|
| 1 | +########################## |
| 2 | +Basic Deep Learning Models |
| 3 | +########################## |
| 4 | + |
| 5 | +This section collects six documents arranging from the simplest to the most challenging, which will guide you through the basic deep learning tasks in PaddlePaddle. |
| 6 | + |
| 7 | +The documentation in this chapter covers a lot of deep learning basics and how to implement them with PaddlePaddle. See the instructions below for how to use: |
| 8 | + |
| 9 | + |
| 10 | +Overview |
| 11 | +====================== |
| 12 | + |
| 13 | +The book you are reading is an "interactive" e-book - each chapter can be run in a Jupyter Notebook. |
| 14 | + |
| 15 | +.. toctree:: |
| 16 | + :titlesonly: |
| 17 | + |
| 18 | + image_classification/index_en.md |
| 19 | + word2vec/index_en.md |
| 20 | + recommender_system/index_en.md |
| 21 | + understand_sentiment/index_en.md |
| 22 | + label_semantic_roles/index_en.md |
| 23 | + machine_translation/index_en.md |
| 24 | + |
| 25 | + |
| 26 | +We packaged Jupyter, PaddlePaddle, and various dependency softwares into a Docker image. It frees you from installing these softwares by yourself, and you only need to just install Docker. For various Linux versions, please refer to https://www.docker.com . If you use docker on `Windows <https://www.docker.com/docker-windows>`_ or `Mac <https://www.docker.com/docker-mac>`_ , consider `allocate more Memory and CPU resources to Docker <http://stackoverflow.com/a/39720010/724872>`_ . |
| 27 | + |
| 28 | + |
| 29 | +Instructions |
| 30 | +====================== |
| 31 | + |
| 32 | + |
| 33 | +This book assumes you are performing CPU training by default. If you want to use GPU training, the steps will vary slightly. Please refer to "GPU Training" below. |
| 34 | + |
| 35 | + |
| 36 | + |
| 37 | + |
| 38 | + |
| 39 | +CPU training |
| 40 | +>>>>>>>>>>>> |
| 41 | + |
| 42 | +Just run these in shell: |
| 43 | + |
| 44 | +.. code-block:: shell |
| 45 | +
|
| 46 | + docker run -d -p 8888:8888 paddlepaddle/book |
| 47 | +
|
| 48 | +It downloads the Docker image for running books from DockerHub.com. |
| 49 | +To read and edit this book on-line, please visit http://localhost:8888 in your browser. |
| 50 | + |
| 51 | +If the Internet connection to DockerHub.com is compromised, try our spare docker image named docker.paddlepaddlehub.com: |
| 52 | + |
| 53 | +:: |
| 54 | + |
| 55 | + docker run -d -p 8888:8888 docker.paddlepaddlehub.com/book |
| 56 | + |
| 57 | + |
| 58 | +GPU training |
| 59 | +>>>>>>>>>>>>> |
| 60 | + |
| 61 | +To ensure that the GPU driver works properly in the image, we recommend running the image with `nvidia docker <https://github.com/NVIDIA/nvidia-docker>`_ . Please install nvidia-docker first, then run: |
| 62 | + |
| 63 | + |
| 64 | +:: |
| 65 | + |
| 66 | + nvidia-docker run -d -p 8888:8888 paddlepaddle/book:latest-gpu |
| 67 | + |
| 68 | + |
| 69 | +Or use a image source in China to run: |
| 70 | + |
| 71 | +:: |
| 72 | + |
| 73 | + nvidia-docker run -d -p 8888:8888 docker.paddlepaddlehub.com/book:latest-gpu |
| 74 | + |
| 75 | + |
| 76 | +modify the following codes |
| 77 | + |
| 78 | +.. code-block:: python |
| 79 | +
|
| 80 | + use_cuda = False |
| 81 | +
|
| 82 | +
|
| 83 | +into : |
| 84 | + |
| 85 | +.. code-block:: python |
| 86 | +
|
| 87 | + use_cuda = True |
| 88 | +
|
| 89 | +
|
| 90 | +
|
| 91 | +Contribute to Book |
| 92 | +=================== |
| 93 | + |
| 94 | +We highly appreciate your original contributions of new chapters to Book! Just Pull Requests of your contributions to the sub-directory in :code:`pending` . When this chapter is endorsed, we'll gladly move it to the root directory. |
| 95 | + |
| 96 | + |
| 97 | +For writing, running, debugging, you need to install `shell <https://github.com/PaddlePaddle/book/blob/develop/.tools/convert-markdown-into-ipynb-and-test.sh>`_ to generate Docker image。 |
| 98 | + |
| 99 | +**Please Note:** We also provide `English Readme <https://github.com/PaddlePaddle/book/blob/develop/README.md>`_ for PaddlePaddle book |
0 commit comments