数据增强之Mosaic和Cutmix的pytorch实现

Mosaic 

    def get_random_data_with_Mosaic(self, annotation_line, input_shape, hue=.1, sat=1.5, val=1.5):
        h, w = input_shape
        min_offset_x = 0.3
        min_offset_y = 0.3
        scale_low = 1 - min(min_offset_x, min_offset_y)
        scale_high = scale_low + 0.2

        image_datas = []
        box_datas = []
        index = 0

        place_x = [0, 0, int(w * min_offset_x), int(w * min_offset_x)]
        place_y = [0, int(h * min_offset_y), int(w * min_offset_y), 0]
        for line in annotation_line:
            # 每一行进行分割
            line_content = line.split()
            # 打开图片
            image = Image.open(line_content[0])
            image = image.convert("RGB")
            # 图片的大小
            iw, ih = image.size
            # 保存框的位置
            box = np.array([np.array(list(map(int, box.split(',')))) for box in line_content[1:]])

            # 是否翻转图片
            flip = self.rand() < .5
            if flip and len(box) > 0:
                image = image.transpose(Image.FLIP_LEFT_RIGHT)
                box[:, [0, 2]] = iw - box[:, [2, 0]]

            # 对输入进来的图片进行缩放
            new_ar = w / h
            scale = self.rand(scale_low, scale_high)
            if new_ar < 1:
                nh = int(scale * h)
                nw = int(nh * new_ar)
            else:
                nw = int(scale * w)
                nh = int(nw / new_ar)
            image = image.resize((nw, nh), Image.BICUBIC)

            # 进行色域变换
            hue = self.rand(-hue, hue)
            sat = self.rand(1, sat) if self.rand() < .5 else 1 / self.rand(1, sat)
            val = self.rand(1, val) if self.rand() < .5 else 1 / self.rand(1, val)
            x = cv2.cvtColor(np.array(image,np.float32)/255, cv2.COLOR_RGB2HSV)
            x[..., 0] += hue*360
            x[..., 0][x[..., 0]>1] -= 1
            x[..., 0][x[..., 0]<0] += 1
            x[..., 1] *= sat
            x[..., 2] *= val
            x[x[:,:, 0]>360, 0] = 360
            x[:, :, 1:][x[:, :, 1:]>1] = 1
            x[x<0] = 0
            image = cv2.cvtColor(x, cv2.COLOR_HSV2RGB) # numpy array, 0 to 1

            image = Image.fromarray((image * 255).astype(np.uint8))
            # 将图片进行放置，分别对应四张分割图片的位置
            dx = place_x[index]
            dy = place_y[index]
            new_image = Image.new('RGB', (w, h),
                                  (np.random.randint(0, 255), np.random.randint(0, 255), np.random.randint(0, 255)))
            new_image.paste(image, (dx, dy))
            image_data = np.array(new_image)

            index = index + 1
            box_data = []
            # 对box进行重新处理
            if len(box) > 0:
                np.random.shuffle(box)
                box[:, [0, 2]] = box[:, [0, 2]] * nw / iw + dx
                box[:, [1, 3]] = box[:, [1, 3]] * nh / ih + dy
                box[:, 0:2][box[:, 0:2] < 0] = 0
                box[:, 2][box[:, 2] > w] = w
                box[:, 3][box[:, 3] > h] = h
                box_w = box[:, 2] - box[:, 0]
                box_h = box[:, 3] - box[:, 1]
                box = box[np.logical_and(box_w > 1, box_h > 1)]
                box_data = np.zeros((len(box), 5))
                box_data[:len(box)] = box

            image_datas.append(image_data)
            box_datas.append(box_data)

        # 将图片分割，放在一起
        cutx = np.random.randint(int(w * min_offset_x), int(w * (1 - min_offset_x)))
        cuty = np.random.randint(int(h * min_offset_y), int(h * (1 - min_offset_y)))

        new_image = np.zeros([h, w, 3])
        new_image[:cuty, :cutx, :] = image_datas[0][:cuty, :cutx, :]
        new_image[cuty:, :cutx, :] = image_datas[1][cuty:, :cutx, :]
        new_image[cuty:, cutx:, :] = image_datas[2][cuty:, cutx:, :]
        new_image[:cuty, cutx:, :] = image_datas[3][:cuty, cutx:, :]

        # 对框进行进一步的处理
        new_boxes = np.array(merge_bboxes(box_datas, cutx, cuty))

        if len(new_boxes) == 0:
            return new_image, []
        if (new_boxes[:, :4] > 0).any():
            return new_image, new_boxes
        else:
            return new_image, []

Cutmix实现有误。删掉了