feat(deepdata): 引入修改密码、文件预览组件与清洗算子增强，deepflow 改名为 deep-flow
本次同步 09-12 至 09-28 的代码变更，主要内容： 新增功能 - 修改密码：后端新增 ChangePasswordRequest DTO 与UserController/UserService 对应接口，前端新增 ChangePasswordDialog 并在 Header 接入入口 - 文件预览组件重构：file-preview 目录拆分出 VideoPreview（支持 blobUrl 直传）、 ImagePreview、AudioPreview，index.tsx 统一调度各类型预览器 - 新增 my_ops 算子模块：markitdown_parser、mineru_pdf_parser、text_quality_evaluator - 新增 tools/minio-file-server MinIO 文件服务 功能增强 - 数据清洗：cleaning_task_service/scheduler/routes 重构， data_juicer_executor 与 wrapper 增强，OperatorTable/LogsTable/TaskDetail 同步调整 - 数据标注：annotation sync.py、project.py 接口与schema 更新 - 数据采集、算子市场、首页与菜单路由相关页面调整 - DataJuicer 算子接入（useOperatorOperations、dj_ops_schema） 结构调整 - deepflow/ 更名为 deep-flow/（419 个文件重命名） - 新增 helm 部署编排、GitHub Actions 之外的自建镜像构建脚本 未纳入本次提交 - scripts-backup/、runtime/python-executor-backup/、components_backup/（备份目录） - *.backup*、__pycache__ 产物 - zh_core_web_sm-3.8.0-py3-none-any.whl（46MB 构建产物） - DataX/（内嵌独立仓库，远程亦未收录其源码）
This commit is contained in:
沃巴蒂
@@ -1,73 +1,73 @@
|
||||
# -- encoding: utf-8 --
|
||||
|
||||
"""
|
||||
Description: 图片去阴影插件
|
||||
Create: 2025/01/16
|
||||
"""
|
||||
import time
|
||||
|
||||
from typing import Dict, Any
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
from loguru import logger
|
||||
|
||||
from deepdata.common.utils import bytes_transform
|
||||
from deepdata.core.base_op import Mapper
|
||||
|
||||
|
||||
class ImgShadowRemove(Mapper):
|
||||
"""图片阴影去除"""
|
||||
|
||||
def __init__(self, *args, **kwargs):
|
||||
super(ImgShadowRemove, self).__init__(*args, **kwargs)
|
||||
self.iter_nums = 9 # 闭运算循环次数(不作为参数传入)。
|
||||
self.k_size = 3 # kernel size大小。
|
||||
self.clip_limit = 2 # 对比度限制阈值, 数值越大，效果越强。
|
||||
self.tile_grid = 8 # 图像划分的网格大小, 数值越小，局部效果越明显。
|
||||
|
||||
def shadow_removed(self, image_data: np.ndarray):
|
||||
'''
|
||||
阴影去除。
|
||||
|
||||
Args:
|
||||
image_data: nd.array 格式图片
|
||||
Returns:
|
||||
阴影去除后的图片
|
||||
'''
|
||||
# 设置kernel大小，进行闭运算
|
||||
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (self.k_size, self.k_size))
|
||||
closing = cv2.morphologyEx(image_data, cv2.MORPH_CLOSE, kernel, iterations=self.iter_nums)
|
||||
|
||||
# 进行~（closing - original）操作
|
||||
cv2.bitwise_not(closing - image_data, dst=closing)
|
||||
cv2.cvtColor(closing, cv2.COLOR_BGR2Lab, dst=closing)
|
||||
|
||||
# 获取处理后图像的亮度通道
|
||||
img_l = cv2.split(closing)[0]
|
||||
del closing
|
||||
|
||||
# 对img_l进行调节后，替换原图的亮度通道
|
||||
cv2.cvtColor(image_data, cv2.COLOR_BGR2Lab, dst=image_data)
|
||||
# 创建 CLAHE 对象
|
||||
clahe = cv2.createCLAHE(clipLimit=self.clip_limit, tileGridSize=(self.tile_grid, self.tile_grid))
|
||||
# 进行 CLAHE 处理
|
||||
image_data[:, :, 0] = clahe.apply(img_l)
|
||||
del img_l
|
||||
|
||||
cv2.cvtColor(image_data, cv2.COLOR_Lab2BGR, dst=image_data)
|
||||
return image_data
|
||||
|
||||
def execute(self, sample: Dict[str, Any]):
|
||||
start = time.time()
|
||||
self.read_file_first(sample)
|
||||
img_bytes = sample[self.data_key]
|
||||
file_name = sample[self.filename_key]
|
||||
