Tensorflow transfer learning fine tunning 改进图像训练结果实践
来源:互联网 发布:营销软件sudm 编辑:程序博客网 时间:2024/05/16 10:39
改进图像训练结果的常用方法是通过随机方式变形,裁剪或增亮训练输入
–random_crop
–random_scale
–random_brightness
传递给脚本来启用这些失真。这些都是控制每个图像应用多少失真的百分比值。对于每个值开始使用5或10的值是合理的,然后通过实验看看哪些值有助于的应用程序。
–flip_left_right将水平随机地镜像一半的图像,只要那些颠倒可能发生在你的应用程序。
–random_brightness 5
/media/haijunz/27a263b4-e313-4b58-a422-0201e4cb11ed/tensorflow/tensorflow/tensorflow/examples/image_retraining$ python retrain.py –image_dir /media/haijunz/27a263b4-e313-4b58-a422-0201e4cb11ed/tensorflow/models/flower_photos/data –random_brightness 5
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn’t compiled to use SSE3 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn’t compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn’t compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
Looking for images in ‘roses’
Looking for images in ‘sunflowers’
Looking for images in ‘tulips’
Looking for images in ‘dandelion’
Looking for images in ‘daisy’
W tensorflow/core/framework/op_def_util.cc:332] Op BatchNormWithGlobalNormalization is deprecated. It will cease to work in GraphDef version 9. Use tf.nn.batch_normalization().
2017-03-14 15:08:42.443384: Step 0: Train accuracy = 69.0%
2017-03-14 15:08:42.443478: Step 0: Cross entropy = 1.527363
2017-03-14 15:08:42.596276: Step 0: Validation accuracy = 60.0% (N=100)
……
- Tensorflow transfer learning fine tunning 改进图像训练结果实践
- Tensorflow fine-tunning AlexNet
- transfer learning and fine-tuning
- Fine-tunning适用情况
- Deep learning系列(十三)Transfer learning 和 caffe Fine-tuning
- Tensorflow 训练结果为 NAN
- 迁移学习(transfer learning)和微调(fine-tune)的几点认识
- caffe image recognization model and prototxt for transfer learning (fine-tuning)
- Borrowing treasures from the wealthy: deep transfer learning through selective joint fine-tuning
- transfer learning
- transfer learning
- Transfer Learning
- Transfer Learning
- Transfer Learning
- Transfer Learning
- Transfer Learning
- Transfer Learning
- transfer learning
- Android学习笔记之蓝牙
- Zookeeper 集群+kafka集群+kafka manager搭建
- 路径不显示图片
- Spring学习心得(14)--cglib动态代理
- JAVA面试题及答案解析
- Tensorflow transfer learning fine tunning 改进图像训练结果实践
- ACM日记_17.3.14——输入均为独立字母与数字时的处理
- Centos 启动盘制作与安装
- mac,finder ,dock
- javascript Math.random的使用
- V4L2采集图像基本流程
- Java复制文件:字节流、字符流、数据流
- memcached安装步骤
- 梯度下降(Gradient Descent)小结