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
@@ -1,61 +1,61 @@
|
||||
# -- encoding: utf-8 --
|
||||
|
||||
"""
|
||||
Description:
|
||||
Create: 2025/01/17
|
||||
"""
|
||||
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 ImgDenoise(Mapper):
|
||||
def __init__(self, *args, **kwargs):
|
||||
super(ImgDenoise, self).__init__(*args, **kwargs)
|
||||
self._denoise_threshold = kwargs.get("denoise_threshold", 8)
|
||||
|
||||
@staticmethod
|
||||
def _denoise_image(data: object):
|
||||
"""降噪处理"""
|
||||
return cv2.medianBlur(data, 3)
|
||||
|
||||
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:
|
||||
data = bytes_transform.bytes_to_numpy(img_bytes)
|
||||
denoise_images = self._denoise_images_filter(data, file_name)
|
||||
sample[self.data_key] = bytes_transform.numpy_to_bytes(denoise_images, file_type)
|
||||
logger.info(f"fileName: {file_name}, method: ImgDenoise costs {time.time() - start:6f} s")
|
||||
return sample
|
||||
|
||||
def _denoise_images_filter(self, ori_img, file_name):
|
||||
# 获取原始图片的去噪图片
|
||||
clean_data = self._denoise_image(ori_img)
|
||||
# 为方便与其他图片比较可以将图片resize到同一个大小
|
||||
ori = cv2.resize(ori_img, (112, 112))
|
||||
dst = cv2.resize(clean_data, (112, 112))
|
||||
# 计算未降噪图片的灰度值的集合
|
||||
signal = np.sum(ori ** 2)
|
||||
# 计算未降噪图片的灰度值与去噪图片灰度值的差值的集合
|
||||
noise = np.sum((ori - dst) ** 2)
|
||||
# 根据未去噪图片和差值计算snr (图片信噪比)
|
||||
snr = 10 * np.log10(signal / noise)
|
||||
# 对于小于阈值的图片，进行降噪处理
|
||||
if snr < self._denoise_threshold:
|
||||
logger.info(f"The image denoise is {self._denoise_threshold}, "
|
||||
f"which exceeds the threshold of {snr}. {file_name} is filtered out.")
|
||||
return clean_data
|
||||
return ori_img
|
||||
# -- encoding: utf-8 --␍␍
|
||||
␍␍
|
||||
"""␍␍
|
||||
Description:␍␍
|
||||
Create: 2025/01/17␍␍
|
||||
"""␍␍
|
||||
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 ImgDenoise(Mapper):␍␍
|
||||
def __init__(self, *args, **kwargs):␍␍
|
||||
super(ImgDenoise, self).__init__(*args, **kwargs)␍␍
|
||||
self._denoise_threshold = kwargs.get("denoise_threshold", 8)␍␍
|
||||
␍␍
|
||||
@staticmethod␍␍
|
||||
def _denoise_image(data: object):␍␍
|
||||
"""降噪处理"""␍␍
|
||||
return cv2.medianBlur(data, 3)␍␍
|
||||
␍␍
|
||||
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:␍␍
|
||||
data = bytes_transform.bytes_to_numpy(img_bytes)␍␍
|
||||
denoise_images = self._denoise_images_filter(data, file_name)␍␍
|
||||
sample[self.data_key] = bytes_transform.numpy_to_bytes(denoise_images, file_type)␍␍
|
||||
logger.info(f"fileName: {file_name}, method: ImgDenoise costs {time.time() - start:.6f} s")␍␍
|
||||
return sample␍␍
|
||||
␍␍
|
||||
def _denoise_images_filter(self, ori_img, file_name):␍␍
|
||||
# 获取原始图片的去噪图片␍␍
|
||||
clean_data = self._denoise_image(ori_img)␍␍
|
||||
# 为方便与其他图片比较可以将图片resize到同一个大小␍␍
|
||||
ori = cv2.resize(ori_img, (112, 112))␍␍
|
||||
dst = cv2.resize(clean_data, (112, 112))␍␍
|
||||
# 计算未降噪图片的灰度值的集合␍␍
|
||||
signal = np.sum(ori ** 2)␍␍
|
||||
# 计算未降噪图片的灰度值与去噪图片灰度值的差值的集合␍␍
|
||||
noise = np.sum((ori - dst) ** 2)␍␍
|
||||
# 根据未去噪图片和差值计算snr (图片信噪比)␍␍
|
||||
snr = 10 * np.log10(signal / noise)␍␍
|
||||
# 对于小于阈值的图片，进行降噪处理␍␍
|
||||
if snr < self._denoise_threshold:␍␍
|
||||
logger.info(f"The image denoise is {self._denoise_threshold}, "␍␍
|
||||
f"which exceeds the threshold of {snr}. {file_name} is filtered out.")␍␍
|
||||
return clean_data␍␍
|
||||
return ori_img␍␍
|
||||
|
||||
Reference in New Issue
Block a user