TensorFlow 2.10是谷歌开发的开源机器学习平台的升级版，已经发布，为Keras API带来了新的用户友好特性，改进了aarch64 CPU性能，并推出了TensorFlow决策森林1.0，开发人员现在将其描述为稳定、成熟，并为专业环境做好了准备。
在Keras的改进中，TensorFlow 2.10扩展并统一了Keras注意层的掩码处理。添加了两个新功能。所有三层，tf。keras。layers。注意,tf.keras.layers。AdditiveAttention，和tf.keras.layers。MultiHeadAttention，现在支持临时注意(使用use_causal_mask参数来调用)和隐式屏蔽(在tf.keras.layers.Embedding中设置mask_zero=True)。这些新功能简化了transformer风格模型的实现。
同样在TensorFlow 2.10中，Keras初始化器被做成了无状态和确定性的，构建在无状态TF随机操作的基础上。种子Keras初始化器和非种子Keras初始化器每次调用时都会生成相同的值。无状态初始化器帮助Keras支持新特性，例如使用DTensor进行多客户端模型训练。
TensorFlow的安装说明可以在Tensorflow.org上找到。TensorFlow 2.1的其他新功能和改进:
1、backupandstore检查点提供步骤级粒度。
2、用户可以通过新的实用程序keras.utils.audio_dataset_from_directory从音频文件目录中轻松生成音频数据集。
3、EinsumDense层不再是实验性的。
4、随着TensorFlow 2.10的发布，TensorFlow决策森林(TF-DF)，一个用于训练、服务和解释决策森林模型的算法集合，达到了1.0的状态。
5、aarch64 CPU的性能得到了改进。
6、通过TensorFlow-DirectML插件，GPU支持在Windows上得到了扩展。
7、实验性API tf.data.experimental.from_list创建了一个包含给定元素列表的tf.data.Dataset。返回的数据集将逐个生成列表中的项。
原文：
TensorFlow 2.10, an upgrade to the Google-developed open source machine learning platform, has been released, bringing new user-friendly features to the Keras API, improved aarch64 CPU performance, and the arrival of TensorFlow Decision Forests 1.0, which the developers now describe as stable, mature, and ready for professional environments.
Among the Keras improvements, TensorFlow 2.10 expands and unifies mask handling for Keras attention layers. Two new features have been added. All three layers, tf.keras.layers.Attention, tf.keras.layers.AdditiveAttention, and tf.keras.layers.MultiHeadAttention, now support casual attention (with a use_causal_mask argument to call) and implicit masking (set mask_zero=True in tf.keras.layers.Embedding). These new capabilities simplify implementation of any Transformer-style model.
Also in TensorFlow 2.10, Keras initializers have been made stateless and deterministic, built on top of stateless TF random ops. Both seeded and unseeded Keras initializers will generate the same values every time they are called. The stateless initializer helps Keras support new features such as multi-client model training with DTensor.
Installation instructions for TensorFlow can be found at Tensorflow.org. Other new capabilities and improvements in TensorFlow 2.1:
BackupAndRestore checkpoints offer step level granularity.
Users can easily generate an audio dataset from a directory of audio files, via a new utility, keras.utils.audio_dataset_from_directory.
The EinsumDense layer is no longer experimental.
In conjunction with the release of TensorFlow 2.10, TensorFlow Decision Forests (TF-DF), a collection of algorithms for training, serving, and interpreting decision forest models, reaches 1.0 status.
Performance has been improved for the aarch64 CPU.
GPU support has been expanded on Windows, through the TensorFlow-DirectML plug-in.
An experimental API, tf.data.experimental.from_list, creates a tf.data.Dataset comprising the given list of elements. The returned dataset will produce items in the list one by one.
💬 评论 (0)