aidlab/AiDA_Python
6
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat:

Browse Source 
fix:  替换项目中所有mmcv的依赖
This commit is contained in:
zcr
2026-02-10 11:17:31 +08:00
parent 23a6a30cc4
commit bafcb68028
16 changed files with 74 additions and 121 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
app/service/attribute/service_att_recognition.py
View File

@@ -3,7 +3,6 @@
from pprint import pprint
import cv2
import mmcv
import numpy as np
import pandas as pd
import torch
@@ -12,6 +11,7 @@ from minio import Minio
from app.core.config import settings, DESIGN_MODEL_URL
from app.schemas.attribute_retrieve import AttributeRecognitionModel
from app.service.utils.image_normalize import my_imnormalize
from app.service.utils.new_oss_client import oss_get_image
minio_client = Minio(settings.MINIO_URL, access_key=settings.MINIO_ACCESS, secret_key=settings.MINIO_SECRET, secure=settings.MINIO_SECURE)
@@ -109,10 +109,9 @@ class AttributeRecognition:
@staticmethod
def preprocess(img):
img = mmcv.imread(img)
img_scale = (224, 224)
img = cv2.resize(img, img_scale)
img = mmcv.imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
img = my_imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
preprocessed_img = np.expand_dims(img.transpose(2, 0, 1), axis=0)
return preprocessed_img

5
app/service/attribute/service_category_recognition.py
View File

@@ -10,7 +10,6 @@
from minio import Minio
from skimage import transform
import cv2
import mmcv
import numpy as np
import pandas as pd
import tritonclient.http as httpclient
@@ -18,6 +17,7 @@ import torch
from app.core.config import settings, DESIGN_MODEL_URL
from app.schemas.attribute_retrieve import CategoryRecognitionModel
from app.service.utils.image_normalize import my_imnormalize
from app.service.utils.new_oss_client import oss_get_image
minio_client = Minio(settings.MINIO_URL, access_key=settings.MINIO_ACCESS, secret_key=settings.MINIO_SECRET, secure=settings.MINIO_SECURE)
@@ -39,11 +39,10 @@ class CategoryRecognition:
@staticmethod
def preprocess(img):
img = mmcv.imread(img)
# ori_shape = img.shape[:2]
img_scale = (224, 224)
img = cv2.resize(img, img_scale)
img = mmcv.imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
img = my_imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
preprocessed_img = np.expand_dims(img.transpose(2, 0, 1), axis=0)
return preprocessed_img

11
app/service/brand_dna/service.py
View File

@@ -1,7 +1,6 @@
import logging
import cv2
import mmcv
import numpy as np
import pandas as pd
import torch
@@ -14,6 +13,7 @@ from app.core.config import settings
from app.schemas.brand_dna import BrandDnaModel
from app.service.attribute.config import const
from app.service.utils.generate_uuid import generate_uuid
from app.service.utils.image_normalize import my_imnormalize
from app.service.utils.new_oss_client import oss_upload_image, oss_get_image
minio_client = Minio(settings.MINIO_URL, access_key=settings.MINIO_ACCESS, secret_key=settings.MINIO_SECRET, secure=settings.MINIO_SECURE)
@@ -202,7 +202,7 @@ class BrandDna:
# 服装分割预处理
@staticmethod
def seg_product_preprocess(image):
img = mmcv.imread(image)
img = image
ori_shape = img.shape[:2]
img_scale_w, img_scale_h = ori_shape
if ori_shape[0] > 1024:
@@ -211,9 +211,9 @@ class BrandDna:
img_scale_h = 1024
# 如果图片size任意一边 大于 1024， 则会resize 成1024
if ori_shape != (img_scale_w, img_scale_h):
# mmcv.imresize(img, img_scale_h, img_scale_w) # 老代码 引以为戒！哈哈哈~ h和w写反了
# my_imnormalize(img, img_scale_h, img_scale_w) # 老代码 引以为戒！哈哈哈~ h和w写反了
img = cv2.resize(img, (img_scale_h, img_scale_w))
img = mmcv.imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
img = my_imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
preprocessed_img = np.expand_dims(img.transpose(2, 0, 1), axis=0)
return preprocessed_img, ori_shape
@@ -227,11 +227,10 @@ class BrandDna:
# 类别检测模型预处理
@staticmethod
def category_preprocess(img):
img = mmcv.imread(img)
# ori_shape = img.shape[:2]
img_scale = (224, 224)
img = cv2.resize(img, img_scale)
img = mmcv.imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
img = my_imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
preprocessed_img = np.expand_dims(img.transpose(2, 0, 1), axis=0)
return preprocessed_img

