Python cv2.resize() Examples

def crop_and_store(frame, mouth_coordinates, name):
	"""
	Args:
		1. frame:				The frame which has to be cropped.
		2. mouth_coordinates:	The coordinates which help in deciding which region is to be cropped.
		3. name:				The path name to be used for storing the cropped image.
	"""

	# Find bounding rectangle for mouth coordinates
	x, y, w, h = cv2.boundingRect(mouth_coordinates)

	mouth_roi = frame[y:y + h, x:x + w]

	h, w, channels = mouth_roi.shape
	# If the cropped region is very small, ignore this case.
	if h < 10 or w < 10:
		return
	
	resized = resize(mouth_roi, 32, 32)
	cv2.imwrite(name, resized) 

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 preprocess(image):
    """Takes an image and apply preprocess"""
    # ????????????
    image = cv2.resize(image, (data_shape, data_shape))
    # ?? BGR ? RGB
    image = image[:, :, (2, 1, 0)]
    # ?mean?????float
    image = image.astype(np.float32)
    # ? mean
    image -= np.array([123, 117, 104])
    # ??? [batch-channel-height-width]
    image = np.transpose(image, (2, 0, 1))
    image = image[np.newaxis, :]
    # ?? ndarray
    image = nd.array(image)
    return image 

def get_image_descriptor_for_image(image, model):
    im = cv2.resize(image, (224, 224)).astype(np.float32)
    dim_ordering = K.image_dim_ordering()
    if dim_ordering == 'th':
        # 'RGB'->'BGR'
        im = im[::-1, :, :]
        # Zero-center by mean pixel
        im[0, :, :] -= 103.939
        im[1, :, :] -= 116.779
        im[2, :, :] -= 123.68
    else:
        # 'RGB'->'BGR'
        im = im[:, :, ::-1]
        # Zero-center by mean pixel
        im[:, :, 0] -= 103.939
        im[:, :, 1] -= 116.779
        im[:, :, 2] -= 123.68
    im = im.transpose((2, 0, 1))
    im = np.expand_dims(im, axis=0)
    inputs = [K.learning_phase()] + model.inputs
    _convout1_f = K.function(inputs, [model.layers[33].output])
    return _convout1_f([0] + [im]) 

def videoize(func, args, src = 0, win_name = "Cam", delim_wait = 1, delim_key = 27):
    cap = cv2.VideoCapture(src)
    while(1):
        ret, frame = cap.read()
        # To speed up processing; Almost real-time on my PC
        frame = cv2.resize(frame, dsize=None, fx=0.5, fy=0.5)
        frame = cv2.flip(frame, 1)
        out = func(frame, args)
        if out is None:
            continue
        out = cv2.resize(out, dsize=None, fx=1.4, fy=1.4)
        cv2.imshow(win_name, out)
        cv2.moveWindow(win_name, (s_w - out.shape[1])/2, (s_h - out.shape[0])/2)
        k = cv2.waitKey(delim_wait)

        if k == delim_key:
            cv2.destroyAllWindows()
            cap.release()
            return 

def add_text(img, text, text_top, image_scale):
    """
    Args:
        img (numpy array of shape (width, height, 3): input image
        text (str): text to add to image
        text_top (int): location of top text to add
        image_scale (float): image resize scale

    Summary:
        Add display text to a frame.

    Returns:
        Next available location of top text (allows for chaining this function)
    """
    cv2.putText(
        img=img,
        text=text,
        org=(0, text_top),
        fontFace=cv2.FONT_HERSHEY_SIMPLEX,
        fontScale=0.15 * image_scale,
        color=(255, 255, 255))
    return text_top + int(5 * image_scale) 

