Upload 10 files

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+data/breakfast.mp4 filter=lfs diff=lfs merge=lfs -text
+data/school.mp4 filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,36 @@
+import gradio as gr
+import cv2
+from utils import object_detection_brainai as odb
+object_detection = odb.ObjectDetectionModel()
+
+def detect_image(img):
+    result_img = object_detection.process(img)
+    
+    return result_img
+
+
+def detect_video(video_path, ):
+    frames, fps, frame_width, frame_height = object_detection.detect_objects_in_video(video_path)
+    output_video_path = object_detection.create_video(frames, fps, frame_width, frame_height)
+    
+    return output_video_path
+
+image_interface = gr.Interface(
+    fn=detect_image, 
+    inputs=gr.Image(label="Upload Image"), 
+    outputs="image", 
+    examples = ['data/desk.jpg', 'data/office.jpg'],
+    title="Image Object Detection"
+)
+
+video_interface = gr.Interface(
+    fn=detect_video, 
+    inputs=gr.Video(label="Upload Video"), 
+    examples = ['data/breakfast.mp4', 'data/school.mp4'],
+    outputs="video", 
+    title="Video Object Detection"
+)
+
+demo = gr.TabbedInterface([image_interface, video_interface], ["Image", "Video"])
+ 
+demo.launch()

data/breakfast.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c72555727af845f336b68f204186b8012781979dafa7e7abb3a4671590f4049c
+size 1396102

data/school.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:636ee794077188d85c717722e49024595a3381deac75acf1471410ab88028a8f
+size 2837273

models/yolov8n.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f59b3d833e2ff32e194b5bb8e08d211dc7c5bdf144b90d2c8412c47ccfc83b36
+size 6549796

models/yolov8n_openvino_model/metadata.yaml

@@ -0,0 +1,93 @@
+description: Ultralytics YOLOv8n model trained on coco.yaml
+author: Ultralytics
+date: '2024-11-27T09:26:37.990600'
+version: 8.3.34
+license: AGPL-3.0 License (https://ultralytics.com/license)
+docs: https://docs.ultralytics.com
+stride: 32
+task: detect
+batch: 1
+imgsz:
+- 640
+- 640
+names:
+  0: person
+  1: bicycle
+  2: car
+  3: motorcycle
+  4: airplane
+  5: bus
+  6: train
+  7: truck
+  8: boat
+  9: traffic light
+  10: fire hydrant
+  11: stop sign
+  12: parking meter
+  13: bench
+  14: bird
+  15: cat
+  16: dog
+  17: horse
+  18: sheep
+  19: cow
+  20: elephant
+  21: bear
+  22: zebra
+  23: giraffe
+  24: backpack
+  25: umbrella
+  26: handbag
+  27: tie
+  28: suitcase
+  29: frisbee
+  30: skis
+  31: snowboard
+  32: sports ball
+  33: kite
+  34: baseball bat
+  35: baseball glove
+  36: skateboard
+  37: surfboard
+  38: tennis racket
+  39: bottle
+  40: wine glass
+  41: cup
+  42: fork
+  43: knife
+  44: spoon
+  45: bowl
+  46: banana
+  47: apple
+  48: sandwich
+  49: orange
+  50: broccoli
+  51: carrot
+  52: hot dog
+  53: pizza
+  54: donut
+  55: cake
+  56: chair
+  57: couch
+  58: potted plant
+  59: bed
+  60: dining table
+  61: toilet
+  62: tv
+  63: laptop
+  64: mouse
+  65: remote
+  66: keyboard
+  67: cell phone
+  68: microwave
+  69: oven
+  70: toaster
+  71: sink
+  72: refrigerator
+  73: book
+  74: clock
+  75: vase
+  76: scissors
+  77: teddy bear
+  78: hair drier
+  79: toothbrush

models/yolov8n_openvino_model/yolov8n.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b86fce278a5a6833dc015b7af8cbcb7174004a5f9b6ff7ec724f753f361681
+size 12708656

utils/object_detection_brainai.py

@@ -0,0 +1,45 @@
+from ultralytics import YOLO
+import cv2
+
+class ObjectDetectionModel(): 
+    
+    def __init__(self):
+        self.model = YOLO("models/yolov8n_openvino_model", task = "detect")
+        self.class_names = self.model.names
+
+    def process(self, img):
+        result = self.model(img)
+        img_plot = result[0].plot()
+
+        return img_plot
+
+    
+    def detect_objects_in_video(self, video_path, conf_thres=0.25, iou_thres=0.45):
+        cap = cv2.VideoCapture(video_path)
+        frame_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+        frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+        fps = cap.get(cv2.CAP_PROP_FPS)
+        frames = []
+    
+        while cap.isOpened():
+            ret, frame = cap.read()
+            if not ret:
+                break
+    
+            img_plot = self.process(frame)
+            frames.append(img_plot)
+        cap.release()
+        return frames, fps, frame_width, frame_height
+    
+    def create_video(self, frames, fps, frame_width, frame_height):
+        fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+        out_path = 'output_video.mp4'
+        out = cv2.VideoWriter(out_path, fourcc, fps, (frame_width, frame_height))
+    
+        for frame in frames:
+            out.write(frame)
+    
+        out.release()
+        return out_path
+
+