Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

Commit 195acd8

Browse files
First pass
Signed-off-by: AlexDBlack <blacka101@gmail.com>
1 parent f756986 commit 195acd8

21 files changed

+19
-56
lines changed

‎about.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@ layout: default
77

88
## About Eclipse Deeplearning4j
99

10-
Eclipse Deeplearning4j is an open-source, distributed deep-learning project in Java and Scala spearheaded by the people at [Skymind](http://www.skymind.ai), a San Francisco-based business intelligence and enterprise software firm. We're a team of data scientists, deep-learning specialists, Java systems engineers and semi-sentient robots.
10+
Eclipse Deeplearning4j is an open-source, distributed deep-learning project in Java and Scala spearheaded by the people at [Konduit](https://konduit.ai/), a San Francisco-based business intelligence and enterprise software firm. We're a team of data scientists, deep-learning specialists, Java systems engineers and semi-sentient robots.
1111

1212
There are a lot of knobs to turn when you're training a distributed deep-learning network. We've done our best to explain them, so that Eclipse Deeplearning4j can serve as a DIY tool for Java, Scala and Clojure programmers working on Hadoop and other file systems.
1313

‎cn/benchmark.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -57,7 +57,7 @@ IntelliJ会自动指定相关的[Java主类](https://docs.oracle.com/javase/tuto
5757

5858
DL4J与垃圾回收器紧密相联。JVM与C++之间的桥梁[JavaCPP](https://github.com/bytedeco/javacpp)会严格遵守您用`Xmx`设置的堆空间限制,大量利用堆外空间进行工作。堆外空间的使用量不会超过您所指定的堆空间容量。
5959

60-
JavaCPP是由Skymind的一位工程师编写的,它依靠垃圾回收器来了解哪些对象已不再使用。我们依靠Java GC来确定回收什么;Java GC指出目标,我们知道如何用JavaCPP来对其解除分配。使用GPU时的情况也与此相同。
60+
JavaCPP是由Konduit的一位工程师编写的,它依靠垃圾回收器来了解哪些对象已不再使用。我们依靠Java GC来确定回收什么;Java GC指出目标,我们知道如何用JavaCPP来对其解除分配。使用GPU时的情况也与此相同。
6161

6262
您设定的批次越大,占用的RAM内存就越多。
6363

‎docs/_100-beta2/deeplearning4j-beginners.md

Lines changed: 2 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -12,7 +12,7 @@ Where you start depends on what you already know.
1212

1313
The prerequisites for really understanding deep learning are linear algebra, calculus and statistics, as well as programming and some machine learning. The prerequisites for applying it are just learning how to deploy a model.
1414

15-
In the case of Deeplearning4j, you should know Java well and be comfortable with tools like the IntelliJ IDE and the automated build tool Maven. [Skymind's SKIL](https://docs.skymind.ai/) also includes a managed Conda environment for machine learning tools using Python.
15+
In the case of Deeplearning4j, you should know Java well and be comfortable with tools like the IntelliJ IDE and the automated build tool Maven.
1616

1717
Below you'll find a list of resources. The sections are roughly organized in the order they will be useful.
1818

@@ -78,9 +78,7 @@ Once you have programming basics down, tackle Java, the world's most widely used
7878

7979
With that under your belt, we recommend you approach Deeplearning4j through its [examples](https://github.com/eclipse/deeplearning4j-examples).
8080

81-
* [Quickstart](./quickstart.html)
82-
83-
You can also download a [free version of the Skymind Intelligence Layer](https://docs.skymind.ai/), which supports Python, Java and Scala machine-learning and data science tools. SKIL is a machine-learning backend that works on prem and in the cloud, and can ship with your software to provide a machine learning model server.
81+
* [Quickstart](./quickstart.html)
8482

8583
## Other Resources
8684

‎docs/_100-beta2/deeplearning4j-benchmark.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -248,7 +248,7 @@ Better garbage collection increases throughput. For a more detailed exploration
248248

