将 tensorflow.contrib.slim 导入为 slim ModuleNotFoundError: No module named 'tensorflow.contrib' 修改代码使用于TensorFlow2.x

在 TensorFlow 2.x 中，`tensorflow.contrib` 已经被移除了。为了使用Slim，可以按照以下步骤进行：

1. 安装 TensorFlow 2.x 和 TensorFlow Addons（用于一些额外的功能）:

!pip install tensorflow==2.5.0
!pip install tensorflow-addons

2. 导入 `tensorflow_addons` 和 `tensorflow.keras`:

import tensorflow_addons as tfa
import tensorflow.keras as keras

3. 通过 `keras` 导入 `slim`:

from tensorflow.keras import layers
from tensorflow.keras import backend as K
from tensorflow.keras.models import Model

from tensorflow.keras.applications import imagenet_utils
from tensorflow.keras.applications import ResNet50

from tensorflow.keras.preprocessing.image import img_to_array
from tensorflow.keras.preprocessing.image import load_img

from tensorflow.keras.applications.mobilenet_v2 import MobileNetV2
from tensorflow.keras.applications.mobilenet_v2 import preprocess_input as mobilenet_v2_preprocess_input

from tensorflow.keras.applications.inception_v3 import InceptionV3
from tensorflow.keras.applications.inception_v3 import preprocess_input as inception_v3_preprocess_input

from tensorflow.keras.applications.vgg16 import VGG16
from tensorflow.keras.applications.vgg16 import preprocess_input as vgg16_preprocess_input

from tensorflow.keras.applications.resnet_v2 import ResNet50V2
from tensorflow.keras.applications.resnet_v2 import preprocess_input as resnet_v2_preprocess_input

from tensorflow.keras.applications.efficientnet import EfficientNetB0
from tensorflow.keras.applications.efficientnet import preprocess_input as efficientnet_preprocess_input

from tensorflow.keras.applications.nasnet import NASNetMobile
from tensorflow.keras.applications.nasnet import preprocess_input as nasnet_preprocess_input

from tensorflow.keras.applications.xception import Xception
from tensorflow.keras.applications.xception import preprocess_input as xception_preprocess_input

import tensorflow_hub as hub

from typing import List, Tuple
import numpy as np
import cv2

这样就可以使用 Slim 的一些功能了。需要注意的是，Slim 在 TensorFlow 2.x 中已经不是官方支持的模块，因此在使用时需要自行承担风险。