Python cv2.imread() Examples

def test_image(addr):
    target = ['angry','disgust','fear','happy','sad','surprise','neutral']
    font = cv2.FONT_HERSHEY_SIMPLEX
    
    im = cv2.imread(addr)
    gray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
    faces = faceCascade.detectMultiScale(gray,scaleFactor=1.1)
    
    for (x, y, w, h) in faces:
            cv2.rectangle(im, (x, y), (x+w, y+h), (0, 255, 0), 2,5)
            face_crop = im[y:y+h,x:x+w]
            face_crop = cv2.resize(face_crop,(48,48))
            face_crop = cv2.cvtColor(face_crop, cv2.COLOR_BGR2GRAY)
            face_crop = face_crop.astype('float32')/255
            face_crop = np.asarray(face_crop)
            face_crop = face_crop.reshape(1, 1,face_crop.shape[0],face_crop.shape[1])
            result = target[np.argmax(model.predict(face_crop))]
            cv2.putText(im,result,(x,y), font, 1, (200,0,0), 3, cv2.LINE_AA)
            
    cv2.imshow('result', im)
    cv2.imwrite('result.jpg',im)
    cv2.waitKey(0) 

def __init__(self, filename, folder=None, classifier=None):
        """
        :param filename: image with sudoku
        :param folder: folder where to save debug images
        :param classifier: digit classifier
        """
        self.filename = os.path.basename(filename)
        image = cv2.imread(filename)
        self.image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
        self.folder = folder or FOLDER
        os.mkdir(os.path.join(self.folder, 'debug/'))
        self.classifier = classifier or DigitClassifier()
        # Default initial values
        self.perspective = False
        self.debug = True
        self.counter = 0
        self.step = -1 

def encode(img_path, wm_path, res_path, alpha):
    img = cv2.imread(img_path)
    img_f = np.fft.fft2(img)
    height, width, channel = np.shape(img)
    watermark = cv2.imread(wm_path)
    wm_height, wm_width = watermark.shape[0], watermark.shape[1]
    x, y = range(height / 2), range(width)
    random.seed(height + width)
    random.shuffle(x)
    random.shuffle(y)
    tmp = np.zeros(img.shape)
    for i in range(height / 2):
        for j in range(width):
            if x[i] < wm_height and y[j] < wm_width:
                tmp[i][j] = watermark[x[i]][y[j]]
                tmp[height - 1 - i][width - 1 - j] = tmp[i][j]
    res_f = img_f + alpha * tmp
    res = np.fft.ifft2(res_f)
    res = np.real(res)
    cv2.imwrite(res_path, res, [int(cv2.IMWRITE_JPEG_QUALITY), 100]) 

def loadImgs(imgsfolder, rows, cols):
    myfiles = glob.glob(imgsfolder+'*.jpg', 0)
    nPics = len(myfiles)
    X = np.zeros((nPics, rows, cols), dtype = 'uint8')
    i = 0; imgNames = []
    for filepath in myfiles:
        sd = filepath.rfind('/'); ed = filepath.find('.'); filename = filepath[int(sd+1):int(ed)]
        imgNames.append(filename)  
        
        temp = cv2.imread(filepath, 0)
        if temp == None:
            continue
        elif temp.size < 1000:
            continue
        elif temp.shape == [rows, cols, 1]:
            X[i,:,:] = temp
        else:
            X[i,:,:] = cv2.resize(temp,(cols, rows), interpolation = cv2.INTER_CUBIC)
        i += 1
    return X, imgNames 

def downscale(old_file_name):
    img = cv2.imread(os.path.join(old_file_name))

    new_file_name = (old_file_name
                     .replace('training', 'training_' + str(min_size))
                     .replace('validation', 'validation_' + str(min_size))
                     .replace('testing', 'testing_' + str(min_size))
                     )

    height, width, _ = img.shape

    if width > height:
        new_width = int(1.0 * width / height * min_size)
        new_height = min_size

    else:
        new_height = int(1.0 * height / width * min_size)
        new_width = min_size

    img_new = cv2.resize(img, (new_width, new_height), interpolation=cv2.INTER_LINEAR)
    cv2.imwrite(new_file_name, img_new) 

def pull_item(self, index):
        img_id = self.ids[index]

        target = ET.parse(self._annopath % img_id).getroot()
        img = cv2.imread(self._imgpath % img_id)
        height, width, channels = img.shape

        if self.target_transform is not None:
            target = self.target_transform(target, width, height)

        if self.transform is not None:
            target = np.array(target)
            img, boxes, labels = self.transform(img, target[:, :4], target[:, 4])
            # to rgb
            img = img[:, :, (2, 1, 0)]
            # img = img.transpose(2, 0, 1)
            target = np.hstack((boxes, np.expand_dims(labels, axis=1)))
        return torch.from_numpy(img).permute(2, 0, 1), target, height, width
        # return torch.from_numpy(img), target, height, width 

def get_rgb_data(img_id):
    image_path = three_band_path + '/' + img_id + '.tif'
    image = tiff.imread(image_path)
    image = image.transpose((1, 2, 0))
    image = image.astype(np.float32)
    return image 