12
app/service/design_batch/utils/design_ensemble.py
View File

@@ -10,13 +10,13 @@
import logging
import cv2
import mmcv
import numpy as np
import torch
import torch.nn.functional as F
import tritonclient.http as httpclient
from app.core.config import DESIGN_MODEL_URL, DESIGN_MODEL_NAME
from app.service.utils.image_normalize import my_imnormalize
"""
keypoint
@@ -25,13 +25,13 @@ from app.core.config import DESIGN_MODEL_URL, DESIGN_MODEL_NAME
def keypoint_preprocess(img_path):
img = mmcv.imread(img_path)
img = img_path
img_scale = (256, 256)
h, w = img.shape[:2]
img = cv2.resize(img, img_scale)
w_scale = img_scale[0] / w
h_scale = img_scale[1] / h
img = mmcv.imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
img = my_imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
preprocessed_img = np.expand_dims(img.transpose(2, 0, 1), axis=0)
return preprocessed_img, (w_scale, h_scale)
@@ -74,7 +74,7 @@ def keypoint_postprocess(output, scale_factor):
# KNet
def seg_preprocess(img_path):
img = mmcv.imread(img_path)
img = img_path
ori_shape = img.shape[:2]
img_scale_w, img_scale_h = ori_shape
if ori_shape[0] > 1024:
@@ -83,9 +83,9 @@ def seg_preprocess(img_path):
img_scale_h = 1024
# 如果图片size任意一边 大于 1024， 则会resize 成1024
if ori_shape != (img_scale_w, img_scale_h):
# mmcv.imresize(img, img_scale_h, img_scale_w) # 老代码 引以为戒！哈哈哈~ h和w写反了
# my_imnormalize(img, img_scale_h, img_scale_w) # 老代码 引以为戒！哈哈哈~ h和w写反了
img = cv2.resize(img, (img_scale_h, img_scale_w))
img = mmcv.imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
img = my_imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
preprocessed_img = np.expand_dims(img.transpose(2, 0, 1), axis=0)
return preprocessed_img, ori_shape

12
app/service/design_fast/utils/design_ensemble.py
View File

@@ -10,12 +10,12 @@
import logging
import cv2
import mmcv
import numpy as np
import torch
import tritonclient.http as httpclient
from app.core.config import DESIGN_MODEL_URL, DESIGN_MODEL_NAME
from app.service.utils.image_normalize import my_imnormalize
"""
keypoint
@@ -24,14 +24,14 @@ from app.core.config import DESIGN_MODEL_URL, DESIGN_MODEL_NAME
def keypoint_preprocess(img_path):
img = mmcv.imread(img_path)
img = img_path
img = cv2.copyMakeBorder(img, 25, 25, 25, 25, cv2.BORDER_CONSTANT, value=[255, 255, 255])
img_scale = (256, 256)
h, w = img.shape[:2]
img = cv2.resize(img, img_scale)
w_scale = img_scale[0] / w
h_scale = img_scale[1] / h
img = mmcv.imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
img = my_imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
preprocessed_img = np.expand_dims(img.transpose(2, 0, 1), axis=0)
return preprocessed_img, (w_scale, h_scale)
@@ -78,7 +78,7 @@ def keypoint_postprocess(output, scale_factor):
# KNet
def seg_preprocess(img_path):
img = mmcv.imread(img_path)
img = img_path
ori_shape = img.shape[:2]
img_scale_w, img_scale_h = ori_shape
if ori_shape[0] > 1024:
@@ -87,12 +87,12 @@ def seg_preprocess(img_path):
img_scale_h = 1024
# 如果图片size任意一边 大于 1024， 则会resize 成1024
if ori_shape != (img_scale_w, img_scale_h):
# mmcv.imresize(img, img_scale_h, img_scale_w) # 老代码 引以为戒！哈哈哈~ h和w写反了
# my_imnormalize(img, img_scale_h, img_scale_w) # 老代码 引以为戒！哈哈哈~ h和w写反了
img = cv2.resize(img, (img_scale_h, img_scale_w))
# 扩充25的白边
img = cv2.copyMakeBorder(img, 25, 25, 25, 25, cv2.BORDER_CONSTANT, value=[255, 255, 255])
img = mmcv.imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
img = my_imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
preprocessed_img = np.expand_dims(img.transpose(2, 0, 1), axis=0)
return preprocessed_img, ori_shape

5
app/service/generate_image/service_agent_tool_generate_image.py
View File

@@ -11,7 +11,6 @@ import logging
import uuid
import cv2
import mmcv
import numpy as np
import pandas as pd
import torch
@@ -21,6 +20,7 @@ from minio import Minio
from tritonclient.utils import np_to_triton_dtype
from app.core.config import settings, FAST_GI_MODEL_URL, GI_MODEL_URL, DESIGN_MODEL_URL, FAST_GI_MODEL_NAME, GI_MODEL_NAME
from app.service.utils.image_normalize import my_imnormalize
from app.service.utils.new_oss_client import oss_upload_image
logger = logging.getLogger()
@@ -86,10 +86,9 @@ class AgentToolGenerateImage:
@staticmethod
def preprocess(img):
img = mmcv.imread(img)
img_scale = (224, 224)
img = cv2.resize(img, img_scale)
img = mmcv.imnormalize(
img = my_imnormalize(
img,
mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]),
to_rgb=True)

