使用本地预训练模型迁移学习

最新推荐文章于 2024-08-31 21:55:55 发布

追梦小狂魔

最新推荐文章于 2024-08-31 21:55:55 发布

阅读量655

点赞数

分类专栏： python 文章标签： tensorflow 深度学习神经网络 python 迁移学习

本文链接：https://blog.csdn.net/qq_15557299/article/details/104378840

版权

python 专栏收录该内容

120 篇文章 5 订阅

订阅专栏

from tensorflow.python.keras.models import Sequential
from tensorflow.python.keras.layers import Dense, Flatten, GlobalAveragePooling2D
import tensorflow as  tf
num_classes = 2
resnet_weights_path = './resnet101_weights_tf_dim_ordering_tf_kernels.h5'

my_new_model = Sequential()
my_new_model.add(tf.keras.applications.resnet.ResNet101( weights=resnet_weights_path))
my_new_model.add(Dense(num_classes, activation='softmax'))

# Say not to train first layer (ResNet) model. It is already trained