def loadLogoSet(path, rows,cols,test_data_rate=0.15):
    random.seed(612)
    _, imgID = readItems('data.txt')
    y, _ = modelDict(path)
    nPics =  len(y)
    faceassset = np.zeros((nPics,rows,cols), dtype = np.uint8) ### gray images
    noImg = []
    for i in range(nPics):
        temp = cv2.imread(path +'logo/'+imgID[i]+'.jpg', 0)
        if temp == None:
            noImg.append(i)
        elif temp.size < 1000:
            noImg.append(i)
        else:
            temp = cv2.resize(temp,(cols, rows), interpolation = cv2.INTER_CUBIC)
            faceassset[i,:,:] = temp
    y = np.delete(y, noImg,0); faceassset = np.delete(faceassset, noImg, 0)
    nPics = len(y)
    index = random.sample(np.arange(nPics), int(nPics*test_data_rate))
    x_test = faceassset[index,:,:]; x_train = np.delete(faceassset, index, 0)
    y_test = y[index]; y_train = np.delete(y, index, 0)
    return (x_train, y_train), (x_test, y_test) 

def test_color():
    image = cv2.imread('data/Lenna.png')
    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

    noise = (np.random.rand(image.shape[0], image.shape[1], 3) - 0.5) * 50
    image_noise = image + noise

    radius = [1, 2, 4]
    eps = [0.005]

    combs = list(itertools.product(radius, eps))

    vis.plot_single(to_32F(image), title='origin')
    vis.plot_single(to_32F(image_noise), title='noise')

    for r, e in combs:
        GF = GuidedFilter(image, radius=r, eps=e)
        vis.plot_single(to_32F(GF.filter(image_noise)), title='r=%d, eps=%.3f' % (r, e)) 

def _get_image_blob(roidb, scale_inds):
  """Builds an input blob from the images in the roidb at the specified
  scales.
  """
  num_images = len(roidb)
  processed_ims = []
  im_scales = []
  for i in range(num_images):
    im = cv2.imread(roidb[i]['image'])
    if roidb[i]['flipped']:
      im = im[:, ::-1, :]
    target_size = cfg.TRAIN.SCALES[scale_inds[i]]
    im, im_scale = prep_im_for_blob(im, cfg.PIXEL_MEANS, target_size,
                    cfg.TRAIN.MAX_SIZE)
    im_scales.append(im_scale)
    processed_ims.append(im)

  # Create a blob to hold the input images
  blob = im_list_to_blob(processed_ims)

  return blob, im_scales 

def get_batch():
    ran = random.randint(600, data_size)
    #print(ran)
    image = []
    label = []
    label_0 = []
    n_pic = ran
    # print(n_pic)
    for i in range(batch_size * n_steps):
        frame_0 = cv2.imread('./cropedoriginalPixel2/%d.jpg' % (n_pic+i), 0)
        frame_0 = cv2.resize(frame_0, (LONGITUDE, LONGITUDE))
        frame_0 = np.array(frame_0).reshape(-1)
        image.append(frame_0)
        #print(np.shape(image))
    for i in range(batch_size):
        frame_1 = cv2.imread('./cropedoriginalPixel2/%d.jpg' % (n_pic + batch_size * (i+1) ), 0)
        frame_1 = cv2.resize(frame_1, (LONGITUDE, LONGITUDE))
        frame_1 = np.array(frame_1).reshape(-1)
        label.append(frame_1)
    for i in range(batch_size):
        frame_2 = cv2.imread('./cropedoriginalUS2/%d.jpg' % (n_pic + batch_size * (i+1) ), 0)
        frame_2 = cv2.resize(frame_2, (LONGITUDE, LONGITUDE))
        frame_2 = np.array(frame_2).reshape(-1)
        label_0.append(frame_2)
    return image , label , label_0 

def get_batch(batch_size=20,data_size=6498):
    ran = np.random.choice(data_size, batch_size,replace=False)
    image=[]
    outline=[]
    for i in range(batch_size):
        n_pic=ran[i]
        #print(n_pic)
        frame_0 = cv2.imread('./cropPicY/%d.jpg' % n_pic,0)
        frame_0 = cv2.resize(frame_0, (24, 24))
        frame_0 = np.array(frame_0).reshape(-1)
        # print('np',frame_0)
        # frame_0 = gray2binary(frame_0)
        #print (frame_0)
        frame_1 = cv2.imread('./cropPicX/%d.jpg' % n_pic, 0)
        frame_1 = cv2.resize(frame_1, (24, 24))
        frame_1 = np.array(frame_1).reshape(-1)
        frame_1 = gray2binary(frame_1)
        image.append(frame_0)
        outline.append(frame_1)
        #print(image)
    return np.array(image),np.array(outline) 

