Python mmcv.imread方法代码示例

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imread [as 别名]
def __call__(self, results):
        """Call function to load images into results.

        Args:
            results (dict): A result dict contains the file name
                of the image to be read.

        Returns:
            dict: ``results`` will be returned containing loaded image.
        """
        if isinstance(results['img'], str):
            results['filename'] = results['img']
            results['ori_filename'] = results['img']
        else:
            results['filename'] = None
            results['ori_filename'] = None
        img = mmcv.imread(results['img'])
        results['img'] = img
        results['img_fields'] = ['img']
        results['img_shape'] = img.shape
        results['ori_shape'] = img.shape
        return results 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imread [as 别名]
def test_flowwrite():
    flow = np.random.rand(100, 100, 2).astype(np.float32)

    # write to a .flo file
    _, filename = tempfile.mkstemp()
    mmcv.flowwrite(flow, filename)
    flow_from_file = mmcv.flowread(filename)
    assert_array_equal(flow, flow_from_file)
    os.remove(filename)

    # write to two .jpg files
    tmp_filename = osp.join(tempfile.gettempdir(), 'mmcv_test_flow.jpg')
    for concat_axis in range(2):
        mmcv.flowwrite(
            flow, tmp_filename, quantize=True, concat_axis=concat_axis)
        shape = (200, 100) if concat_axis == 0 else (100, 200)
        assert osp.isfile(tmp_filename)
        assert mmcv.imread(tmp_filename, flag='unchanged').shape == shape
        os.remove(tmp_filename)

    # test exceptions
    with pytest.raises(AssertionError):
        mmcv.flowwrite(flow, tmp_filename, quantize=True, concat_axis=2) 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imread [as 别名]
def test_flip():
    # test assertion for invalid flip_ratio
    with pytest.raises(AssertionError):
        transform = dict(type='RandomFlip', flip_ratio=1.5)
        build_from_cfg(transform, PIPELINES)

    # test assertion for invalid direction
    with pytest.raises(AssertionError):
        transform = dict(
            type='RandomFlip', flip_ratio=1, direction='horizonta')
        build_from_cfg(transform, PIPELINES)

    transform = dict(type='RandomFlip', flip_ratio=1)
    flip_module = build_from_cfg(transform, PIPELINES)

    results = dict()
    img = mmcv.imread(
        osp.join(osp.dirname(__file__), '../data/color.jpg'), 'color')
    original_img = copy.deepcopy(img)
    results['img'] = img
    results['img2'] = copy.deepcopy(img)
    results['img_shape'] = img.shape
    results['ori_shape'] = img.shape
    # Set initial values for default meta_keys
    results['pad_shape'] = img.shape
    results['scale_factor'] = 1.0
    results['img_fields'] = ['img', 'img2']

    results = flip_module(results)
    assert np.equal(results['img'], results['img2']).all()

    flip_module = build_from_cfg(transform, PIPELINES)
    results = flip_module(results)
    assert np.equal(results['img'], results['img2']).all()
    assert np.equal(original_img, results['img']).all() 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imread [as 别名]
def test_pad():
    # test assertion if both size_divisor and size is None
    with pytest.raises(AssertionError):
        transform = dict(type='Pad')
        build_from_cfg(transform, PIPELINES)

    transform = dict(type='Pad', size_divisor=32)
    transform = build_from_cfg(transform, PIPELINES)
    results = dict()
    img = mmcv.imread(
        osp.join(osp.dirname(__file__), '../data/color.jpg'), 'color')
    original_img = copy.deepcopy(img)
    results['img'] = img
    results['img2'] = copy.deepcopy(img)
    results['img_shape'] = img.shape
    results['ori_shape'] = img.shape
    # Set initial values for default meta_keys
    results['pad_shape'] = img.shape
    results['scale_factor'] = 1.0
    results['img_fields'] = ['img', 'img2']

    results = transform(results)
    assert np.equal(results['img'], results['img2']).all()
    # original img already divisible by 32
    assert np.equal(results['img'], original_img).all()
    img_shape = results['img'].shape
    assert img_shape[0] % 32 == 0
    assert img_shape[1] % 32 == 0

