utils.py 文件源码

def load_im_data(path, roi_entry, 
                 target_size=None, dim_ordering='default'):
    if pil_im is None:
        raise ImportError('Could not import PIL.Image. '
                          'The use of `array_to_img` requires PIL.')
    im = pil_im.open(path)    
    if roi_entry['flipped']:
        im = im.transpose(pil_im.FLIP_LEFT_RIGHT)

    im = im.convert('RGB')

    # substract pixel means
    #im = preprocess_input(im, dim_ordering)

    gt_inds = np.where(roi_entry['gt_classes'] != 0)[0]
    gt_boxes = np.empty((len(gt_inds), 5), dtype=np.float32)

    #resize im to match with network input
    if target_size == None:
        target_size = (224,224)

    w, h = im.size
    s_w = float(target_size[0]) / float(w)
    s_h = float(target_size[1]) / float(h)
    gt_boxes[:, 0] = roi_entry['boxes'][gt_inds, 0]*s_w
    gt_boxes[:, 2] = roi_entry['boxes'][gt_inds, 2]*s_w
    gt_boxes[:, 1] = roi_entry['boxes'][gt_inds, 1]*s_h
    gt_boxes[:, 3] = roi_entry['boxes'][gt_inds, 3]*s_h
    gt_boxes[:, 4] = roi_entry['gt_classes'][gt_inds]
    im = im.resize(size=target_size, resample=pil_im.BILINEAR)

    return im, gt_boxes