def get_train_batch(noise=0):
    ran = random.randint(600, data_size)
    #print(ran)
    image = []
    label = []
    label_0 = []
    n_pic = ran
    # print(n_pic)
    for i in range(batch_size ):
        frame_0 = cv2.imread('./cropedoriginalPixel2/%d.jpg' % (n_pic+i), 0)
        frame_0 = add_noise(frame_0, n = noise)
        frame_0 = cv2.resize(frame_0, (LONGITUDE, LONGITUDE))
        frame_0 = np.array(frame_0).reshape(-1)
        image.append(frame_0)
        #print(np.shape(image))
    for i in range(batch_size):
        frame_1 = cv2.imread('./cropedoriginalPixel2/%d.jpg' % (n_pic + batch_size * (i+1) ), 0)
        frame_1 = cv2.resize(frame_1, (LONGITUDE, LONGITUDE))
        frame_1 = np.array(frame_1).reshape(-1)
        label.append(frame_1)
    return image , label 

def get_batch(batch_size=20,data_size=6498):
    ran = np.random.choice(data_size, batch_size,replace=False)
    image=[]
    for i in range(batch_size):
        n_pic=ran[i]
        #print(n_pic)
        frame_0 = cv2.imread('./cropPicX/%d.jpg' % n_pic,0)
        frame_0 = cv2.resize(frame_0, (24, 24))
        frame_0 = np.array(frame_0).reshape(-1)
        image.append(frame_0)
        #print(image)
    return np.array(image)


# Visualize decoder setting
# Parameters 

def get_batch(batch_size=20,data_size=6498):
    ran = np.random.choice(data_size, batch_size,replace=False)
    image=[]
    outline=[]
    for i in range(batch_size):
        n_pic=ran[i]
        #print(n_pic)
        frame_0 = cv2.imread('./easyPixelImage2/%d.jpg' % n_pic,0)
        frame_0 = cv2.resize(frame_0, (24, 24))
        frame_0 = np.array(frame_0).reshape(-1)
        # print('np',frame_0)
        # frame_0 = gray2binary(frame_0)
        #print (frame_0)
        frame_1 = cv2.imread('./easyPixelImage2/%d.jpg' % n_pic, 0)
        frame_1 = cv2.resize(frame_1, (24, 24))
        frame_1 = np.array(frame_1).reshape(-1)
        frame_1 = gray2binary(frame_1)
        image.append(frame_0)
        outline.append(frame_1)
        #print(image)
    return np.array(image),np.array(outline) 

def get_train_batch(noise=500):
    ran = np.random.randint(600,5800,size=10,dtype='int')
    #print(ran)
    image = []
    label = []
    label_0 = []
    n_pic = ran
    # print(n_pic)
    for i in range(10):
        frame_0 = cv2.imread('./cropedoriginalPixel2/%d.jpg' % (n_pic[i]), 0)
        frame_0 = add_noise(frame_0, n = noise)
        frame_0 = cv2.resize(frame_0, (24, 24))
        frame_0 = np.array(frame_0).reshape(-1)
        frame_0 = frame_0 / 255.0
        image.append(frame_0)
        #print(np.shape(image))
    for i in range(10):
        frame_1 = cv2.imread('./cropedoriginalPixel2/%d.jpg' % (n_pic[i]), 0)
        frame_1 = cv2.resize(frame_1, (24, 24))
        frame_1 = np.array(frame_1).reshape(-1)
        frame_1 = gray2binary(frame_1)
        label.append(frame_1)
    return np.array(image,dtype='float') , np.array(label,dtype='float') 

def get_test_batch(noise=500):
    ran = np.random.randint(5800,6000,size=10,dtype='int')
    #print(ran)
    image = []
    label = []
    label_0 = []
    n_pic = ran
    # print(n_pic)
    for i in range(10):
        frame_0 = cv2.imread('./cropedoriginalPixel2/%d.jpg' % (n_pic[i]), 0)
        frame_0 = add_noise(frame_0, n = noise)
        frame_0 = cv2.resize(frame_0, (24, 24))
        frame_0 = np.array(frame_0).reshape(-1)
        frame_0 = frame_0 / 255.0
        image.append(frame_0)
        #print(np.shape(image))
    for i in range(10):
        frame_1 = cv2.imread('./cropedoriginalPixel2/%d.jpg' % (n_pic[i]), 0)
        frame_1 = cv2.resize(frame_1, (24, 24))
        frame_1 = np.array(frame_1).reshape(-1)
        frame_1 = gray2binary(frame_1)
        label.append(frame_1)
    return np.array(image,dtype='float') , np.array(label,dtype='float') 

def get_data(datadir):
    #datadir = args.data
    # assume each image is 512x256 split to left and right
    imgs = glob.glob(os.path.join(datadir, '*.jpg'))
    data_X = np.zeros((len(imgs),3,img_cols,img_rows))
    data_Y = np.zeros((len(imgs),3,img_cols,img_rows))  
    i = 0
    for file in imgs:
        img = cv2.imread(file,cv2.IMREAD_COLOR)
        img = cv2.resize(img, (img_cols*2, img_rows)) 
        #print('{} {},{}'.format(i,np.shape(img)[0],np.shape(img)[1]))
        img = np.swapaxes(img,0,2)

        X, Y = split_input(img)

        data_X[i,:,:,:] = X
        data_Y[i,:,:,:] = Y
        i = i+1
    return data_X, data_Y 

def gen_image_frames(img_path, fps, duration):
    """Generate frames from a image so that can play like a video.