    resize_transform = dict(
        type='Resize', img_scale=(1333, 800), keep_ratio=True)
    resize_module = build_from_cfg(resize_transform, PIPELINES)
    results = resize_module(results)
    results = transform(results)
    img_shape = results['img'].shape
    assert np.equal(results['img'], results['img2']).all()
    assert img_shape[0] % 32 == 0
    assert img_shape[1] % 32 == 0 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imread [as 别名]
def apredict(self, img):
            if isinstance(img, str):
                img = mmcv.imread(img)
            async with concurrent(self.streamqueue):
                result = await async_inference_detector(self.model, img)
            return result 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imread [as 别名]
def inference_single(self, imagname, slide_size, chip_size):
        img = mmcv.imread(imagname)
        height, width, channel = img.shape
        slide_h, slide_w = slide_size
        hn, wn = chip_size
        # TODO: check the corner case
        # import pdb; pdb.set_trace()
        total_detections = [np.zeros((0, 9)) for _ in range(len(self.classnames))]

        for i in tqdm(range(int(width / slide_w + 1))):
            for j in range(int(height / slide_h) + 1):
                subimg = np.zeros((hn, wn, channel))
                # print('i: ', i, 'j: ', j)
                chip = img[j*slide_h:j*slide_h + hn, i*slide_w:i*slide_w + wn, :3]
                subimg[:chip.shape[0], :chip.shape[1], :] = chip

                chip_detections = inference_detector(self.model, subimg)

                # print('result: ', result)
                for cls_id, name in enumerate(self.classnames):
                    chip_detections[cls_id][:, :8][:, ::2] = chip_detections[cls_id][:, :8][:, ::2] + i * slide_w
                    chip_detections[cls_id][:, :8][:, 1::2] = chip_detections[cls_id][:, :8][:, 1::2] + j * slide_h
                    # import pdb;pdb.set_trace()
                    try:
                        total_detections[cls_id] = np.concatenate((total_detections[cls_id], chip_detections[cls_id]))
                    except:
                        import pdb; pdb.set_trace()
        # nms
        for i in range(len(self.classnames)):
            keep = py_cpu_nms_poly_fast_np(total_detections[i], 0.1)
            total_detections[i] = total_detections[i][keep]
        return total_detections 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imread [as 别名]
def _inference_single(model, img, img_transform, device):
    img = mmcv.imread(img)
    data = _prepare_data(img, img_transform, model.cfg, device)
    with torch.no_grad():
        result = model(return_loss=False, rescale=True, **data)
    return result 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imread [as 别名]
def show_result(img, result, class_names, score_thr=0.3, out_file=None):
    """Visualize the detection results on the image.

    Args:
        img (str or np.ndarray): Image filename or loaded image.
        result (tuple[list] or list): The detection result, can be either
            (bbox, segm) or just bbox.
        class_names (list[str] or tuple[str]): A list of class names.
        score_thr (float): The threshold to visualize the bboxes and masks.
        out_file (str, optional): If specified, the visualization result will
            be written to the out file instead of shown in a window.
    """
    assert isinstance(class_names, (tuple, list))
    img = mmcv.imread(img)
    if isinstance(result, tuple):
        bbox_result, segm_result = result
    else:
        bbox_result, segm_result = result, None
    bboxes = np.vstack(bbox_result)
    # draw segmentation masks
    if segm_result is not None:
        segms = mmcv.concat_list(segm_result)
        inds = np.where(bboxes[:, -1] > score_thr)[0]
        for i in inds:
            color_mask = np.random.randint(0, 256, (1, 3), dtype=np.uint8)
            mask = maskUtils.decode(segms[i]).astype(np.bool)
            img[mask] = img[mask] * 0.5 + color_mask * 0.5
    # draw bounding boxes
    labels = [
        np.full(bbox.shape[0], i, dtype=np.int32)
        for i, bbox in enumerate(bbox_result)
    ]
    labels = np.concatenate(labels)
    mmcv.imshow_det_bboxes(
        img.copy(),
        bboxes,
        labels,
        class_names=class_names,
        score_thr=score_thr,
        show=out_file is None,
        out_file=out_file) 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imread [as 别名]
def draw_poly_detections(img, detections, class_names, scale, threshold=0.2):
    """

