Python image.transform_inverse方法代碼示例

# 需要導入模塊: from utils import image [as 別名]
# 或者: from utils.image import transform_inverse [as 別名]
def vis_all_detection(im_array, detections, class_names, scale, cfg, threshold=1e-3):
    """
    visualize all detections in one image
    :param im_array: [b=1 c h w] in rgb
    :param detections: [ numpy.ndarray([[x1 y1 x2 y2 score]]) for j in classes ]
    :param class_names: list of names in imdb
    :param scale: visualize the scaled image
    :return:
    """
    import matplotlib.pyplot as plt
    import random
    im = image.transform_inverse(im_array, cfg.network.PIXEL_MEANS)
    plt.imshow(im)
    for j, name in enumerate(class_names):
        if name == '__background__':
            continue
        color = (random.random(), random.random(), random.random())  # generate a random color
        dets = detections[j]
        for det in dets:
            bbox = det[:4] * scale
            score = det[-1]
            if score < threshold:
                continue
            rect = plt.Rectangle((bbox[0], bbox[1]),
                                 bbox[2] - bbox[0],
                                 bbox[3] - bbox[1], fill=False,
                                 edgecolor=color, linewidth=3.5)
            plt.gca().add_patch(rect)
            plt.gca().text(bbox[0], bbox[1] - 2,
                           '{:s} {:.3f}'.format(name, score),
                           bbox=dict(facecolor=color, alpha=0.5), fontsize=12, color='white')
    plt.show() 

# 需要導入模塊: from utils import image [as 別名]
# 或者: from utils.image import transform_inverse [as 別名]
def draw_all_detection(im_array, detections, class_names, scale, cfg, threshold=1e-1):
    """
    visualize all detections in one image
    :param im_array: [b=1 c h w] in rgb
    :param detections: [ numpy.ndarray([[x1 y1 x2 y2 score]]) for j in classes ]
    :param class_names: list of names in imdb
    :param scale: visualize the scaled image
    :return:
    """
    import cv2
    import random
    color_white = (255, 255, 255)
    im = image.transform_inverse(im_array, cfg.network.PIXEL_MEANS)
    # change to bgr
    im = cv2.cvtColor(im, cv2.COLOR_RGB2BGR)
    for j, name in enumerate(class_names):
        if name == '__background__':
            continue
        color = (random.randint(0, 256), random.randint(0, 256), random.randint(0, 256))  # generate a random color
        dets = detections[j]
        for det in dets:
            bbox = det[:4] * scale
            score = det[-1]
            if score < threshold:
                continue
            bbox = map(int, bbox)
            cv2.rectangle(im, (bbox[0], bbox[1]), (bbox[2], bbox[3]), color=color, thickness=2)
            cv2.putText(im, '%s %.3f' % (class_names[j], score), (bbox[0], bbox[1] + 10),
                        color=color_white, fontFace=cv2.FONT_HERSHEY_COMPLEX, fontScale=0.5)
    return im 

# 需要導入模塊: from utils import image [as 別名]
# 或者: from utils.image import transform_inverse [as 別名]
def vis_all_detection(im_array, detections, class_names, scale, cfg, threshold=0.1):
    """
    visualize all detections in one image
    :param im_array: [b=1 c h w] in rgb
    :param detections: [ numpy.ndarray([[x1 y1 x2 y2 score]]) for j in classes ]
    :param class_names: list of names in imdb
    :param scale: visualize the scaled image
    :return:
    """
    import matplotlib.pyplot as plt
    import random
    im = image.transform_inverse(im_array, cfg.network.PIXEL_MEANS)
    plt.imshow(im)
    for j, name in enumerate(class_names):
        if name == '__background__':
            continue
        color = (random.random(), random.random(), random.random())  # generate a random color
        dets = detections[j]
        for det in dets:
            bbox = det[:4] * scale
            score = det[-1]
            if score < threshold:
                continue
            rect = plt.Rectangle((bbox[0], bbox[1]),
                                 bbox[2] - bbox[0],
                                 bbox[3] - bbox[1], fill=False,
                                 edgecolor=color, linewidth=3.5)
            plt.gca().add_patch(rect)
            plt.gca().text(bbox[0], bbox[1] - 2,
                           '{:s} {:.3f}'.format(name, score),
                           bbox=dict(facecolor=color, alpha=0.5), fontsize=12, color='white')
    plt.show() 

# 需要導入模塊: from utils import image [as 別名]
# 或者: from utils.image import transform_inverse [as 別名]
def draw_all_detection(im_array, detections, class_names, scale, cfg, threshold=0.1):
    """
    visualize all detections in one image
    :param im_array: [b=1 c h w] in rgb
    :param detections: [ numpy.ndarray([[x1 y1 x2 y2 score]]) for j in classes ]
    :param class_names: list of names in imdb
    :param scale: visualize the scaled image
    :return:
    """
    import cv2
    import random
    color_white = (255, 255, 255)
    im = image.transform_inverse(im_array, cfg.network.PIXEL_MEANS)
    # change to bgr
    im = cv2.cvtColor(im, cv2.COLOR_RGB2BGR)
    for j, name in enumerate(class_names):
        if name == '__background__':
            continue
        color = (random.randint(0, 256), random.randint(0, 256), random.randint(0, 256))  # generate a random color
        dets = detections[j]
        for det in dets:
            bbox = det[:4] * scale
            score = det[-1]
            if score < threshold:
                continue
            bbox = map(int, bbox)
            cv2.rectangle(im, (bbox[0], bbox[1]), (bbox[2], bbox[3]), color=color, thickness=2)
            cv2.putText(im, '%s %.3f' % (class_names[j], score), (bbox[0], bbox[1] + 10),
                        color=color_white, fontFace=cv2.FONT_HERSHEY_COMPLEX, fontScale=0.5)
    return im 

# 需要導入模塊: from utils import image [as 別名]
# 或者: from utils.image import transform_inverse [as 別名]
def vis_all_detection(im_array, detections, class_names, scale, cfg, threshold=1e-4):
    """
    visualize all detections in one image
    :param im_array: [b=1 c h w] in rgb
    :param detections: [ numpy.ndarray([[x1 y1 x2 y2 score]]) for j in classes ]
    :param class_names: list of names in imdb
    :param scale: visualize the scaled image
    :return:
    """
    import matplotlib.pyplot as plt
    import random
    im = image.transform_inverse(im_array, cfg.network.PIXEL_MEANS)
    plt.imshow(im)
    for j, name in enumerate(class_names):
        if name == '__background__':
            continue
        color = (random.random(), random.random(), random.random())  # generate a random color
        dets = detections[j]
        for det in dets:
            bbox = det[:4] * scale
            score = det[-1]
            if score < threshold:
                continue
            rect = plt.Rectangle((bbox[0], bbox[1]),
                                 bbox[2] - bbox[0],
                                 bbox[3] - bbox[1], fill=False,
                                 edgecolor=color, linewidth=3.5)
            plt.gca().add_patch(rect)
            plt.gca().text(bbox[0], bbox[1] - 2,
                           '{:s} {:.3f}'.format(name, score),
                           bbox=dict(facecolor=color, alpha=0.5), fontsize=12, color='white')
    plt.show() 

# 需要導入模塊: from utils import image [as 別名]
# 或者: from utils.image import transform_inverse [as 別名]
def draw_all_poly_detection(im_array, detections, class_names, scale, cfg, threshold=0.2):
    """
    visualize all detections in one image
    :param im_array: [b=1 c h w] in rgb
    :param detections: [ numpy.ndarray([[x1 y1 x2 y2 score]]) for j in classes ]
    :param class_names: list of names in imdb
    :param scale: visualize the scaled image
    :return:
    """
    import cv2
    import random
    color_white = (255, 255, 255)
    im = image.transform_inverse(im_array, cfg.network.PIXEL_MEANS)
    # change to bgr
    im = cv2.cvtColor(im, cv2.COLOR_RGB2BGR)
    if DEBUG:
        class_names = ['__background__', 'fg']
    for j, name in enumerate(class_names):
        if name == '__background__':
            continue
        color = (random.randint(0, 256), random.randint(0, 256), random.randint(0, 256))  # generate a random color
        dets = detections[j]
        for det in dets:
            bbox = det[:8] * scale
            score = det[-1]
            if score < threshold:
                continue
            bbox = map(int, bbox)
            # draw first point
            cv2.circle(im, (bbox[0], bbox[1]), 3, (0, 0, 255), -1)
            for i in range(3):
                cv2.line(im, (bbox[i * 2], bbox[i * 2 + 1]), (bbox[(i+1) * 2], bbox[(i+1) * 2 + 1]), color=color, thickness=2)
            cv2.line(im, (bbox[6], bbox[7]), (bbox[0], bbox[1]), color=color, thickness=2)
            cv2.putText(im, '%s %.3f' % (class_names[j], score), (bbox[0], bbox[1] + 10),
                        color=color_white, fontFace=cv2.FONT_HERSHEY_COMPLEX, fontScale=0.5)
    return im 

# 需要導入模塊: from utils import image [as 別名]
# 或者: from utils.image import transform_inverse [as 別名]
def draw_all_poly_detection(im_array, detections, class_names, scale, cfg, threshold=0.2):
    """
    visualize all detections in one image
    :param im_array: [b=1 c h w] in rgb
    :param detections: [ numpy.ndarray([[x1 y1 x2 y2 score]]) for j in classes ]
    :param class_names: list of names in imdb
    :param scale: visualize the scaled image
    :return:
    """
    # pdb.set_trace()
    import cv2
    import random
    color_white = (255, 255, 255)
    im = image.transform_inverse(im_array, cfg.network.PIXEL_MEANS)
    # change to bgr
    im = cv2.cvtColor(im, cv2.COLOR_RGB2BGR)
    for j, name in enumerate(class_names):
        if name == '__background__':
            continue
        color = (random.randint(0, 256), random.randint(0, 256), random.randint(0, 256))  # generate a random color
        try:
            dets = detections[j]
        except:
            pdb.set_trace()
        for det in dets:
            bbox = det[:8] * scale
            score = det[-1]
            if score < threshold:
                continue
            bbox = map(int, bbox)
            # draw first point
            cv2.circle(im, (bbox[0], bbox[1]), 3, (0, 0, 255), -1)
            for i in range(3):
                cv2.line(im, (bbox[i * 2], bbox[i * 2 + 1]), (bbox[(i+1) * 2], bbox[(i+1) * 2 + 1]), color=color, thickness=2)
            cv2.line(im, (bbox[6], bbox[7]), (bbox[0], bbox[1]), color=color, thickness=2)
            cv2.putText(im, '%s %.3f' % (class_names[j], score), (bbox[0], bbox[1] + 10),
                        color=color_white, fontFace=cv2.FONT_HERSHEY_COMPLEX, fontScale=0.5)
    return im