TensorFlow 2.0中不再提供投影转换,我该怎么办? [英] Projective transformations no longer available in TensorFlow 2.0 what can I do?
问题描述
我的团队正在切换到TensorFlow 2.0。我正在研究数据扩充管道。 TensorFlow 1.X的 tf.contrib.image.transform
允许进行投影转换。 TensorFlow在 tf.image
中没有转换功能,当然也没有 tf.contrib
模块
My team are switching to TensorFlow 2.0. I'm working on a data augmentation pipeline. TensorFlow 1.X had tf.contrib.image.transform
that allows for projective transformations. TensorFlow doesn't have the transform function in tf.image
and it certainly doesn't have a tf.contrib
module.
我考虑了其他用于数据增强的选项:
I considered other options for data augmentation:
- NVIDIA DALI仅允许用于具有6个参数的仿射变换。
- Python包Augmentor支持投影变换,但它在PIL图像而不是张量上运行。
推荐答案
tf.contrib.image.transform
中先前包含的功能正在升级为TF 2.0并迁移到TensorFlow插件( tfa.image
)。如果您迫切需要尚未添加的特定端点,请将其作为问题提交到Addons存储库中。
Functionality previous included in tf.contrib.image.transform
is in the process of being upgraded to TF 2.0 and migrated to TensorFlow Addons (tfa.image
). If you have an immediate need for a specific endpoint that has not yet been added, please file it as an issue in the Addons repo.
迁移,弃用和重命名命运TensorFlow组织RFC
Migration, deprecation, and rename fates for tf.contrib
endpoints are detailed in the TensorFlow organization RFC here.
这篇关于TensorFlow 2.0中不再提供投影转换,我该怎么办?的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!