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 format_img(img, C):
	img_min_side = float(C.im_size)
	(height,width,_) = img.shape
	
	if width <= height:
		f = img_min_side/width
		new_height = int(f * height)
		new_width = int(img_min_side)
	else:
		f = img_min_side/height
		new_width = int(f * width)
		new_height = int(img_min_side)
	fx = width/float(new_width)
	fy = height/float(new_height)
	img = cv2.resize(img, (new_width, new_height), interpolation=cv2.INTER_CUBIC)
	img = img[:, :, (2, 1, 0)]
	img = img.astype(np.float32)
	img[:, :, 0] -= C.img_channel_mean[0]
	img[:, :, 1] -= C.img_channel_mean[1]
	img[:, :, 2] -= C.img_channel_mean[2]
	img /= C.img_scaling_factor
	img = np.transpose(img, (2, 0, 1))
	img = np.expand_dims(img, axis=0)
	return img, fx, fy 

def resize_image(self,img,*args):
        # unpacks width, height
        height, width,_ = img.shape
        print("Original size: {} {}".format(width, height))
        count_times_resized = 0
        while width > 500 or height > 500:
        #if width > 300 or height > 300:
            # divides images WxH by half
            width = width / 2
            height = height /2
            count_times_resized += 1
        # prints x times resized to console
        if count_times_resized != 0:
            print("Resized {}x smaller, to: {} {}".format(count_times_resized*2,width, height))
        # makes sures image is not TOO small
        if width < 300 and height < 300:
            width = width * 2
            height = height * 2

        img = cv2.resize(img,(int(width),int(height)))

        return img 

def switch_camara(self):
        self.activo = not self.activo
        if self.activo:

            # Capturo el primer frame para quedarme con el tamano y el factor de resize

            ret,frame = self.cap.read(self.camera_id)

            self.activo = ret
            if ret:
                self.img_height, self.img_width, self.img_channels = frame.shape
                self.img_zoomx = 320.0/self.img_width
                self.img_zoomy = 200.0/self.img_height
                # Ya tengo los datos. Capturo la imagen final y me quedo con el frame
                self.captura_frame()
            else:
                self.status = "No puedo encontrar la camara"
                print "No encuentro la camara!!!!" 

def get_frame(self):

        ret,frame = self.cap.read(self.camera_id)
        self.frame = cv2.resize(frame,None,fx=self.img_zoomx, fy=self.img_zoomy, \
                interpolation = cv2.INTER_AREA)

        self.frame = cv2.blur(self.frame, (3,3))
        self.hsv = cv2.cvtColor(self.frame, cv2.COLOR_BGR2HSV)
        self.frame = cv2.cvtColor(self.frame, cv2.COLOR_BGR2RGB)

        self.colors = []
        if self.escaneando:
            self.draw_osd(self.frame)

        return self.frame 

def decorate_img_for_env(img, env_id, image_scale):
    """
    Args:
        img (numpy array of (width, height, 3)): input image
        env_id (str): the gym env id
        image_scale (float): a scale to resize the image

    Returns:
        an image

    Summary:
        Adds environment specific image decorations. Currently used to make it easier to
        block/label in Pong.

    """
    if env_id is not None and 'Pong' in env_id:
        h, w, _ = img.shape
        est_catastrophe_y = h - 142
        est_block_clearance_y = est_catastrophe_y - int(20 * image_scale)
        # cv2.line(img, (0, est_catastrophe_y), (int(500 * image_scale), est_catastrophe_y), (0, 0, 255))
        cv2.line(img, (250, est_catastrophe_y), (int(500 * image_scale), est_catastrophe_y), (0, 255, 255))
        # cv2.line(img, (0, est_block_clearance_y), (int(500 * image_scale), est_block_clearance_y),
        #          (255, 0, 0))
    return img 

def detect(self, img):
        img_h, img_w, _ = img.shape
        inputs = cv2.resize(img, (self.image_size, self.image_size))
        inputs = cv2.cvtColor(inputs, cv2.COLOR_BGR2RGB).astype(np.float32)
        inputs = (inputs / 255.0) * 2.0 - 1.0
        inputs = np.reshape(inputs, (1, self.image_size, self.image_size, 3))

        result = self.detect_from_cvmat(inputs)[0]

        for i in range(len(result)):
            result[i][1] *= (1.0 * img_w / self.image_size)
            result[i][2] *= (1.0 * img_h / self.image_size)
            result[i][3] *= (1.0 * img_w / self.image_size)
            result[i][4] *= (1.0 * img_h / self.image_size)

        return result 

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 crop(image, name, crop_size, padding_size):
    (width, height) = image.shape
    cropped_images = []
    for i in xrange(0, width, padding_size):
        for j in xrange(0, height, padding_size):
            box = (i, j, i+crop_size, j+crop_size) #left, upper, right, lower
            cropped_name = name + '_' + str(i) + '_' + str(j) + '.jpg'
            cropped_image = image[i:i+crop_size, j:j+crop_size]
            resized_image = cv2.resize(cropped_image, (IMAGE_SIZE, IMAGE_SIZE))
            cropped_images.append(resized_image)
 
