keras-team/keras-docs-zh

Chinese (zh-cn) translation of the Keras documentation.

keras-docs-zh's Issues

example目录链接失效

仓库中关于example的资料已经没有了。
跳转后显示Page not found

中文搜索失败

https://keras.io/zh/ 左上角输入中文搜索失败，英文OK，验证多浏览器均有此问题。

关于backend里的函数翻译很不严谨，返回类型tf.variable、tf.tensor、keras tensor混乱不清。感觉就是程序源码注释里的翻译；eval()应该是计算，翻译成估计

关于backend里的函数翻译很不严谨，返回类型tf.variable、tf.tensor、keras tensor混乱不清。感觉就是程序源码注释里的翻译；eval()应该是计算，翻译成估计

Dense的输出是全局变量吗？自定义loss时候未传递输出但是依然可以使用该输出结果

请问有更新到tf2版本的意向吗？

目前的 keras 已经被集成到 tensorflow2 ，是否有意向对文档进行更新？

有PDF版本的吗？或者可以生成PDF？

有PDF版本的吗？或者可以生成PDF？

链接失效

原文“Sequential顺序建模指引”小节中的“示例”标题下，”examples”链接失效
原链接为：https://github.com/keras-team/keras/tree/master/examples
按照上下文的意思，examples指向的链接似乎应当是：https://github.com/keras-team/keras/tree/master/keras/datasets

A link error on the homepage

Feedback: The link to an edit button in the upper right corner of the website is wrong, please update. Maybe you can link it to this project.

显示存在问题

keras.io/zh打卡子目录时，左栏目录有问题

为啥官网的文档不更新而要在 readthedocs.io 上建文档?

这些地方显示不正确也没人管。

lstm中，定义input=Input((None,embedding))时，和定义input=Input((seq_len,embedding))区别

输入：x_train=np.random.random((32,30,300)) y_train=np.random.randint(2,size=(32,30,1))
模型A：inputs=Input(shape=(None,300)) lstm=LSTM(40,return_sequences=True)(inputs) outer=TimeDistributed(Dense(1,activation='sigmoid'))(lstm)
模型B：‘inputs=Input(shape=(30,300))
lstm=LSTM(40,return_sequences=True)(inputs)
outer=TimeDistributed(Dense(1,activation='sigmoid'))(lstm)’
二者都不会报错，请问准确率各方面有什么区别吗？

How to contribute?

I'm Chinese and would like to contribute to the keras docs-zh translation.
Is there any ways that we can help and share the task? Thanks.

引用格式是什么

作为参考文献的引用格式怎么写？

目录生成错误

如图所示， 在ubuntu下采用火狐浏览器， 打开https://keras.io/zh/总是出现左边的排版错误， 其中： 快速开始， 模型， layers， 数据预处理等4章无法打开， 这个问题已经持续了有一周了。

The version released by github.io is inconsistent with the version compiled by the current project, and the page jump style is different.

The version released by github.io is inconsistent with the version compiled by the current project, and the page jump style is different.

The home version of the deploy version is different from other theme styles. For example, click on the quick start, the directory bar can not view all the directories, but I compiled the version in the repository without this problem.

please deploy the latest version to github.io!

keras.backend.image_data_format()

keras.backend.image_data_format()

原作者注释写成'channels_first'
不过现在 都是last了，

Docs » Layers » 卷积层 Convolutional

The introduction of Convolutional Layers Conv1D:

参数:
padding: "valid", "causal" 或 "same" 之一 (大小写敏感) "valid" 表示「不填充」。 "same" 表示填充输入以使输出具有与原始输入相同的长度。 "causal" 表示因果（膨胀）卷积， 例如，output[t] 不依赖于 input[t+1:]， 在模型不应违反时间顺序的时间数据建模时非常有用。 在模型不应违反时间顺序的时间数据建模时非常有用。 详见 WaveNet: A Generative Model for Raw Audio, section 2.1。

The sentence of “在模型不应违反时间顺序的时间数据建模时非常有用。” is repeated.

We need to follow the English document, would you like to contribute?

We need to follow the English document recently, would you like to contribute?

Currently, these files need to be updates:

English	Chinese	GitHub	Description	Currently Translating
Keras FAQ: Frequently Asked Keras Questions	Keras FAQ: 常见问题解答	faq.md	Some links need to be fixed, and some paragraphs need to be added.	jiemojiemo
Core Layers	核心网络层	core.md	Flatten, Input, SpatialDropout1D, SpatialDropout2D, SpatialDropout3D	jiemojiemo
Convolutional Layers	卷积层	convolutional.md	SeparableConv1D	King-HAW
Pooling Layers	池化层	pooling.md	GlobalMaxPooling3D, GlobalAveragePooling3D	King-HAW
Recurrent Layers	循环层	recurrent.md	GRU, StackedRNNCells	King-HAW
Advanced Activations Layers	高级激活层	advanced-activations.md	ReLU	desti-nation
Optimizers	优化器	optimizers.md	Adagrad, Adadelta	King-HAW
Activations	激活函数	activations.md	Total page	jiemojiemo
Callbacks	回调函数	callbacks.md	TerminateOnNaN, BaseLogger, ProgbarLogger, RemoteMonitor, TensorBoard
Applications	应用	applications.md	Add MobileNetV2, and adjust the whole page.
Backend	后端	backend.md	is_tensor, slice
Regularizers	正正则化	regularizers.md	Adjust the whole page.	sighsmile
Constraints	约束项	constraints.md	Adjust the whole page.	sighsmile
Utils	工具	utils.md	multi_gpu_model	desti-nation

Contributions are welcome.

If you wanna contribute, please reply to this issue directly, we will mark you in this table. Thanks.

文档目录失效

没人管了吗？左侧目录失效，点不了，看起来好难受啊

CSS 错误

在英文文档中，侧边栏有一个 wy-side-scroll ，覆盖了父元素的 overflow-y: hidden; 属性为 scroll，而中文文档没有这个 nav，导致侧边栏无法滚动

Order of stored weights.

Hi, I wanna to extract the weights from VGG model in the keras library for further other usage. And I read the weights from the following script

from keras.applications.vgg16 import VGG16
model = VGG16()
weights = []
for layer in model.layers:
    weights.append(layer.get_weights())  # list of numpy array

And the shape of weights in CONV1 is tuple(3,3,3,64). Could you help me check the order of this tuple? Is it (width of filter, height of filter, channel of filter, number of kernel) or ( height of filter, width of filter, channel of filter, number of kernel)?

Thanks