    :param img:
    :param detections:
    :param class_names:
    :param scale:
    :param cfg:
    :param threshold:
    :return:
    """
    import pdb
    import cv2
    import random
    assert isinstance(class_names, (tuple, list))
    img = mmcv.imread(img)
    color_white = (255, 255, 255)

    for j, name in enumerate(class_names):
        color = (random.randint(0, 256), random.randint(0, 256), random.randint(0, 256))
        try:
            dets = detections[j]
        except:
            pdb.set_trace()
        for det in dets:
            bbox = det[:8] * scale
            score = det[-1]
            if score < threshold:
                continue
            bbox = list(map(int, bbox))

            cv2.circle(img, (bbox[0], bbox[1]), 3, (0, 0, 255), -1)
            for i in range(3):
                cv2.line(img, (bbox[i * 2], bbox[i * 2 + 1]), (bbox[(i+1) * 2], bbox[(i+1) * 2 + 1]), color=color, thickness=2)
            cv2.line(img, (bbox[6], bbox[7]), (bbox[0], bbox[1]), color=color, thickness=2)
            cv2.putText(img, '%s %.3f' % (class_names[j], score), (bbox[0], bbox[1] + 10),
                        color=color_white, fontFace=cv2.FONT_HERSHEY_COMPLEX, fontScale=0.5)
    return img 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imread [as 别名]
def __call__(self, results):
        if isinstance(results['img'], str):
            results['filename'] = results['img']
        else:
            results['filename'] = None
        img = mmcv.imread(results['img'])
        results['img'] = img
        results['img_shape'] = img.shape
        results['ori_shape'] = img.shape
        return results 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imread [as 别名]
def setup_class(cls):
        cls.data_dir = osp.join(osp.dirname(__file__), '../data')
        # the test img resolution is 400x300
        cls.img_path = osp.join(cls.data_dir, 'color.jpg')
        cls.img_path_obj = Path(cls.img_path)
        cls.gray_img_path = osp.join(cls.data_dir, 'grayscale.jpg')
        cls.gray_img_path_obj = Path(cls.gray_img_path)
        cls.gray_img_dim3_path = osp.join(cls.data_dir, 'grayscale_dim3.jpg')
        cls.gray_alpha_img_path = osp.join(cls.data_dir, 'gray_alpha.png')
        cls.palette_img_path = osp.join(cls.data_dir, 'palette.gif')
        cls.img = cv2.imread(cls.img_path) 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imread [as 别名]
def test_imwrite(self):
        img = mmcv.imread(self.img_path)
        out_file = osp.join(tempfile.gettempdir(), 'mmcv_test.jpg')
        mmcv.imwrite(img, out_file)
        rewrite_img = mmcv.imread(out_file)
        os.remove(out_file)
        self.assert_img_equal(img, rewrite_img)

        ret = mmcv.imwrite(
            img, './non_exist_path/mmcv_test.jpg', auto_mkdir=False)
        assert ret is False 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imread [as 别名]
def __call__(self, results):
        filename = osp.join(results['img_prefix'],
                            results['img_info']['filename'])
        img = mmcv.imread(filename)
        if self.to_float32:
            img = img.astype(np.float32)
        results['filename'] = filename
        results['img'] = img
        results['img_shape'] = img.shape
        results['ori_shape'] = img.shape
        return results 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imread [as 别名]
def _load_semantic_seg(self, results):
        results['gt_semantic_seg'] = mmcv.imread(
            osp.join(results['seg_prefix'], results['ann_info']['seg_map']),
            flag='unchanged').squeeze()
        return results 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imread [as 别名]
def __call__(self, results):
        if results['img_prefix'] is not None:
            filename = osp.join(results['img_prefix'],
                                results['img_info']['filename'])
        else:
            filename = results['img_info']['filename']
        img = mmcv.imread(filename)
        if self.to_float32:
            img = img.astype(np.float32)
        results['filename'] = filename
        results['img'] = img
        results['img_shape'] = img.shape
        results['ori_shape'] = img.shape
        return results