4
app/service/generate_image/service_generate_image.py
View File

@@ -189,10 +189,10 @@ if __name__ == '__main__':
tasks_id="123-89",
prompt="a single item of sketch of dress, 4k, white background",
image_url="aida-collection-element/89/Sketchboard/95f20cdc-e059-435c-b8b1-d04cc9e80c3d.png",
mode='img2img',
mode='txt2img',
category="sketch",
gender="Female",
version="fast"
version="hight"
)
server = GenerateImage(rd)
print(server.get_result())

9
app/service/generate_image/utils/image_processing.py
View File

@@ -2,23 +2,23 @@ import logging
import time
import cv2
import mmcv
import numpy as np
import torch
import tritonclient.http as httpclient
from app.core.config import settings, DESIGN_MODEL_URL, DESIGN_MODEL_NAME
from app.service.generate_image.utils.upload_sd_image import upload_stain_png_sd, upload_face_png_sd
from app.service.utils.image_normalize import my_imnormalize
logger = logging.getLogger()
def seg_preprocess(img_path):
img = mmcv.imread(img_path)
img = img_path
ori_shape = img.shape[:2]
img_scale = ori_shape
img = cv2.resize(img, img_scale)
img = mmcv.imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
img = my_imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
preprocessed_img = np.expand_dims(img.transpose(2, 0, 1), axis=0)
return preprocessed_img, ori_shape
@@ -242,10 +242,9 @@ def stain_detection(image, user_id, category, tasks_id, spot_size=100):
def generate_category_recognition(image, gender):
def preprocess(img):
img = mmcv.imread(img)
img_scale = (224, 224)
img = cv2.resize(img, img_scale)
img = mmcv.imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
img = my_imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
preprocessed_img = np.expand_dims(img.transpose(2, 0, 1), axis=0)
return preprocessed_img

8
app/service/lineart/service.py
View File

@@ -1,7 +1,6 @@
import logging
import cv2
import mmcv
import numpy as np
import torch
import torch.nn.functional as F
@@ -10,6 +9,7 @@ from minio import Minio
from app.core.config import settings
from app.core.config import DESIGN_MODEL_URL
from app.schemas.image2sketch import Image2SketchModel
from app.service.utils.image_normalize import my_imnormalize
from app.service.utils.new_oss_client import oss_get_image, oss_upload_image
logger = logging.getLogger()
@@ -67,7 +67,7 @@ class LineArtService:
@staticmethod
def line_art_preprocess(image):
img = mmcv.imread(image)
img = image
ori_shape = img.shape[:2]
img_scale_w, img_scale_h = ori_shape
if ori_shape[0] > 1024:
@@ -76,9 +76,9 @@ class LineArtService:
img_scale_h = 1024
# 如果图片size任意一边 大于 1024， 则会resize 成1024
if ori_shape != (img_scale_w, img_scale_h):
# mmcv.imresize(img, img_scale_h, img_scale_w) # 老代码 引以为戒！哈哈哈~ h和w写反了
# my_imnormalize(img, img_scale_h, img_scale_w) # 老代码 引以为戒！哈哈哈~ h和w写反了
img = cv2.resize(img, (img_scale_h, img_scale_w))
img = mmcv.imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
img = my_imnormalize(img, mean=np.array([123.675, 116.28, 103.53]), std=np.array([58.395, 57.12, 57.375]), to_rgb=True)
preprocessed_img = np.expand_dims(img.transpose(2, 0, 1), axis=0)
return preprocessed_img, ori_shape

27
app/service/utils/image_normalize.py Normal file
View File

@@ -0,0 +1,27 @@
import cv2
import np
def my_imnormalize(img, mean, std, to_rgb=True):
"""Inplace normalize an image with mean and std.
Args:
img (ndarray): Image to be normalized.
mean (ndarray): The mean to be used for normalize.
std (ndarray): The std to be used for normalize.
to_rgb (bool): Whether to convert to rgb.
Returns:
ndarray: The normalized image.
"""
# cv2 inplace normalization does not accept uint8
img = img.copy().astype(np.float32)
assert img.dtype != np.uint8
mean = np.float64(mean.reshape(1, -1))
stdinv = 1 / np.float64(std.reshape(1, -1))
if to_rgb:
cv2.cvtColor(img, cv2.COLOR_BGR2RGB, img) # inplace
cv2.subtract(img, mean, img) # inplace
cv2.multiply(img, stdinv, img) # inplace
return img