Tensorflow transfer learning fine tunning 改进图像训练结果实践_it will cease to work in graphdef version 9. use t

作者：繁依Fanyi0 | 2024-02-16 17:43:40

踩

it will cease to work in graphdef version 9. use tf.nn.batch_normalization()

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。 
1

–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

声明：本文内容由网友自发贡献，不代表【wpsshop博客】立场，版权归原作者所有，本站不承担相应法律责任。如您发现有侵权的内容，请联系我们。转载请注明出处：https://www.wpsshop.cn/w/繁依Fanyi0/article/detail/95743