    Parameters
    ----------
    img_path : string
        absolute path to the image.
    fps : int
        frame rates per second
    duration : float
        duration of the sequence in second
    """
    num_frames = int(fps*duration)

    img = cv2.imread(img_path)
    frames = []
    for i in xrange(num_frames):
        frames.append(img)

    return frames, len(frames) 

def _get_image_blob(roidb, scale_inds):
    """Builds an input blob from the images in the roidb at the specified
    scales.
    """
    num_images = len(roidb)
    processed_ims = []
    im_scales = []
    im_shapes = np.zeros((0, 2), dtype=np.float32)
    for i in xrange(num_images):
        im = cv2.imread(roidb[i]['image'])
        if roidb[i]['flipped']:
            im = im[:, ::-1, :]
        target_size = cfg.TRAIN.SCALES[scale_inds[i]]
        im, im_scale, im_shape = prep_im_for_blob(im, cfg.PIXEL_MEANS, target_size)
        im_scales.append(im_scale)
        processed_ims.append(im)
        im_shapes = np.vstack((im_shapes, im_shape))

    # Create a blob to hold the input images
    blob = im_list_to_blob(processed_ims)

    return blob, im_scales, im_shapes 

def get_image_features(self, img_file, stride=5, padding=True):
        """
        Take an image file as input, and output an array of image features whose matrix size is
        based on the image size. When no padding, and the image size is smaller than the required
        feature space size (in x or y direction), the image is not checked, and this method will
        return a tuple of two empty lists; When padding is True, and the image size is more than
        4 pixels smaller than the require feature space size (in x or y direction), the image is
        not checked either. This method can be used by both the trainer and predictor.
        Args:
            img_file: The file name of the image.
            stride: Optional. The stride of the sliding.
            padding: Optional. Whether to pad the image to fit the feature space size or to
                discard the extra pixels if padding is False.
        Returns:
            coordinates: A list of coordinates, each of which contains y and x that are the top
                left corner offsets of the sliding window.
            features: A matrix (python list), in which each row contains the features of the
                sampling sliding window, while the number of rows depends on the image size of
                the input.
        """
        img = cv2.imread(img_file)
        img_arr = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

        return self.get_image_array_features(img_arr, stride, padding) 

def s1_predict(config_file, model_dir, model_file, predict_file_list, out_dir):
    """
    This function serves as a test/validation tool during the model development. It is not used as
    a final product in part of the pipeline.
    """
    with open(config_file) as config_buffer:
        config = json.loads(config_buffer.read())

    with tf.Graph().as_default() as graph:
        converted_model = ConvertedModel(config, graph, 's1_keras', model_dir, model_file)

    with tf.Session(graph=graph) as sess:
        for img_file in predict_file_list:
            image = cv2.imread(img_file)
            boxes = converted_model.predict(sess, image)
            image = draw_boxes(image, boxes)

            _, filename = os.path.split(img_file)
            cv2.imwrite(os.path.join(out_dir, filename), image) 

def get_batch_idx(self, idx):
        hh = self.inp_height
        ww = self.inp_width
        x = np.zeros([len(idx), hh, ww, 3], dtype='float32')
        orig_height = []
        orig_width = []
        ids = []
        for kk, ii in enumerate(idx):
            fname = self.ids[ii]
            ids.append('{:06}'.format(ii))
            x_ = cv2.imread(fname).astype('float32') / 255
            x[kk] = cv2.resize(
                x_, (self.inp_width, self.inp_height),
                interpolation=cv2.INTER_CUBIC)
            orig_height.append(x_.shape[0])
            orig_width.append(x_.shape[1])
            pass
        return {
            'x': x,
            'orig_height': np.array(orig_height),
            'orig_width': np.array(orig_width),
            'id': ids
        } 

def process_frame(frame_number, frame, keypoint_data, detector, matcher):
    log = logging.getLogger("process_frame")

    # Create a copy of source frame to draw into
    processed = frame.copy()

    gray_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    kp, des = detector.detectAndCompute(frame, None)
    
    # Match descriptors
    matches = matcher.match(keypoint_data.descriptors, des)
    
    # Sort them in order of distance
    matches = sorted(matches, key = lambda x:x.distance)
    
    processed = drawMatches(cv2.imread('car.png',0), keypoint_data.keypoints, gray_frame, kp, matches[:])
    
    return processed
    
# ============================================================================ 

def check_image(name):
    expected_data = json.loads(open('./img/' + name + '.json').read())
    if not expected_data['enabled']:
        return

    expected_targets = expected_data['targets']

    img = cv2.imread('./img/' + name + '.jpg', cv2.IMREAD_COLOR)
    hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
    args = config.copy()
    args['img'] = hsv
    args['output_images'] = {}

    actual_targets = find(**args)