249249
DL4J is tightly linked to the garbage collector. [JavaCPP](https://github.com/bytedeco/javacpp), the bridge between the JVM and C++, adheres to the heap space you set with `Xmx` and works extensively with off-heap memory. The off-heap memory will not surpass the amount of heap space you specify.
250250

251-
JavaCPP, created by a Skymind engineer, relies on the garbage collector to tell it what has been done. We rely on the Java GC to tell us what to collect; the Java GC points at things, and we know how to de-allocate them with JavaCPP. This applies equally to how we work with GPUs.
251+
JavaCPP, created by a Konduit engineer, relies on the garbage collector to tell it what has been done. We rely on the Java GC to tell us what to collect; the Java GC points at things, and we know how to de-allocate them with JavaCPP. This applies equally to how we work with GPUs.
252252

253253
The larger the batch size you use, the more RAM you’re taking in memory.
254254

‎docs/_100-beta2/deeplearning4j-config-memory.md

Lines changed: 0 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -22,10 +22,6 @@ Despite the differences between these two approaches, the idea is the same: once
2222
- For JVM/GC memory: whenever an INDArray is collected by the garbage collector, its off-heap memory will be deallocated, assuming it is not used elsewhere.
2323
- For `MemoryWorkspaces`: whenever an INDArray leaves the workspace scope - for example, when a layer finished forward pass/predictions - its memory may be reused without deallocation and reallocation. This results in better performance for cyclical workloads.
2424

25-
<p align="center">
26-
<a href="https://docs.skymind.ai/docs/welcome" type="button" class="btn btn-lg btn-success" onClick="ga('send', 'event', ‘quickstart', 'click');">GET STARTED WITH DEEP LEARNING</a>
27-
</p>
28-
2925
## Configuring Memory Limits
3026

3127
With DL4J/ND4J, there are two types of memory limits to be aware of and configure: The on-heap JVM memory limit, and the off-heap memory limit, where NDArrays live. Both limits are controlled via Java command-line arguments:

‎docs/_100-beta2/deeplearning4j-nlp-word2vec.md

Lines changed: 0 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -32,13 +32,6 @@ Why? Because words are simply discrete states like the other data mentioned abov
3232

3333
The purpose and usefulness of Word2vec is to group the vectors of similar words together in vectorspace. That is, it detects similarities mathematically. Word2vec creates vectors that are distributed numerical representations of word features, features such as the context of individual words. It does so without human intervention.
3434

35-
<p align="center">
36-
<a href="https://docs.skymind.ai/docs/welcome" type="button" class="btn btn-lg btn-success"
37-
data-ga-event="click"
38-
data-ga-category="Click/Button"
39-
data-ga-action="GoTo/SKILDocs"
40-
data-ga-label="Word2VecPage">GET STARTED WITH WORD2VEC</a>
41-
</p>
4235

4336
Given enough data, usage and contexts, Word2vec can make highly accurate guesses about a word’s meaning based on past appearances. Those guesses can be used to establish a word's association with other words (e.g. "man" is to "boy" what "woman" is to "girl"), or cluster documents and classify them by topic. Those clusters can form the basis of search, [sentiment analysis](https://github.com/eclipse/deeplearning4j-examples/blob/master/dl4j-examples/src/main/java/org/deeplearning4j/examples/recurrent/word2vecsentiment/Word2VecSentimentRNN.java) and recommendations in such diverse fields as scientific research, legal discovery, e-commerce and customer relationship management.
4437

‎docs/_100-beta2/deeplearning4j-nn-computationgraph.md

Lines changed: 0 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -41,10 +41,6 @@ Specifically, the ComputationGraph allows for networks to be built with the foll
4141

