Keras 是一个极简的、高度模块化的神经网络库，采用 Python 开发，能够运行在 TensorFlow、CNTK 和 Theano 平台上。Keras 2.1.2 更新如下：
改进
Bug 修复和性能改进。
Keras 应用、生成器方法的 API 改进。
API 更改
Make preprocess_input in all Keras applications compatible with both Numpy arrays and symbolic tensors (previously only supported Numpy arrays).
Allow the weights argument in all Keras applications to accept the path to a custom weights file to load (previously only supported the built-in imagenet weights file).
steps_per_epoch behavior change in generator training/evaluation methods:
If specified, the specified value will be used (previously, in the case of generator of type Sequence, the specified value was overridden by the Sequence length)
If unspecified and if the generator passed is a Sequence, we set it to the Sequencelength.
Allow workers=0 in generator training/evaluation methods (will run the generator in the main process, in a blocking way).
Add interpolation argument in ImageDataGenerator.flow_from_directory, allowing a custom interpolation method for image resizing.
Allow gpus argument in multi_gpu_model to be a list of specific GPU ids.
Keras 2.1.2 发布，高度模块化的神经网络库
Keras 是一个极简的、高度模块化的神经网络库，采用 Python 开发，能够运行在 TensorFlow、CNTK 和 Theano 平台上。Keras 2.1.2 更新如下：
改进
Bug 修复和性能改进。
Keras 应用、生成器方法的 API 改进。
API 更改
Make
preprocess_inputin all Keras applications compatible with both Numpy arrays and symbolic tensors (previously only supported Numpy arrays).Allow the
weightsargument in all Keras applications to accept the path to a custom weights file to load (previously only supported the built-inimagenetweights file).steps_per_epochbehavior change in generator training/evaluation methods:If specified, the specified value will be used (previously, in the case of generator of type
Sequence, the specified value was overridden by theSequencelength)If unspecified and if the generator passed is a
Sequence, we set it to theSequencelength.Allow
workers=0in generator training/evaluation methods (will run the generator in the main process, in a blocking way).Add
interpolationargument inImageDataGenerator.flow_from_directory, allowing a custom interpolation method for image resizing.Allow
gpusargument inmulti_gpu_modelto be a list of specific GPU ids.请注意，
steps_per_epoch如上所述的更改，可能会影响部分用户使用。下载地址：
Source code (zip)
Source code (tar.gz)