Update applications.md

[ypwhs]

[gaussic]

Arguments

• input_shape: optional shape tuple, only to be specified if include_top is False (otherwise the input shape has to be (224, 224, 3) (with 'channels_last' data format) or (3, 224, 224) (with 'channels_first' data format) for NASNetMobile or (331, 331, 3) (with 'channels_last' data format) or (3, 331, 331) (with 'channels_first' data format) for NASNetLarge. It should have exactly 3 inputs channels, and width and height should be no smaller than 32. E.g. (200, 200, 3) would be one valid value.

• input_shape: 可选，输入尺寸元组，仅当 include_top=False 时有效（不然对于 NASNetMobile 模型来说，输入形状必须是 (331, 331, 3) （channels_last 格式），对于 NASNetLarge 来说，输入形状必须是 (331, 331, 3) （channels_last 格式）。输入尺寸必须是三个数字，且宽高必须不小于 32，比如 (200, 200, 3) 是一个合法的输入尺寸。

It seems a little bit different to the English version.

[ypwhs]

Note that only TensorFlow is supported for now, therefore it only works with the data format image_data_format='channels_last' in your Keras config at ~/.keras/keras.json.

[gaussic]

Then you should add the translation of this line in the new document.

[ypwhs]

注意，该模型目前仅能在 TensorFlow 后端使用，因此它只支持 channels_last 的维度顺序（高度、宽度、通道），可以在 ~/.keras/keras.json Keras 配置文件中设置。

https://github.com/keras-team/keras-docs-zh/blame/5591261f78e2646493469f87aa97b77646e4b0d9/sources/applications.md#L539

[gaussic]

Sorry，我的失误。

但是，原文提到的是：

Note that only TensorFlow is supported for now

指的是目前暂时只支持 TensorFlow，未来是否支持其他 backend 并没有明说，所以直接精简化英文文档的做法是否过于主观？

我个人的观点还是坚持按照英文文档翻译较好。

[ypwhs]

同意，未来如果支持了其他框架，我们可以删去刚才那句，然后把不同维度的说明加上。

（然而不知道还会不会支持其他框架