4242
As a general rule, when building networks with a single input layer, a single output layer, and an input->a->b->c->output type connection structure: MultiLayerNetwork is usually the preferred network. However, everything that MultiLayerNetwork can do, ComputationGraph can do as well - though the configuration may be a little more complicated.
4343

44-
<p align="center">
45-
<a href="https://docs.skymind.ai/docs/welcome" type="button" class="btn btn-lg btn-success" onClick="ga('send', 'event', ‘quickstart', 'click');">GET STARTED WITH DEEP LEARNING</a>
46-
</p>
47-
4844
## <a name="usecases">Computation Graph: Some Example Use Cases</a>
4945

5046
Examples of some architectures that can be built using ComputationGraph include:

‎docs/_100-beta2/deeplearning4j-quickstart-new.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -24,7 +24,7 @@ If you're having difficulty, we recommend that you join our [Gitter Live Chat](h
2424

2525
For this quickstart tutorial, you will learn how to set up an environment that will allow you create and execute code in an interactive environment. There are a couple of open source tools that can help you do this, and these instructions will help you set them up step-by-step.
2626

27-
Notebooks are interactive coding environments that can be easily installed on a computer and exported and shared with others. This quickstart will use an open-source notebook tool known as [Apache Zeppelin](https://zeppelin.apache.org/). This tutorial and others like it are already prepackaged on a community edition of [SKIL](https://skymind.ai/platform) from Skymind (the creators of Deeplearning4j), and we will be using a tool known as [Docker](https://docs.docker.com/install/) to download and run the tutorial.
27+
Notebooks are interactive coding environments that can be easily installed on a computer and exported and shared with others. This quickstart will use an open-source notebook tool known as [Apache Zeppelin](https://zeppelin.apache.org/). We will be using a tool known as [Docker](https://docs.docker.com/install/) to download and run the tutorial.
2828

2929
#### Download Docker CE
3030
If you don't already have Docker on your system, visit the [Docker install page](ttps://docs.docker.com/install/) and install the version of Docker that works best for you. You can test if you have Docker installed by opening a terminal and running `docker --version`.

‎docs/_100-beta2/deeplearning4j-quickstart.md

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -153,7 +153,6 @@ Congratulations! You just trained your first neural network with Deeplearning4j.
153153
- [Deeplearning4j artifacts on Maven Central](http://search.maven.org/#search%7Cga%7C1%7Cdeeplearning4j)
154154
- [ND4J artifacts on Maven Central](http://search.maven.org/#search%7Cga%7C1%7Cnd4j)
155155
- [Datavec artifacts on Maven Central](http://search.maven.org/#search%7Cga%7C1%7Cdatavec)
156-
- [Scala code for UCI notebook](https://github.com/SkymindIO/SKIL_Examples/blob/master/skil_example_notebooks/scala/uci_quickstart_notebook.scala)
157156

158157
### Troubleshooting
159158

‎docs/_100-beta2/deeplearning4j-spark-training.md

Lines changed: 0 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -45,14 +45,6 @@ Spark jobs, this page will not teach you. Please consider studying Spark basics
4545

4646
If you want to run multiple models on the same server, consider using [parallelwrapper instead](https://github.com/eclipse/deeplearning4j-examples/blob/master/dl4j-cuda-specific-examples/src/main/java/org/deeplearning4j/examples/multigpu/MultiGpuLenetMnistExample.java).
4747

48-
<p align="center">
49-
<a href="https://docs.skymind.ai/docs/welcome" type="button" class="btn btn-lg btn-success"
50-
data-ga-event="click"
51-
data-ga-category="Click/Button"
52-
data-ga-action="GoTo/SKILDocs"
53-
data-ga-label="SparkPage">GET STARTED WITH DEEP LEARNING</a>
54-
</p>
55-
5648
`Parallelwrapper` implements the same concepts (parameter averaging and gradient sharing) optimized for a single server.
5749
You should use `parallelwrapper` when you have a big box (64 cores or more) or multiple GPUs.
5850

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /