Python utils.image.transform_inverse() Examples

The following are 30 code examples of utils.image.transform_inverse(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module utils.image , or try the search function .
Example #1
Source File: tester.py    From Faster_RCNN_for_DOTA with Apache License 2.0 5 votes vote down vote up 
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:
    """
    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
Example #2
Source File: demo.py    From RoITransformer_DOTA with MIT License 5 votes vote down vote up 
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
Example #3
Source File: tester.py    From RoITransformer_DOTA with MIT License 5 votes vote down vote up 
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()
Example #4
Source File: tester.py    From RoITransformer_DOTA with MIT License 5 votes vote down vote up 
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
Example #5
Source File: tester.py    From Relation-Networks-for-Object-Detection with MIT License 5 votes vote down vote up 
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()
Example #6
Source File: tester.py    From Accel with MIT License 5 votes vote down vote up 
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()
Example #7
Source File: tester.py    From Accel with MIT License 5 votes vote down vote up 
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
Example #8
Source File: tester.py    From Accel with MIT License 5 votes vote down vote up 
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()
Example #9
Source File: tester.py    From Accel with MIT License 5 votes vote down vote up 
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
Example #10
Source File: tester.py    From Accel with MIT License 5 votes vote down vote up 
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()
Example #11
Source File: tester.py    From Faster_RCNN_for_DOTA with Apache License 2.0 5 votes vote down vote up 
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()
Example #12
Source File: tester.py    From RoITransformer_DOTA with MIT License 5 votes vote down vote up 
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
Example #13
Source File: tester.py    From Faster_RCNN_for_DOTA with Apache License 2.0 5 votes vote down vote up 
def draw_all_quadrangle_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:
    """
    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[:8] * scale
            score = det[-1]
            if score < threshold:
                continue
            bbox = map(int, bbox)
            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
Example #14
Source File: tester.py    From Sequence-Level-Semantics-Aggregation with Apache License 2.0 5 votes vote down vote up 
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()
Example #15
Source File: tester.py    From Decoupled-Classification-Refinement with MIT License 5 votes vote down vote up 
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()
Example #16
Source File: tester.py    From Decoupled-Classification-Refinement with MIT License 5 votes vote down vote up 
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
Example #17
Source File: tester.py    From Decoupled-Classification-Refinement with MIT License 5 votes vote down vote up 
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()
Example #18
Source File: tester.py    From Decoupled-Classification-Refinement with MIT License 5 votes vote down vote up 
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
Example #19
Source File: tester.py    From Decoupled-Classification-Refinement with MIT License 5 votes vote down vote up 
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()
Example #20
Source File: tester.py    From Decoupled-Classification-Refinement with MIT License 5 votes vote down vote up 
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()
Example #21
Source File: tester.py    From Decoupled-Classification-Refinement with MIT License 5 votes vote down vote up 
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
Example #22
Source File: tester.py    From Deep-Feature-Flow with MIT License 5 votes vote down vote up 
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()
Example #23
Source File: tester.py    From kaggle-rsna18 with MIT License 5 votes vote down vote up 
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
Example #24
Source File: tester.py    From kaggle-rsna18 with MIT License 5 votes vote down vote up 
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()
Example #25
Source File: tester.py    From kaggle-rsna18 with MIT License 5 votes vote down vote up 
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
Example #26
Source File: tester.py    From kaggle-rsna18 with MIT License 5 votes vote down vote up 
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()
Example #27
Source File: tester.py    From kaggle-rsna18 with MIT License 5 votes vote down vote up 
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()
Example #28
Source File: tester.py    From MANet_for_Video_Object_Detection with Apache License 2.0 5 votes vote down vote up 
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()
Example #29
Source File: tester.py    From MANet_for_Video_Object_Detection with Apache License 2.0 5 votes vote down vote up 
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
Example #30
Source File: tester.py    From Deep-Feature-Flow with MIT License 5 votes vote down vote up 
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()