Merge branch 'refs/heads/local'

# Conflicts:
#	app/service/attribute/service_att_recognition.py
#	app/service/design/utils/design_ensemble.py
#	app/service/generate_image/utils/image_processing.py

app/service/attribute/service_att_recognition.py

@@ -1,14 +1,14 @@
 #!/usr/bin/env python
 # -*- coding: UTF-8 -*-
+import logging
 from pprint import pprint
-
+import torch
 import cv2
 import mmcv
 import numpy as np
 import pandas as pd
-import torch
+from minio import Minio
 import tritonclient.http as httpclient
-
 from app.core.config import *
 from app.schemas.attribute_retrieve import AttributeRecognitionModel
 from app.service.utils.oss_client import oss_get_image
@@ -108,7 +108,7 @@ class AttributeRecognition:
     def preprocess(img):
         img = mmcv.imread(img)
         img_scale = (224, 224)
-        img = cv2.resize(img, img_scale, interpolation=cv2.INTER_LINEAR)
+        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)
         preprocessed_img = np.expand_dims(img.transpose(2, 0, 1), axis=0)
         return preprocessed_img

app/service/attribute/service_category_recognition.py

@@ -41,10 +41,7 @@ class CategoryRecognition:
         img = mmcv.imread(img)
         # ori_shape = img.shape[:2]
         img_scale = (224, 224)
-        scale_factor = []
-        img, x, y = mmcv.imresize(img, img_scale, return_scale=True)
-        scale_factor.append(x)
-        scale_factor.append(y)
+        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)
         preprocessed_img = np.expand_dims(img.transpose(2, 0, 1), axis=0)
         return preprocessed_img

app/service/design/utils/design_ensemble.py

@@ -28,9 +28,9 @@ def keypoint_preprocess(img_path):
     img = mmcv.imread(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 = cv2.resize(img, img_scale, interpolation=cv2.INTER_LINEAR)
     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)
     preprocessed_img = np.expand_dims(img.transpose(2, 0, 1), axis=0)
     return preprocessed_img, (w_scale, h_scale)
@@ -84,7 +84,7 @@ def seg_preprocess(img_path):
     # 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
-        img = cv2.resize(img, (img_scale_h, img_scale_w), interpolation=cv2.INTER_LINEAR)
+        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)
     preprocessed_img = np.expand_dims(img.transpose(2, 0, 1), axis=0)
     return preprocessed_img, ori_shape

app/service/generate_image/utils/image_processing.py

@@ -16,14 +16,8 @@ logger = logging.getLogger()
 def seg_preprocess(img_path):
     img = mmcv.imread(img_path)
     ori_shape = img.shape[:2]
-    img_scale_w, img_scale_h = ori_shape
-    if ori_shape[0] > 1024:
-        img_scale_w = 1024
-    if ori_shape[1] > 1024:
-        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):
-        img = cv2.resize(img, (img_scale_h, img_scale_w), interpolation=cv2.INTER_LINEAR)
+    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)
     preprocessed_img = np.expand_dims(img.transpose(2, 0, 1), axis=0)
     return preprocessed_img, ori_shape
@@ -249,12 +243,8 @@ 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)
-        # ori_shape = img.shape[:2]
         img_scale = (224, 224)
-        scale_factor = []
-        img, x, y = mmcv.imresize(img, img_scale, return_scale=True)
-        scale_factor.append(x)
-        scale_factor.append(y)
+        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)
         preprocessed_img = np.expand_dims(img.transpose(2, 0, 1), axis=0)
         return preprocessed_img