    # make sure same number of targets are detected
    assert len(expected_targets) == len(actual_targets)

    # targets is a list of 2-tuples with expected and actual results
    targets = zip(expected_targets, actual_targets)
    # compare all the different features of targets to make sure they match
    for pair in targets:
        expected, actual = pair
        # make sure that the targets are close to where they are supposed to be
        assert is_close(expected['pos']['x'], actual['pos']['x'], 0.02)
        assert is_close(expected['pos']['y'], actual['pos']['y'], 0.02)
        # make sure that the targets are close to the size they are supposed to be
        assert is_close(expected['size']['width'], actual['size']['width'], 0.02)
        assert is_close(expected['size']['height'], actual['size']['height'], 0.02) 

def create_composite_image_coin_id(coin_id, crop_dir, data_dir):
    images = []
    images_gif = []

    for id in range(0,56):
        image_id = coin_id * 100 + id
        crop = ci.get_rotated_crop(crop_dir, image_id, 56, 0)
        images.append(crop)
        filename =  ci.get_filename_from(image_id,crop_dir)
        images_gif.append(imageio.imread(filename))

    composite_image = ci.get_composite_image(images, 8, 8)
    cv2.imwrite(data_dir + str(coin_id) + '.png', composite_image)
    imageio.mimsave(data_dir + str(coin_id) + '.gif', images_gif)

    return 

def get_image_array(roidb, scales, scale_indexes, need_mean=True):
    """
    build image array from specific roidb
    :param roidb: images to be processed
    :param scales: scale list
    :param scale_indexes: indexes
    :return: array [b, c, h, w], list of scales
    """
    num_images = len(roidb)
    processed_ims = []
    im_scales = []
    for i in range(num_images):
        im = cv2.imread(roidb[i]['image'])
        if roidb[i]['flipped']:
            im = im[:, ::-1, :]
        target_size = scales[scale_indexes[i]]
        im, im_scale = image_processing.resize(im, target_size, config.MAX_SIZE)
        im_tensor = image_processing.transform(im, config.PIXEL_MEANS, need_mean=need_mean)
        processed_ims.append(im_tensor)
        im_scales.append(im_scale)
    array = image_processing.tensor_vstack(processed_ims)
    return array, im_scales 

def _get_image_blob(roidb, scale_inds):
    """Builds an input blob from the images in the roidb at the specified
    scales.
    """
    num_images = len(roidb)
    processed_ims = []
    im_scales = []
    for i in xrange(num_images):
        im = cv2.imread(roidb[i]['image'])
        if roidb[i]['flipped']:
            im = im[:, ::-1, :]
        target_size = cfg.TRAIN.SCALES[scale_inds[i]]
        im, im_scale = prep_im_for_blob(im, cfg.PIXEL_MEANS, target_size,
                                        cfg.TRAIN.MAX_SIZE)
        im_scales.append(im_scale)
        processed_ims.append(im)

    # Create a blob to hold the input images
    blob = im_list_to_blob(processed_ims)

    return blob, im_scales 

def imdb_proposals(net, imdb):
    """Generate RPN proposals on all images in an imdb."""

    _t = Timer()
    imdb_boxes = [[] for _ in xrange(imdb.num_images)]
    for i in xrange(imdb.num_images):
        im = cv2.imread(imdb.image_path_at(i))
        _t.tic()
        imdb_boxes[i], scores = im_proposals(net, im)
        _t.toc()
        print 'im_proposals: {:d}/{:d} {:.3f}s' \
              .format(i + 1, imdb.num_images, _t.average_time)
        if 0:
            dets = np.hstack((imdb_boxes[i], scores))
            # from IPython import embed; embed()
            _vis_proposals(im, dets[:3, :], thresh=0.9)
            plt.show()

    return imdb_boxes 

def _get_feature_scale(self, num_images=100):
        TARGET_NORM = 20.0 # Magic value from traditional R-CNN
        _t = Timer()
        roidb = self.imdb.roidb
        total_norm = 0.0
        count = 0.0
        inds = npr.choice(xrange(self.imdb.num_images), size=num_images,
                          replace=False)
        for i_, i in enumerate(inds):
            im = cv2.imread(self.imdb.image_path_at(i))
            if roidb[i]['flipped']:
                im = im[:, ::-1, :]
            _t.tic()
            scores, boxes = im_detect(self.net, im, roidb[i]['boxes'])
            _t.toc()
            feat = self.net.blobs[self.layer].data
            total_norm += np.sqrt((feat ** 2).sum(axis=1)).sum()
            count += feat.shape[0]
            print('{}/{}: avg feature norm: {:.3f}'.format(i_ + 1, num_images,
                                                           total_norm / count))

        return TARGET_NORM * 1.0 / (total_norm / count) 

def predict(the_net,image):
  inputs = []
  if not os.path.exists(image):
    raise Exception("Image path not exist")
    return
  try:
    tmp_input = cv2.imread(image)
    tmp_input = cv2.resize(tmp_input,(SIZE,SIZE))
    tmp_input = tmp_input[11:11+128,11:11+128]
    tmp_input = np.subtract(tmp_input,mean)
    tmp_input = tmp_input.transpose((2, 0, 1))
    tmp_input = np.require(tmp_input, dtype=np.float32)
  except Exception as e:
    #raise Exception("Image damaged or illegal file format")
    return None
  the_net.blobs['data'].reshape(1, *tmp_input.shape)
  the_net.reshape()
  the_net.blobs['data'].data[...] = tmp_input
  the_net.forward()
  scores = copy.deepcopy(the_net.blobs['feature'].data)
  return scores 