    return cropped_images




# ????
# ???????????????????????????????????data_num? 

def get_conv_image_descriptor_for_image(image, model):
    im = cv2.resize(image, (224, 224)).astype(np.float32)
    dim_ordering = K.image_dim_ordering()
    if dim_ordering == 'th':
        # 'RGB'->'BGR'
        im = im[::-1, :, :]
        # Zero-center by mean pixel
        im[0, :, :] -= 103.939
        im[1, :, :] -= 116.779
        im[2, :, :] -= 123.68
    else:
        # 'RGB'->'BGR'
        im = im[:, :, ::-1]
        # Zero-center by mean pixel
        im[:, :, 0] -= 103.939
        im[:, :, 1] -= 116.779
        im[:, :, 2] -= 123.68
    im = im.transpose((2, 0, 1))
    im = np.expand_dims(im, axis=0)
    inputs = [K.learning_phase()] + model.inputs
    _convout1_f = K.function(inputs, [model.layers[31].output])
    return _convout1_f([0] + [im]) 

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 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 RandomCrop(rand_seed,img, top,left,height=224, width=224,u=0.5,aug_factor=9/8):
    #first zoom in by a factor of aug_factor of input img,then random crop by(height,width)
    # if rand_seed < u:
    if 1:
        # h,w,c = img.shape
        # img = cv2.resize(img, (round(aug_factor*w), round(aug_factor*h)), interpolation=cv2.INTER_LINEAR)
        # h, w, c = img.shape

        new_h, new_w = height,width

        # top = np.random.randint(0, h - new_h)
        # left = np.random.randint(0, w - new_w)

        img = img[top: top + new_h,
              left: left + new_w]
    return img 

def __init__(self, dpt, fx, fy, importer=None, refineNet=None):
        """
        Constructor
        :param dpt: depth image
        :param fx: camera focal lenght
        :param fy: camera focal lenght
        """
        self.dpt = dpt
        self.maxDepth = min(1500, dpt.max())
        self.minDepth = max(10, dpt.min())
        # set values out of range to 0
        self.dpt[self.dpt > self.maxDepth] = 0.
        self.dpt[self.dpt < self.minDepth] = 0.
        # camera settings
        self.fx = fx
        self.fy = fy
        # Optional refinement of CoM
        self.refineNet = refineNet
        self.importer = importer
        # depth resize method
        self.resizeMethod = self.RESIZE_CV2_NN 

def resizeCrop(self, crop, sz):
        """
        Resize cropped image
        :param crop: crop
        :param sz: size
        :return: resized image
        """
        if self.resizeMethod == self.RESIZE_CV2_NN:
            rz = cv2.resize(crop, sz, interpolation=cv2.INTER_NEAREST)
        elif self.resizeMethod == self.RESIZE_BILINEAR:
            rz = self.bilinearResize(crop, sz, self.getNDValue())
        elif self.resizeMethod == self.RESIZE_CV2_LINEAR:
            rz = cv2.resize(crop, sz, interpolation=cv2.INTER_LINEAR)
        else:
            raise NotImplementedError("Unknown resize method!")
        return rz 

def get_whole_rotated_image(crop, mask, angle, crop_size, before_rotate_size, scale):
    #Better for larger:
    #pixels_to_jitter = 35 * scale
    #For Dates:
    pixels_to_jitter = 4 #Old Way

    center_x = before_rotate_size / 2 + (random.random() * pixels_to_jitter * 2) - pixels_to_jitter
    center_y = before_rotate_size / 2 + (random.random() * pixels_to_jitter * 2) - pixels_to_jitter

    rot_image = crop.copy()
    rot_image = rotate(rot_image, angle, center_x, center_y, before_rotate_size, before_rotate_size)
    # This is hard coded for 28x28.
    rot_image = cv2.resize(rot_image, (41, 41), interpolation=cv2.INTER_AREA)
    rot_image = rot_image[6:34, 6:34]

