Upload 19 files

FRCNN_MODEL_3Classes_100Epochs.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea6c7bed92de7ef93e4c81ce566b87d246172fb3a643154580899b5031944e06
+size 76062139

app.py

@@ -0,0 +1,133 @@
+import streamlit as st
+import torch
+import torchvision
+import torchvision.transforms as transforms
+from torchvision import datasets, models
+from torchvision.transforms import functional as FT
+from torchvision import transforms as T
+from torch import nn, optim
+from torch.nn import functional as F
+from torch.utils.data import DataLoader, sampler, random_split, Dataset
+from torchvision.models.detection.faster_rcnn import FastRCNNPredictor
+from torchvision.transforms import ToTensor
+from PIL import Image, ImageDraw
+from pycocotools.coco import COCO
+import cv2
+import numpy as np
+import pandas as pd
+import os
+
+
+import tempfile
+from tempfile import NamedTemporaryFile
+
+dataset_path = "Dataset"
+
+#load classes
+coco = COCO(os.path.join(dataset_path, "train", "_annotations.coco.json"))
+categories = coco.cats
+n_classes = len(categories.keys())
+
+# load the faster rcnn model
+modeltest = models.detection.fasterrcnn_mobilenet_v3_large_fpn(num_classes=4)
+in_features = modeltest.roi_heads.box_predictor.cls_score.in_features # we need to change the head
+modeltest.roi_heads.box_predictor = models.detection.faster_rcnn.FastRCNNPredictor(in_features, n_classes)
+
+# Load the saved parameters into the model
+modeltest.load_state_dict(torch.load("FRCNN_MODEL_3Classes_100Epochs.pth"))
+
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+modeltest.to(device)
+
+# Number of classes
+classes = ['pole', 'cross_arm', 'pole', 'tag']
+
+st.title(""" Object Detection Using Faster-RCNN For Electrical Domain """)
+
+# st.subheader("Prediction of Object Detection")
+
+images = ["img16.jpg","img1.jpg","img2.jpg","img3.jpg","img4.jpg","img5.jpg","img6.jpg","img8.jpg",
+          "img10.jpg","img11.jpg","img12.jpg","img13.jpg","img14.jpg","img15.jpg","img9.jpg"]
+
+with st.sidebar:
+    st.write("Choose an Image from Sample Images ")
+    st.image(images)
+
+# with st.sidebar:
+#     st.write("Choose an Image From The DropDown")
+#     selected_image = st.selectbox("Select an image", images)
+
+    
+# with st.sidebar:
+#     st.write("Choose an Image")
+#     for image in images:
+#         with Image.open(image) as img:
+#             st.image(img, width=100, quality=90)   # quality parameter is not there in image, it will give error
+    
+# with st.sidebar:
+#     st.write("Choose an Image")
+#     st.image(images,width=100)
+    
+
+# define the function to perform object detection on an image
+def detect_objects(image_path):
+    # load the image
+    image = Image.open(image_path).convert('RGB')
+    
+    # convert the image to a tensor
+    image_tensor = ToTensor()(image).to(device)
+    
+    # run the image through the model to get the predictions
+    modeltest.eval()
+    with torch.no_grad():
+        predictions = modeltest([image_tensor])
+
+    # filter out the predictions below the threshold
+    threshold = 0.5
+    scores = predictions[0]['scores'].cpu().numpy()
+    boxes = predictions[0]['boxes'].cpu().numpy()
+    labels = predictions[0]['labels'].cpu().numpy()
+    mask = scores > threshold
+    scores = scores[mask]
+    boxes = boxes[mask]
+    labels = labels[mask]
+
+    # create a new image with the predicted objects outlined in rectangles
+    draw = ImageDraw.Draw(image)
+    for box, label in zip(boxes, labels):
+        
+        # draw the rectangle around the object
+        draw.rectangle([(box[0], box[1]), (box[2], box[3])], outline='red')
+        
+        # write the object class above the rectangle
+        class_name = classes[label]
+        draw.text((box[0], box[1]), class_name, fill='yellow')
+    
+    # show the image
+    st.write("Obects detected in the image are: ")
+    st.image(image, use_column_width=True)
+    # st.image.show()
+
+file = st.file_uploader('Upload an Image', type=(["jpeg", "jpg", "png"]))
+
+
+if file is None:
+    st.write("Please upload an image file")
+else:
+    image = Image.open(file)
+    st.write("Input Image")
+    st.image(image, use_column_width=True)
+    with NamedTemporaryFile(dir='.', suffix='.') as f:
+        f.write(file.getbuffer())
+        # your_function_which_takes_a_path(f.name)
+        detect_objects(f.name)
+
+st.subheader("Model Description : ")
+st.write(""" The Faster R-CNN model with MobileNet V3 Large as the backbone and Feature Pyramid Network (FPN) architecture is a popular 
+             object detection model that combines high detection accuracy with efficient computation. The MobileNet V3 Large backbone 
+             is a lightweight neural network architecture that reduces the number of parameters while maintaining high accuracy, 
+             making it suitable for mobile and embedded devices. The FPN architecture enhances the feature representation of the model 
+             by aggregating features from multiple scales and improving spatial resolution. This combination of a lightweight backbone 
+             with an efficient feature extraction architecture makes Faster R-CNN with MobileNet V3 Large FPN a popular choice for 
+             object detection in real-time applications and on devices with limited computational resources.
+         """)

requirements.txt

@@ -0,0 +1,11 @@
+streamlit
+torch
+torchvision
+matplotlib
+transformers
+pandas
+numpy
+seaborn
+scikit-learn
+opencv-python
+pycocotools