def predict(the_net,image):
  inputs = []
  if not os.path.exists(image):
    raise Exception("Image path not exist")
    return
  try:
    tmp_input = cv2.imread(image)
    tmp_input = cv2.resize(tmp_input,(SIZE,SIZE))
    tmp_input = tmp_input[13:13+224,13:13+224]
    #tmp_input = np.subtract(tmp_input,mean)
    tmp_input = tmp_input.transpose((2, 0, 1))
    tmp_input = np.require(tmp_input, dtype=np.float32)
  except Exception as e:
    #raise Exception("Image damaged or illegal file format")
    return None
  the_net.blobs['data'].reshape(1, *tmp_input.shape)
  the_net.reshape()
  the_net.blobs['data'].data[...] = tmp_input
  the_net.forward()
  scores = copy.deepcopy(the_net.blobs['fc6'].data)
  return scores 

def predict(the_net,image):
  inputs = []
  if not os.path.exists(image):
    raise Exception("Image path not exist")
    return
  try:
    tmp_input = cv2.imread(image)
    tmp_input = cv2.resize(tmp_input,(SIZE,SIZE))
    tmp_input = tmp_input[13:13+224,13:13+224]
    tmp_input = np.subtract(tmp_input,mean)
    tmp_input = tmp_input.transpose((2, 0, 1))
    tmp_input = np.require(tmp_input, dtype=np.float32)
  except Exception as e:
    #raise Exception("Image damaged or illegal file format")
    return None
  the_net.blobs['data'].reshape(1, *tmp_input.shape)
  the_net.reshape()
  the_net.blobs['data'].data[...] = tmp_input
  the_net.forward()
  scores = copy.deepcopy(the_net.blobs['fc6'].data)
  return scores 

def get_batcher(self, shuffle=True, augment=True):
        """ produces batch generator """
        w, h = self.resize

        if shuffle: np.random.shuffle(self.data)
        data = iter(self.data)
        while True:
            x = np.zeros((self.batch_size, self.timesteps, h, w, 3))
            y = np.zeros((self.batch_size, 1))
            for b in range(self.batch_size):
                images, label = next(data)
                for t, img_name in enumerate(images):
                    image_path = self.folder + 'images/' + img_name
                    img = cv2.imread(image_path)
                    img = img[190:350, 100:520] # crop
                    if augment:
                        img = aug.augment_image(img) # augmentation
                    img = cv2.resize(img.copy(), (w, h))
                    x[b, t] = img
                y[b] = label
            x = np.transpose(x, [0, 4, 1, 2, 3])
            yield x, y 

def repaint_skin(filename):
    import cv2
    shutil.copy(filename, filename + '.bak')
    frame = cv2.imread(filename)
    HSV = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
    l = np.array([0, 50, 80], dtype = "uint8")
    u = np.array([23, 255, 255], dtype = "uint8")
    skin_area = cv2.inRange(HSV, l, u)
    not_skin_area = cv2.bitwise_not(frame, frame, mask = skin_area)
    cv2.imwrite(filename, not_skin_area) 

def _get_image_blob(roidb, scale_inds, data_i):
    """Builds an input blob from the images in the roidb at the specified
    scales.
    """
    num_images = len(roidb)
    processed_ims = []
    im_scales = []
    for i in xrange(num_images):
        im = cv2.imread(roidb[i]['image'][data_i])
        if roidb[i]['flipped']:
            im = im[:, ::-1, :]
        target_size = cfg.TRAIN.SCALES[scale_inds[i]]
        im, im_scale = prep_im_for_blob(im, cfg.PIXEL_MEANS, target_size,
                                        cfg.TRAIN.MAX_SIZE)
        im_scales.append(im_scale)
        processed_ims.append(im)

    # Create a blob to hold the input images
    blob = im_list_to_blob(processed_ims)

    return blob, im_scales 

def _get_feature_scale(self, num_images=100):
        TARGET_NORM = 20.0 # Magic value from traditional R-CNN
        _t = Timer()
        roidb = self.imdb.roidb
        total_norm = 0.0
        count = 0.0
        inds = npr.choice(xrange(self.imdb.num_images), size=num_images,
                          replace=False)
        for i_, i in enumerate(inds):
            im = cv2.imread(self.imdb.image_path_at(i))
            if roidb[i]['flipped']:
                im = im[:, ::-1, :]
            _t.tic()
            scores, boxes = im_detect(self.net, im, roidb[i]['boxes'])
            _t.toc()
            feat = self.net.blobs[self.layer].data
            total_norm += np.sqrt((feat ** 2).sum(axis=1)).sum()
            count += feat.shape[0]
            print('{}/{}: avg feature norm: {:.3f}'.format(i_ + 1, num_images,
                                                           total_norm / count))

        return TARGET_NORM * 1.0 / (total_norm / count) 

def _get_image_blob(roidb, scale_inds):
    """Builds an input blob from the images in the roidb at the specified
    scales.
    """
    num_images = len(roidb)
    processed_ims = []
    im_scales = []
    for i in xrange(num_images):
        im = cv2.imread(roidb[i]['image'])
        if roidb[i]['flipped']:
            im = im[:, ::-1, :]
        target_size = cfg.TRAIN.SCALES[scale_inds[i]]
        im, im_scale = prep_im_for_blob(im, cfg.PIXEL_MEANS, target_size,
                                        cfg.TRAIN.MAX_SIZE)
        im_scales.append(im_scale)
        processed_ims.append(im)

