_R_50_FPN_1x.yaml")) # load  the default configuration
+        self.cfg.MODEL.WEIGHTS = 'model_final.pth'
+        self.cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.8
+        self.cfg.MODEL.ROI_HEADS.NUM_CLASSES = 2
+        self.cfg.MODEL.DEVICE="cpu"
+
+        dataset_name="guns"
+        classes=['guns','Gun']
+        MetadataCatalog.get(dataset_name).set(thing_classes=classes)
+
+        self.predictor = DefaultPredictor(self.cfg)
+
+    def onImage(self, imagePath):
+        image = cv2.imread(imagePath)
+        predictions = self.predictor(image)
+        dataset_name="guns"
+
+        viz = Visualizer(image,MetadataCatalog.get(dataset_name),scale=1)
+        
+        output = viz.draw_instance_predictions(predictions['instances'].to('cpu'))
+        filename = 'result.jpg'
+        cv2.imwrite(filename, output.get_image()[:,:,::-1])
+        # cv2.waitKey(0)
+        # cv2.destroyAllWindows()
+

model_final.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7689e1052d4376881a28adcc8fc4a0ae135546d8f92e1078fbe58678d8e3aa1a
+size 330065763