    # rot_image = rot_image * mask
    return rot_image 

def resize(im, target_size, max_size):
    """
    only resize input image to target size and return scale
    :param im: BGR image input by opencv
    :param target_size: one dimensional size (the short side)
    :param max_size: one dimensional max size (the long side)
    :return:
    """
    im_shape = im.shape
    im_size_min = np.min(im_shape[0:2])
    im_size_max = np.max(im_shape[0:2])
    im_scale = float(target_size) / float(im_size_min)
    # prevent bigger axis from being more than max_size:
    if np.round(im_scale * im_size_max) > max_size:
        im_scale = float(max_size) / float(im_size_max)
    im = cv2.resize(im, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)
    return im, im_scale 

def resize(im, target_size, max_size):
    """
    only resize input image to target size and return scale
    :param im: BGR image input by opencv
    :param target_size: one dimensional size (the short side)
    :param max_size: one dimensional max size (the long side)
    :return:
    """
    im_shape = im.shape
    im_size_min = np.min(im_shape[0:2])
    im_size_max = np.max(im_shape[0:2])
    im_scale = float(target_size) / float(im_size_min)
    if np.round(im_scale * im_size_max) > max_size:
        im_scale = float(max_size) / float(im_size_max)
    im = cv2.resize(im, None, None, fx=im_scale, fy=im_scale, interpolation=cv2.INTER_LINEAR)
    return im, im_scale 

def predict(image,the_net):
    inputs = []
    try:
        tmp_input = 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
    the_net.blobs['data'].reshape(1, *tmp_input.shape)
    the_net.reshape()
    the_net.blobs['data'].data[...] = tmp_input
    the_net.forward()
    scores = the_net.blobs['prob'].data[0]
    return copy.deepcopy(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[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(image,the_net):
    inputs = []
    try:
        tmp_input = 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
    the_net.blobs['data'].reshape(1, *tmp_input.shape)
    the_net.reshape()
    the_net.blobs['data'].data[...] = tmp_input
    the_net.forward()
    scores = the_net.blobs['prob'].data[0]
    return copy.deepcopy(scores) 

def predict(image,the_net):
    inputs = []
    try:
        tmp_input = 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
    the_net.blobs['data'].reshape(1, *tmp_input.shape)
    the_net.reshape()
    the_net.blobs['data'].data[...] = tmp_input
    the_net.forward()
    scores = the_net.blobs['prob'].data[0]
    return copy.deepcopy(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(image,the_net):
    inputs = []
    try:
        tmp_input = 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
    the_net.blobs['data'].reshape(1, *tmp_input.shape)
    the_net.reshape()
    the_net.blobs['data'].data[...] = tmp_input
    the_net.forward()
    scores = the_net.blobs['prob'].data[0]
    return copy.deepcopy(scores) 

def predict(image,the_net):
    inputs = []
    try:
        tmp_input = 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
    the_net.blobs['data'].reshape(1, *tmp_input.shape)
    the_net.reshape()
    the_net.blobs['data'].data[...] = tmp_input
    the_net.forward()
    scores = the_net.blobs['prob'].data[0]
    return copy.deepcopy(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 __init__(self,
                 folder:str,
                 resize:(int, int),
                 batch_size:int,
                 timesteps:int,
                 windowsteps:int,
                 shift:int,
                 train:bool):
        self.folder  = folder
        self.resize = resize
        self.batch_size = batch_size
        self.timesteps  = timesteps
        self.train = train
        self.images = sorted(os.listdir(folder + 'images/'))
        self.labels = open(folder + 'labels.txt').readlines()
        self.data = self._sliding_window(self.images, shift, windowsteps) 

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 prep_im_for_blob(im, pixel_means, target_size, max_size):
    """Mean subtract and scale an image for use in a blob."""
    im = im.astype(np.float32, copy=False)
    im -= pixel_means
    im = im / 127.5
    im_shape = im.shape
    im_size_min = np.min(im_shape[0:2])
    im_size_max = np.max(im_shape[0:2])
    im_scale = float(target_size) / float(im_size_min)
    # Prevent the biggest axis from being more than MAX_SIZE
    if np.round(im_scale * im_size_max) > max_size:
        im_scale = float(max_size) / float(im_size_max)
    im = cv2.resize(im, None, None, fx=im_scale, fy=im_scale,
                    interpolation=cv2.INTER_LINEAR)