    # Create a blob to hold the input images
    blob = im_list_to_blob(processed_ims)

    return blob, im_scales 

def imdb_proposals(net, imdb):
    """Generate RPN proposals on all images in an imdb."""

    _t = Timer()
    imdb_boxes = [[] for _ in xrange(imdb.num_images)]
    for i in xrange(imdb.num_images):
        im = cv2.imread(imdb.image_path_at(i))
        _t.tic()
        imdb_boxes[i], scores = im_proposals(net, im)
        _t.toc()
        print 'im_proposals: {:d}/{:d} {:.3f}s' \
              .format(i + 1, imdb.num_images, _t.average_time)
        if 0:
            dets = np.hstack((imdb_boxes[i], scores))
            # from IPython import embed; embed()
            _vis_proposals(im, dets[:3, :], thresh=0.9)
            plt.show()

    return imdb_boxes 

def _get_feature_scale(self, num_images=100):
        TARGET_NORM = 20.0 # Magic value from traditional R-CNN
        _t = Timer()
        roidb = self.imdb.roidb
        total_norm = 0.0
        count = 0.0
        inds = npr.choice(xrange(self.imdb.num_images), size=num_images,
                          replace=False)
        for i_, i in enumerate(inds):
            im = cv2.imread(self.imdb.image_path_at(i))
            if roidb[i]['flipped']:
                im = im[:, ::-1, :]
            _t.tic()
            scores, boxes = im_detect(self.net, im, roidb[i]['boxes'])
            _t.toc()
            feat = self.net.blobs[self.layer].data
            total_norm += np.sqrt((feat ** 2).sum(axis=1)).sum()
            count += feat.shape[0]
            print('{}/{}: avg feature norm: {:.3f}'.format(i_ + 1, num_images,
                                                           total_norm / count))

        return TARGET_NORM * 1.0 / (total_norm / count) 

def init_file_path(directory):
    """
    Get the image file path array
    :param directory: the directory that store images
    :return: an array of image file path
    """
    paths = []

    if not debug:
        print "Throwing all gray space images now... this may takes some time.."

    for file_name in os.listdir(directory):
        # Skip files that is not jpg
        file_path = '%s/%s' % (directory, file_name)
        if not file_name.endswith('.jpg') or imghdr.what(file_path) is not 'jpeg':
            continue
        if debug:
            paths.append(file_path)
        else:
            # Throw gray space images, this takes long time if have many images
            # TODO: maybe can change to a fast way
            img = cv2.imread(file_path, cv2.IMREAD_UNCHANGED)
            if len(img.shape) == 3 and img.shape[2] != 1:
                paths.append(file_path)
    return paths 

def store_raw_images():
    '''To download images from image-net
        (Change the url for different needs of cascades)
    '''
    neg_images_link = 'http://image-net.org/api/text/imagenet.synset.geturls?wnid=n07942152'
    neg_image_urls = urllib2.urlopen(neg_images_link).read().decode()

    pic_num = 1

    for i in neg_image_urls.split('\n'):
        try:

            print i
            urllib.urlretrieve(i, "neg/" + str(pic_num) + '.jpg')
            img = cv2.imread("neg/" + str(pic_num) +'.jpg',
                                cv2.IMREAD_GRAYSCALE)
            resized_image = cv2.resize(img, (100, 100))
            cv2.imwrite("neg/" + str(pic_num) + '.jpg', resized_image)
            pic_num = pic_num + 1

        except:
            print "error" 

def find_uglies():
    '''image-net gives a default image when it's real one is not available,
        this is to remove them
    '''
    for file_type in ['neg']:
        for img in os.listdir(file_type):
            for ugly in os.listdir('uglies'):
                try:
                    current_image_path = str(file_type) + '/' + str(img)
                    ugly = cv2.imread('uglies/' + str(ugly))
                    question = cv2.imread(current_image_path)

                    if ugly.shape == question.shape and not (np.bitwise_xor(ugly, question).any()):
                        print "girl you ugly"
                        os.remove(current_image_path)
                except:
                    print "error" 

def GetFeature(image_path):
	#MinBlackRate, left_most_pixel_gradiant,  hill_number, average_hill_peak, average_hill_valley, BlackRate
	boundary_path = image_path.split(".")[0]+"_upper_boundary.txt"
	file = open(boundary_path)
	tmp_str = file.readline().strip()
	tmp_arr = tmp_str.split(" ")
	boundary = []
	for i in range(len(tmp_arr)):
		if tmp_arr[i]!="":
			boundary.append(int(tmp_arr[i]))
	boundary = np.array(boundary)
	file.close()
	image = cv2.imread(image_path,cv2.IMREAD_GRAYSCALE)
	image = CropLowerBoundary(image)

