Add files via upload

Author: abhijeetgupta23

Diff for: Dockerfile

@@ -15,7 +15,7 @@ RUN apt-get update && apt-get install -y mesa-utils
 
 RUN pip install --upgrade pip && pip install -r requirements.txt
 
-# Make port 80 available to the world outside this container
+# Make port 8000 available to the world outside this container
 EXPOSE 8000
 
 # Define environment variable

Diff for: Linkedin Writeup.docx

@@ -0,0 +1,14 @@
+COCO_INSTANCE_CATEGORY_NAMES = [
+    '__background__', 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus',
+    'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'N/A', 'stop sign',
+    'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
+    'elephant', 'bear', 'zebra', 'giraffe', 'N/A', 'backpack', 'umbrella', 'N/A', 'N/A',
+    'handbag', 'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball',
+    'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 'tennis racket',
+    'bottle', 'N/A', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl',
+    'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza',
+    'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed', 'N/A', 'dining table',
+    'N/A', 'N/A', 'toilet', 'N/A', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
+    'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'N/A', 'book',
+    'clock', 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush'
+]

Diff for: Yolo8_Model_Creation.ipynb

@@ -0,0 +1,29 @@
+import torchvision
+import numpy
+import torch
+import argparse
+import cv2
+import detect_utils
+from PIL import Image
+
+# construct the argument parser
+parser = argparse.ArgumentParser()
+parser.add_argument('-i', '--input', help='path to input image/video')
+parser.add_argument('-m', '--min-size', dest='min_size', default=800, 
+                    help='minimum input size for the FasterRCNN network')
+args = vars(parser.parse_args())
+
+# download or load the model from disk
+model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True, 
+                                                    min_size=args['min_size'])
+
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+image = Image.open(args['input'])
+model.eval().to(device)
+boxes, classes, labels = detect_utils.predict(image, model, device, 0.8)
+image = detect_utils.draw_boxes(boxes, classes, labels, image)
+cv2.imshow('Image', image)
+save_name = f"{args['input'].split('/')[-1].split('.')[0]}_{args['min_size']}"
+cv2.imwrite(f"outputs/{save_name}.jpg", image)
+cv2.waitKey(0)

Diff for: coco_names.py

@@ -0,0 +1,47 @@
+import torchvision.transforms as transforms
+import cv2
+import numpy as np
+from coco_names import COCO_INSTANCE_CATEGORY_NAMES as coco_names
+
+# this will help us create a different color for each class
+COLORS = np.random.uniform(0, 255, size=(len(coco_names), 3))
+
+# define the torchvision image transforms
+transform = transforms.Compose([
+    transforms.ToTensor(),
+])
+
+def predict(image, model, device, detection_threshold):
+    # transform the image to tensor
+    image = transform(image).to(device)
+    image = image.unsqueeze(0) # add a batch dimension
+    outputs = model(image) # get the predictions on the image
+    # print the results individually
+    # print(f"BOXES: {outputs[0]['boxes']}")
+    # print(f"LABELS: {outputs[0]['labels']}")
+    # print(f"SCORES: {outputs[0]['scores']}")
+    # get all the predicited class names
+    pred_classes = [coco_names[i] for i in outputs[0]['labels'].cpu().numpy()]
+    # get score for all the predicted objects
+    pred_scores = outputs[0]['scores'].detach().cpu().numpy()
+    # get all the predicted bounding boxes
+    pred_bboxes = outputs[0]['boxes'].detach().cpu().numpy()
+    # get boxes above the threshold score
+    boxes = pred_bboxes[pred_scores >= detection_threshold].astype(np.int32)
+    return boxes, pred_classes, outputs[0]['labels']
+
+def draw_boxes(boxes, classes, labels, image):
+    # read the image with OpenCV
+    image = cv2.cvtColor(np.asarray(image), cv2.COLOR_BGR2RGB)
+    for i, box in enumerate(boxes):
+        color = COLORS[labels[i]]
+        cv2.rectangle(
+            image,
+            (int(box[0]), int(box[1])),
+            (int(box[2]), int(box[3])),
+            color, 2
+        )
+        cv2.putText(image, classes[i], (int(box[0]), int(box[1]-5)),
+                    cv2.FONT_HERSHEY_SIMPLEX, 0.8, color, 2, 
+                    lineType=cv2.LINE_AA)
+    return image

Diff for: detect.py

@@ -15,13 +15,13 @@
 async def read_index():
     return FileResponse('Upload_for_Detection.html')
 
-# Define endpoint for making box predictions
+# Define endpoint for making box predictions using Web UI
 @app.post("/YOLO_Box_Prediction_Website/")
 def predict_uploaded_image(file: UploadFile):
 
     try:
 
-        # Upload the image transmitted via POST in a file based on its name
+        # Upload and open the image transmitted via POST in a file based on its name
         file_name = file.filename
         with open(file_name, "wb") as f:
             f.write(file.file.read())
@@ -41,12 +41,10 @@ def predict_uploaded_image(file: UploadFile):
     except Exception as e:
         return {"message": e.args}
 
-# Define endpoint for making box predictions
+# Define endpoint for making box predictions programatically
 @app.post("/YOLO_Box_Prediction_Service/")
 async def predict_uploaded_image(file: UploadFile):
 
-    #contents = await file.read()
-
     try:
 
         # Upload the image transmitted via POST in a file based on its name