You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
221 lines
8.2 KiB
221 lines
8.2 KiB
# Ultralytics YOLO 🚀, AGPL-3.0 license |
|
|
|
import argparse |
|
from typing import Tuple, Union |
|
|
|
import cv2 |
|
import numpy as np |
|
import tensorflow as tf |
|
import yaml |
|
|
|
from ultralytics.utils import ASSETS |
|
|
|
try: |
|
from tflite_runtime.interpreter import Interpreter |
|
except ImportError: |
|
import tensorflow as tf |
|
|
|
Interpreter = tf.lite.Interpreter |
|
|
|
|
|
class YOLOv8TFLite: |
|
""" |
|
YOLOv8TFLite. |
|
|
|
A class for performing object detection using the YOLOv8 model with TensorFlow Lite. |
|
|
|
Attributes: |
|
model (str): Path to the TensorFlow Lite model file. |
|
conf (float): Confidence threshold for filtering detections. |
|
iou (float): Intersection over Union threshold for non-maximum suppression. |
|
metadata (Optional[str]): Path to the metadata file, if any. |
|
|
|
Methods: |
|
detect(img_path: str) -> np.ndarray: |
|
Performs inference and returns the output image with drawn detections. |
|
""" |
|
|
|
def __init__(self, model: str, conf: float = 0.25, iou: float = 0.45, metadata: Union[str, None] = None): |
|
""" |
|
Initializes an instance of the YOLOv8TFLite class. |
|
|
|
Args: |
|
model (str): Path to the TFLite model. |
|
conf (float, optional): Confidence threshold for filtering detections. Defaults to 0.25. |
|
iou (float, optional): IoU (Intersection over Union) threshold for non-maximum suppression. Defaults to 0.45. |
|
metadata (Union[str, None], optional): Path to the metadata file or None if not used. Defaults to None. |
|
""" |
|
self.conf = conf |
|
self.iou = iou |
|
if metadata is None: |
|
self.classes = {i: i for i in range(1000)} |
|
else: |
|
with open(metadata) as f: |
|
self.classes = yaml.safe_load(f)["names"] |
|
np.random.seed(42) |
|
self.color_palette = np.random.uniform(128, 255, size=(len(self.classes), 3)) |
|
|
|
self.model = Interpreter(model_path=model) |
|
self.model.allocate_tensors() |
|
|
|
input_details = self.model.get_input_details()[0] |
|
|
|
self.in_width, self.in_height = input_details["shape"][1:3] |
|
self.in_index = input_details["index"] |
|
self.in_scale, self.in_zero_point = input_details["quantization"] |
|
self.int8 = input_details["dtype"] == np.int8 |
|
|
|
output_details = self.model.get_output_details()[0] |
|
self.out_index = output_details["index"] |
|
self.out_scale, self.out_zero_point = output_details["quantization"] |
|
|
|
def letterbox(self, img: np.ndarray, new_shape: Tuple = (640, 640)) -> Tuple[np.ndarray, Tuple[float, float]]: |
|
"""Resizes and reshapes images while maintaining aspect ratio by adding padding, suitable for YOLO models.""" |
|
shape = img.shape[:2] # current shape [height, width] |
|
|
|
# Scale ratio (new / old) |
|
r = min(new_shape[0] / shape[0], new_shape[1] / shape[1]) |
|
|
|
# Compute padding |
|
new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r)) |
|
dw, dh = (new_shape[1] - new_unpad[0]) / 2, (new_shape[0] - new_unpad[1]) / 2 # wh padding |
|
|
|
if shape[::-1] != new_unpad: # resize |
|
img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR) |
|
top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1)) |
|
left, right = int(round(dw - 0.1)), int(round(dw + 0.1)) |
|
img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=(114, 114, 114)) |
|
|
|
return img, (top / img.shape[0], left / img.shape[1]) |
|
|
|
def draw_detections(self, img: np.ndarray, box: np.ndarray, score: np.float32, class_id: int) -> None: |
|
""" |
|
Draws bounding boxes and labels on the input image based on the detected objects. |
|
|
|
Args: |
|
img (np.ndarray): The input image to draw detections on. |
|
box (np.ndarray): Detected bounding box in the format [x1, y1, width, height]. |
|
score (np.float32): Corresponding detection score. |
|
class_id (int): Class ID for the detected object. |
|
|
|
Returns: |
|
None |
|
""" |
|
x1, y1, w, h = box |
|
color = self.color_palette[class_id] |