	feature = MinGridBlackRate(image,boundary)+BlackRate(image,boundary)
	flag,tmp_feature = CountHill(boundary,image)
	if flag==False:
		return [False,feature]
	feature += tmp_feature
	return [True,feature] 

def read_images( filenames, domain=None, image_size=64):

    images = []

    for fn in filenames:
        image = cv2.imread(fn)
        if image is None:
            continue

        if domain == 'A':
            kernel = np.ones((3,3), np.uint8)
            image = image[:, :256, :]
            image = 255. - image
            image = cv2.dilate( image, kernel, iterations=1 )
            image = 255. - image
        elif domain == 'B':
            image = image[:, 256:, :]

        image = cv2.resize(image, (image_size,image_size))
        image = image.astype(np.float32) / 255.
        image = image.transpose(2,0,1)
        images.append( image )

    images = np.stack( images )
    return images 

def train_dir(nets, optim, optim2, dataloader, args):
    
  global image_size, it, image_sizes
  caffe.set_mode_gpu() 
  
  if args.debug:
    image_sizes = [[416, 416]]

  while True:
      
    if it % 500 == 0:
      image_size = image_sizes[random.randint(0, len(image_sizes) - 1)]
      print(image_size)
    
    #im = cv2.imread('/home/busta/data/90kDICT32px/background/n03085781_3427.jpg')
    #try:
    process_batch(nets, optim, optim2, image_size, args)
    
    if it % valid_interval == 0:
      validate(nets, dataloader, image_size = [416, 416], split_words=False)
        
    #except:
    #    continue 

def __init__(self, g_pool,selected_watermark_path = None,pos = (20,20)):
        super().__init__(g_pool)
        self.order = .9
        self.menu = None

        available_files = glob(os.path.join(self.g_pool.user_dir,'*png')) #we only look for png's
        self.available_files = [f for f in available_files if cv2.imread(f,-1).shape[2]==4] #we only look for rgba images
        logger.debug('Found {} watermark files: {}'.format(len(self.available_files), self.available_files))

        self.watermark = None
        self.watermark_path = None
        self.alpha_mask = None

        if selected_watermark_path in self.available_files:
            self.load_watermark(selected_watermark_path)
        elif self.available_files:
            self.load_watermark(self.available_files[0])
        else:
            logger.warning("No .png files found. Make sure they are in RGBA format.")

        self.pos = list(pos) #if we make the default arg a list the instance will edit the default vals and a new call of the class constructor creates an ainstace with modified default values.
        self.move_watermark = False
        self.drag_offset = None 

def color_quant(input,K,output):
    img = cv2.imread(input)
    Z = img.reshape((-1,3))
    # convert to np.float32
    Z = np.float32(Z)
    # define criteria, number of clusters(K) and apply kmeans()
    criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 15, 1.0)

    ret,label,center=cv2.kmeans(Z,K,None,criteria,10,cv2.KMEANS_RANDOM_CENTERS)

    # Now convert back into uint8, and make original image
    center = np.uint8(center)
    res = center[label.flatten()]
    res2 = res.reshape((img.shape))

    cv2.imshow('res2',res2)
    cv2.waitKey(0)
    cv2.imwrite(output, res2)
    cv2.destroyAllWindows() 

def decode(ori_path, img_path, res_path, alpha):
    ori = cv2.imread(ori_path)
    img = cv2.imread(img_path)
    ori_f = np.fft.fft2(ori)
    img_f = np.fft.fft2(img)
    height, width = ori.shape[0], ori.shape[1]
    watermark = (ori_f - img_f) / alpha
    watermark = np.real(watermark)
    res = np.zeros(watermark.shape)
    random.seed(height + width)
    x = range(height / 2)
    y = range(width)
    random.shuffle(x)
    random.shuffle(y)
    for i in range(height / 2):
        for j in range(width):
            res[x[i]][y[j]] = watermark[i][j]
    cv2.imwrite(res_path, res, [int(cv2.IMWRITE_JPEG_QUALITY), 100]) 

def plot_face_bb(p, bb, scale=True, path=True, plot=True):
    if path:
        im = cv2.imread(p)
    else:
        im = cv2.cvtColor(p, cv2.COLOR_RGB2BGR)
    if scale:
        h, w, _ = im.shape
        cv2.rectangle(im, (int(bb[0] * h), int(bb[1] * w)),
                      (int(bb[2] * h), int(bb[3] * w)),
                      (255, 255, 0), thickness=4)
        # print bb * np.asarray([h, w, h, w])
    else:
        cv2.rectangle(im, (int(bb[0]), int(bb[1])), (int(bb[2]), int(bb[3])),
                      (255, 255, 0), thickness=4)
        print "no"
    if plot:
        plt.figure()
        plt.imshow(im[:, :, ::-1])
    else:
        return im[:, :, ::-1]