yolov7/yolov7_utils.py

import cv2
import numpy as np


def prepare_input(image, input_shape):
    input_height, input_width = input_shape
    input_img = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

    # Resize input image
    input_img = cv2.resize(input_img, (input_width, input_height))
    # Scale input pixel values to 0 to 1
    input_img = input_img / 255.0
    input_img = input_img.transpose(2, 0, 1)
    input_tensor = input_img[np.newaxis, :, :, :].astype(np.float32)

    return input_tensor

def process_output(output, ori_shape, input_shape, conf_threshold, iou_threshold, classes=[]):
        predictions = output[0]
        # predictions = np.squeeze(output[0])
        # print(predictions.shape)
        # print([p[5] for p in predictions])
        # exit()
        # Filter out object confidence scores below threshold
        # obj_conf = predictions[:, 4]
        obj_conf = predictions[:, 6]
        # predictions = predictions[obj_conf > conf_threshold]
        # obj_conf = obj_conf[obj_conf > conf_threshold]

        # print(obj_conf[0])

        # Multiply class confidence with bounding box confidence
        # predictions[:, 5] *= obj_conf[:, np.newaxis]
        # predictions[:, 6] *= obj_conf

        # Get the scores
        # scores = np.max(predictions[:, 5:], axis=1)
        scores = predictions[:, 6]

        # Filter out the objects with a low score
        predictions = predictions[obj_conf > conf_threshold]
        scores = scores[scores > conf_threshold]

        if len(scores) == 0:
            return [], [], []

        # Get the class with the highest confidence
        # class_ids = np.argmax(predictions[:, 5:], axis=1)
        class_ids = predictions[:, 5].astype(np.uint16)
        # Extract boxes from predictions
        boxes = predictions[:, 1:5]

        # Scale boxes to original image dimensions
        boxes = rescale_boxes(boxes, ori_shape, input_shape)

        # Convert boxes to xyxy format
        # boxes = xywh2xyxy(boxes)

        # Apply non-maxima suppression to suppress weak, overlapping bounding boxes
        indices = nms(boxes, scores, iou_threshold)

        dets = []
        for i in indices:
            if len(classes) > 0:
                if class_ids[i] in classes:
                    dets.append([*boxes[i], scores[i], class_ids[i]])
            else:
                dets.append([*boxes[i], scores[i], class_ids[i]])

        # return boxes[indices], scores[indices], class_ids[indices]
        return np.array(dets)


def rescale_boxes(boxes, ori_shape, input_shape):
    
    input_height, input_width = input_shape
    img_height, img_width = ori_shape
    # Rescale boxes to original image dimensions
    input_shape = np.array([input_width, input_height, input_width, input_height])
    boxes = np.divide(boxes, input_shape, dtype=np.float32)
    boxes *= np.array([img_width, img_height, img_width, img_height])
    return boxes

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

# Create a list of colors for each class where each color is a tuple of 3 integer values
rng = np.random.default_rng(3)
colors = rng.uniform(0, 255, size=(len(class_names), 3))

def nms(boxes, scores, iou_threshold):
    # Sort by score
    sorted_indices = np.argsort(scores)[::-1]

    keep_boxes = []
    while sorted_indices.size > 0:
        # Pick the last box
        box_id = sorted_indices[0]
        keep_boxes.append(box_id)

        # Compute IoU of the picked box with the rest
        ious = compute_iou(boxes[box_id, :], boxes[sorted_indices[1:], :])

        # Remove boxes with IoU over the threshold
        keep_indices = np.where(ious < iou_threshold)[0]

        # print(keep_indices.shape, sorted_indices.shape)
        sorted_indices = sorted_indices[keep_indices + 1]

    return keep_boxes


def compute_iou(box, boxes):
    # Compute xmin, ymin, xmax, ymax for both boxes
    xmin = np.maximum(box[0], boxes[:, 0])
    ymin = np.maximum(box[1], boxes[:, 1])
    xmax = np.minimum(box[2], boxes[:, 2])
    ymax = np.minimum(box[3], boxes[:, 3])

    # Compute intersection area
    intersection_area = np.maximum(0, xmax - xmin) * np.maximum(0, ymax - ymin)

    # Compute union area
    box_area = (box[2] - box[0]) * (box[3] - box[1])
    boxes_area = (boxes[:, 2] - boxes[:, 0]) * (boxes[:, 3] - boxes[:, 1])
    union_area = box_area + boxes_area - intersection_area

    # Compute IoU
    iou = intersection_area / union_area

    return iou


def xywh2xyxy(x):
    # Convert bounding box (x, y, w, h) to bounding box (x1, y1, x2, y2)
    y = np.copy(x)
    y[..., 0] = x[..., 0] - x[..., 2] / 2
    y[..., 1] = x[..., 1] - x[..., 3] / 2
    y[..., 2] = x[..., 0] + x[..., 2] / 2
    y[..., 3] = x[..., 1] + x[..., 3] / 2
    return y

def draw_detections(image, boxes, scores, class_ids, mask_alpha=0.3):
    mask_img = image.copy()
    det_img = image.copy()

    img_height, img_width = image.shape[:2]
    size = min([img_height, img_width]) * 0.0006
    text_thickness = int(min([img_height, img_width]) * 0.001)
    # Draw bounding boxes and labels of detections
    for box, score, class_id in zip(boxes, scores, class_ids):
        color = colors[class_id]

        x1, y1, x2, y2 = box.astype(int)

        # Draw rectangle
        cv2.rectangle(det_img, (x1, y1), (x2, y2), color, 2)

        # Draw fill rectangle in mask image
        cv2.rectangle(mask_img, (x1, y1), (x2, y2), color, -1)

        label = class_names[class_id]
        caption = f'{label} {int(score * 100)}%'
        (tw, th), _ = cv2.getTextSize(text=caption, fontFace=cv2.FONT_HERSHEY_SIMPLEX,
                                      fontScale=size, thickness=text_thickness)
        th = int(th * 1.2)

        cv2.rectangle(det_img, (x1, y1),
                      (x1 + tw, y1 - th), color, -1)
        cv2.rectangle(mask_img, (x1, y1),
                      (x1 + tw, y1 - th), color, -1)
        cv2.putText(det_img, caption, (x1, y1),
                    cv2.FONT_HERSHEY_SIMPLEX, size, (255, 255, 255), text_thickness, cv2.LINE_AA)

        cv2.putText(mask_img, caption, (x1, y1),
                    cv2.FONT_HERSHEY_SIMPLEX, size, (255, 255, 255), text_thickness, cv2.LINE_AA)

        cv2.imwrite('reult.png', mask_img)
    exit()


# def draw_detections(image, boxes, scores, class_ids, draw_scores=True, mask_alpha=0.4):

#     return draw_detections(image, boxes, scores,
#                             class_ids, mask_alpha)