    return im, im_scale 

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 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 _gene_signature(self,wm,size,key):
        '''????????????????????????'''
        wm = cv2.resize(wm,(size,size))        
        wU,_,wV = np.linalg.svd(np.mat(wm))


        sumU = np.sum(np.array(wU),axis=0)
        sumV = np.sum(np.array(wV),axis=0)

        sumU_mid = np.median(sumU)
        sumV_mid = np.median(sumV)

        sumU=np.array([1 if sumU[i] >sumU_mid else 0 for i in range(len(sumU)) ])
        sumV=np.array([1 if sumV[i] >sumV_mid else 0 for i in range(len(sumV)) ])

        uv_xor=np.logical_xor(sumU,sumV)

        np.random.seed(key)
        seq=np.random.randint(2,size=len(uv_xor))

        signature = np.logical_xor(uv_xor, seq)

        sqrts = int(np.sqrt(size))
        return np.array(signature,dtype=np.int8).reshape((sqrts,sqrts)) 

def _gene_signature(self,wm,key):
        '''????????????????????????'''
        wm = cv2.resize(wm,(256,256))        
        wU,_,wV = np.linalg.svd(np.mat(wm))


        sumU = np.sum(np.array(wU),axis=0)
        sumV = np.sum(np.array(wV),axis=0)

        sumU_mid = np.median(sumU)
        sumV_mid = np.median(sumV)

        sumU=np.array([1 if sumU[i] >sumU_mid else 0 for i in range(len(sumU)) ])
        sumV=np.array([1 if sumV[i] >sumV_mid else 0 for i in range(len(sumV)) ])

        uv_xor=np.logical_xor(sumU,sumV)

        np.random.seed(key)
        seq=np.random.randint(2,size=len(uv_xor))

        signature = np.logical_xor(uv_xor, seq)
        return np.array(signature,dtype=np.int8) 

def create_heatmaps(img, pred):
    """
    Uses objectness probability to draw a heatmap on the image and returns it
    """
    # find anchors with highest prediction
    best_pred = np.max(pred[..., 0], axis=-1)
    # convert probabilities to colormap scale
    best_pred = np.uint8(best_pred * 255)
    # apply color map
    # cv2 colormaps create BGR, not RGB
    cmap = cv2.cvtColor(cv2.applyColorMap(best_pred, cv2.COLORMAP_JET), cv2.COLOR_BGR2RGB)
    # resize the color map to fit image
    cmap = cv2.resize(cmap, img.shape[1::-1], interpolation=cv2.INTER_NEAREST)

    # overlay cmap with image
    return cv2.addWeighted(cmap, 1, img, 0.5, 0) 

def swap(self,head_name,face_path):
        '''
        ??? ????
        head_name?
            ?????????
        face_path:
            ?????????
        '''
        im_head,landmarks_head,im_face,landmarks_face=self.resize(*self.heads[head_name],*self.read_and_mark(face_path))
        M = self.transformation_from_points(landmarks_head[self.ALIGN_POINTS],
                                       landmarks_face[self.ALIGN_POINTS])
        
        face_mask = self.get_face_mask(im_face, landmarks_face)
        warped_mask = self.warp_im(face_mask, M, im_head.shape)
        combined_mask = np.max([self.get_face_mask(im_head, landmarks_head), warped_mask],
                                  axis=0)
        
        warped_face = self.warp_im(im_face, M, im_head.shape)
        warped_corrected_im2 = self.correct_colours(im_head, warped_face, landmarks_head)
        
        out=im_head * (1.0 - combined_mask) + warped_corrected_im2 * combined_mask
        return out 

def detect(img):
    img_h, img_w, _ = img.shape
    inputs = cv2.resize(img, (settings.image_size, settings.image_size))
    inputs = cv2.cvtColor(inputs, cv2.COLOR_BGR2RGB).astype(np.float32)
    inputs = (inputs / 255.0) * 2.0 - 1.0
    inputs = np.reshape(inputs, (1, settings.image_size, settings.image_size, 3))
    result = detect_from_cvmat(inputs)[0]
    print result

    for i in range(len(result)):
        result[i][1] *= (1.0 * img_w / settings.image_size)
        result[i][2] *= (1.0 * img_h / settings.image_size)
        result[i][3] *= (1.0 * img_w / settings.image_size)
        result[i][4] *= (1.0 * img_h / settings.image_size)

    return result