|
|
|
cv2.rectangle(img, (int(x1), int(y1)), (int(x1 + w), int(y1 + h)), color, 2) |
|
|
|
label = f"{self.classes[class_id]}: {score:.2f}" |
|
|
|
(label_width, label_height), _ = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.5, 1) |
|
|
|
label_x = x1 |
|
label_y = y1 - 10 if y1 - 10 > label_height else y1 + 10 |
|
|
|
cv2.rectangle( |
|
img, |
|
(int(label_x), int(label_y - label_height)), |
|
(int(label_x + label_width), int(label_y + label_height)), |
|
color, |
|
cv2.FILLED, |
|
) |
|
|
|
cv2.putText(img, label, (int(label_x), int(label_y)), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0), 1, cv2.LINE_AA) |
|
|
|
def preprocess(self, img: np.ndarray) -> Tuple[np.ndarray, Tuple[float, float]]: |
|
""" |
|
Preprocesses the input image before performing inference. |
|
|
|
Args: |
|
img (np.ndarray): The input image to be preprocessed. |
|
|
|
Returns: |
|
Tuple[np.ndarray, Tuple[float, float]]: A tuple containing: |
|
- The preprocessed image (np.ndarray). |
|
- A tuple of two float values representing the padding applied (top/bottom, left/right). |
|
""" |
|
img, pad = self.letterbox(img, (self.in_width, self.in_height)) |
|
img = img[..., ::-1][None] # N,H,W,C for TFLite |
|
img = np.ascontiguousarray(img) |
|
img = img.astype(np.float32) |
|
return img / 255, pad |
|
|
|
def postprocess(self, img: np.ndarray, outputs: np.ndarray, pad: Tuple[float, float]) -> np.ndarray: |
|
""" |
|
Performs post-processing on the model's output to extract bounding boxes, scores, and class IDs. |
|
|
|
Args: |
|
img (numpy.ndarray): The input image. |
|
outputs (numpy.ndarray): The output of the model. |
|
pad (Tuple[float, float]): Padding used by letterbox. |
|
|
|
Returns: |
|
numpy.ndarray: The input image with detections drawn on it. |
|
""" |
|
outputs[:, 0] -= pad[1] |
|
outputs[:, 1] -= pad[0] |
|
outputs[:, :4] *= max(img.shape) |
|
|
|
outputs = outputs.transpose(0, 2, 1) |
|
outputs[..., 0] -= outputs[..., 2] / 2 |
|
outputs[..., 1] -= outputs[..., 3] / 2 |
|
|
|
for out in outputs: |
|
scores = out[:, 4:].max(-1) |
|
keep = scores > self.conf |
|
boxes = out[keep, :4] |
|
scores = scores[keep] |
|
class_ids = out[keep, 4:].argmax(-1) |
|
|
|
indices = cv2.dnn.NMSBoxes(boxes, scores, self.conf, self.iou).flatten() |
|
|
|
[self.draw_detections(img, boxes[i], scores[i], class_ids[i]) for i in indices] |
|
|
|
return img |
|
|
|
def detect(self, img_path: str) -> np.ndarray: |
|
""" |
|
Performs inference using a TFLite model and returns the output image with drawn detections. |
|
|
|
Args: |
|
img_path (str): The path to the input image file. |
|
|
|
Returns: |
|
np.ndarray: The output image with drawn detections. |
|
""" |
|
img = cv2.imread(img_path) |
|
x, pad = self.preprocess(img) |
|
if self.int8: |
|
x = (x / self.in_scale + self.in_zero_point).astype(np.int8) |
|
self.model.set_tensor(self.in_index, x) |
|
|
|
self.model.invoke() |
|
|
|
y = self.model.get_tensor(self.out_index) |
|
|
|
if self.int8: |
|
y = (y.astype(np.float32) - self.out_zero_point) * self.out_scale |
|
|
|
return self.postprocess(img, y, pad) |
|
|
|
|
|
if __name__ == "__main__": |
|
parser = argparse.ArgumentParser() |
|
parser.add_argument( |
|
"--model", |
|
type=str, |
|
default="yolov8n_saved_model/yolov8n_full_integer_quant.tflite", |
|
help="Path to TFLite model.", |
|
) |
|
parser.add_argument("--img", type=str, default=str(ASSETS / "bus.jpg"), help="Path to input image") |
|
parser.add_argument("--conf", type=float, default=0.25, help="Confidence threshold") |
|
parser.add_argument("--iou", type=float, default=0.45, help="NMS IoU threshold") |
|
parser.add_argument("--metadata", type=str, default="yolov8n_saved_model/metadata.yaml", help="Metadata yaml") |
|
args = parser.parse_args() |
|
|
|
detector = YOLOv8TFLite(args.model, args.conf, args.iou, args.metadata) |
|
result = detector.detect(str(ASSETS / "bus.jpg"))[..., ::-1] |
|
|
|
cv2.imshow("Output", result) |
|
cv2.waitKey(0)
|
|
|