file_type = "." + sample[self.filetype_key]
|
||||
if img_bytes:
|
||||
# 进行阴影去除
|
||||
img_data = bytes_transform.bytes_to_numpy(img_bytes)
|
||||
img_data = self.shadow_removed(img_data)
|
||||
sample[self.data_key] = bytes_transform.numpy_to_bytes(img_data, file_type)
|
||||
logger.info(f"fileName: {file_name}, method: ImageShadowRemove costs {time.time() - start:6f} s")
|
||||
return sample
|
||||
# -- encoding: utf-8 --␍␍
|
||||
␍␍
|
||||
"""␍␍
|
||||
Description: 图片去阴影插件␍␍
|
||||
Create: 2025/01/16␍␍
|
||||
"""␍␍
|
||||
import time␍␍
|
||||
␍␍
|
||||
from typing import Dict, Any␍␍
|
||||
␍␍
|
||||
import cv2␍␍
|
||||
import numpy as np␍␍
|
||||
from loguru import logger␍␍
|
||||
␍␍
|
||||
from deepdata.common.utils import bytes_transform␍␍
|
||||
from deepdata.core.base_op import Mapper␍␍
|
||||
␍␍
|
||||
␍␍
|
||||
class ImgShadowRemove(Mapper):␍␍
|
||||
"""图片阴影去除"""␍␍
|
||||
␍␍
|
||||
def __init__(self, *args, **kwargs):␍␍
|
||||
super(ImgShadowRemove, self).__init__(*args, **kwargs)␍␍
|
||||
self.iter_nums = 9 # 闭运算循环次数(不作为参数传入)。␍␍
|
||||
self.k_size = 3 # kernel size大小。␍␍
|
||||
self.clip_limit = 2 # 对比度限制阈值, 数值越大，效果越强。␍␍
|
||||
self.tile_grid = 8 # 图像划分的网格大小, 数值越小，局部效果越明显。␍␍
|
||||
␍␍
|
||||
def shadow_removed(self, image_data: np.ndarray):␍␍
|
||||
'''␍␍
|
||||
阴影去除。␍␍
|
||||
␍␍
|
||||
Args:␍␍
|
||||
image_data: nd.array 格式图片␍␍
|
||||
Returns:␍␍
|
||||
阴影去除后的图片␍␍
|
||||
'''␍␍
|
||||
# 设置kernel大小，进行闭运算␍␍
|
||||
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (self.k_size, self.k_size))␍␍
|
||||
closing = cv2.morphologyEx(image_data, cv2.MORPH_CLOSE, kernel, iterations=self.iter_nums)␍␍
|
||||
␍␍
|
||||
# 进行~（closing - original）操作␍␍
|
||||
cv2.bitwise_not(closing - image_data, dst=closing)␍␍
|
||||
cv2.cvtColor(closing, cv2.COLOR_BGR2Lab, dst=closing)␍␍
|
||||
␍␍
|
||||
# 获取处理后图像的亮度通道␍␍
|
||||
img_l = cv2.split(closing)[0]␍␍
|
||||
del closing␍␍
|
||||
␍␍
|
||||
# 对img_l进行调节后，替换原图的亮度通道␍␍
|
||||
cv2.cvtColor(image_data, cv2.COLOR_BGR2Lab, dst=image_data)␍␍
|
||||
# 创建 CLAHE 对象␍␍
|
||||
clahe = cv2.createCLAHE(clipLimit=self.clip_limit, tileGridSize=(self.tile_grid, self.tile_grid))␍␍
|
||||
# 进行 CLAHE 处理␍␍
|
||||
image_data[:, :, 0] = clahe.apply(img_l)␍␍
|
||||
del img_l␍␍
|
||||
␍␍
|
||||
cv2.cvtColor(image_data, cv2.COLOR_Lab2BGR, dst=image_data)␍␍
|
||||
return image_data␍␍
|
||||
␍␍
|
||||
def execute(self, sample: Dict[str, Any]) -> Dict[str, Any]:␍␍
|
||||
start = time.time()␍␍
|
||||
self.read_file_first(sample)␍␍
|
||||
img_bytes = sample[self.data_key]␍␍
|
||||
file_name = sample[self.filename_key]␍␍
|
||||
file_type = "." + sample[self.filetype_key]␍␍
|
||||
if img_bytes:␍␍
|
||||
# 进行阴影去除␍␍
|
||||
img_data = bytes_transform.bytes_to_numpy(img_bytes)␍␍
|
||||
img_data = self.shadow_removed(img_data)␍␍
|
||||
sample[self.data_key] = bytes_transform.numpy_to_bytes(img_data, file_type)␍␍
|
||||
logger.info(f"fileName: {file_name}, method: ImageShadowRemove costs {time.time() - start:.6f} s")␍␍
|
||||
return sample␍␍
|
||||
|
||||
Reference in New Issue
Block a user