├── src ├── requirements.txt └── train.py ├── Dockerfile.cpu ├── Dockerfile.gpu ├── .gitignore ├── README.md └── LICENSE /src/requirements.txt: -------------------------------------------------------------------------------- 1 | h5py==2.7.* 2 | Keras==2.1.* 3 | numpy==1.14.* 4 | scipy==1.1.* 5 | six==1.11.* 6 | -------------------------------------------------------------------------------- /Dockerfile.cpu: -------------------------------------------------------------------------------- 1 | FROM tensorflow/tensorflow:latest-py3 2 | 3 | # Install system packages 4 | RUN apt-get update && apt-get install -y --no-install-recommends \ 5 | bzip2 \ 6 | g++ \ 7 | git \ 8 | graphviz \ 9 | libgl1-mesa-glx \ 10 | libhdf5-dev \ 11 | openmpi-bin \ 12 | wget && \ 13 | rm -rf /var/lib/apt/lists/* 14 | 15 | COPY src /src 16 | 17 | WORKDIR /src 18 | 19 | RUN pip install -r requirements.txt 20 | 21 | ENV PYTHONPATH='/src/:$PYTHONPATH' 22 | 23 | CMD ["python", "train.py"] 24 | -------------------------------------------------------------------------------- /Dockerfile.gpu: -------------------------------------------------------------------------------- 1 | FROM tensorflow/tensorflow:latest-gpu-py3 2 | 3 | # Install system packages 4 | RUN apt-get update && apt-get install -y --no-install-recommends \ 5 | bzip2 \ 6 | g++ \ 7 | git \ 8 | graphviz \ 9 | libgl1-mesa-glx \ 10 | libhdf5-dev \ 11 | openmpi-bin \ 12 | wget && \ 13 | rm -rf /var/lib/apt/lists/* 14 | 15 | COPY src /src 16 | 17 | WORKDIR /src 18 | 19 | RUN pip install -r requirements.txt 20 | 21 | ENV PYTHONPATH='/src/:$PYTHONPATH' 22 | 23 | CMD ["python", "train.py"] 24 | -------------------------------------------------------------------------------- /src/train.py: -------------------------------------------------------------------------------- 1 | import time 2 | import numpy as np 3 | from keras.utils import to_categorical 4 | from keras.datasets import mnist 5 | from keras.models import Sequential 6 | from keras.layers import Dense 7 | from keras.layers import Dropout 8 | from keras.layers import Conv2D 9 | from keras.layers import MaxPooling2D 10 | from keras.layers import GlobalAveragePooling2D 11 | 12 | 13 | def cnn(): 14 | model = Sequential() 15 | model.add(Conv2D(64, (3, 3), input_shape=(28, 28, 1), activation='relu')) 16 | model.add(Conv2D(64, (3, 3), activation='relu')) 17 | model.add(MaxPooling2D()) 18 | model.add(Conv2D(128, (3, 3), activation='relu')) 19 | model.add(Conv2D(128, (3, 3), activation='relu')) 20 | model.add(GlobalAveragePooling2D()) 21 | model.add(Dropout(0.5)) 22 | model.add(Dense(10, activation='softmax')) 23 | model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy']) 24 | return model 25 | 26 | 27 | def main(): 28 | # load data 29 | (X_train, y_train), (X_test, y_test) = mnist.load_data() 30 | 31 | # one-hot encode labels 32 | y_train = to_categorical(y_train) 33 | y_test = to_categorical(y_test) 34 | 35 | # scale image RGB values to [0, 1] 36 | X_train = X_train / 255 37 | X_test = X_test / 255 38 | 39 | # expand dimensions for 2d convolutional filters 40 | X_train = np.expand_dims(X_train, -1) 41 | X_test = np.expand_dims(X_test, -1) 42 | 43 | # build model 44 | model = cnn() 45 | 46 | # start training 47 | start_time = time.time() 48 | model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=3, batch_size=128, verbose=1) 49 | print('training took {} seconds'.format(time.time() - start_time)) 50 | 51 | # final evaluation 52 | loss, accuracy = model.evaluate(X_test, y_test, verbose=1) 53 | print('val accuracy: {}'.format(accuracy)) 54 | 55 | 56 | if __name__ == '__main__': 57 | main() 58 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | 2 | # Created by https://www.gitignore.io/api/python 3 | 4 | ### Python ### 5 | # Byte-compiled / optimized / DLL files 6 | __pycache__/ 7 | *.py[cod] 8 | *$py.class 9 | 10 | # C extensions 11 | *.so 12 | 13 | # Distribution / packaging 14 | .Python 15 | build/ 16 | develop-eggs/ 17 | dist/ 18 | downloads/ 19 | eggs/ 20 | .eggs/ 21 | lib/ 22 | lib64/ 23 | parts/ 24 | sdist/ 25 | var/ 26 | wheels/ 27 | *.egg-info/ 28 | .installed.cfg 29 | *.egg 30 | 31 | # PyInstaller 32 | # Usually these files are written by a python script from a template 33 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 34 | *.manifest 35 | *.spec 36 | 37 | # Installer logs 38 | pip-log.txt 39 | pip-delete-this-directory.txt 40 | 41 | # Unit test / coverage reports 42 | htmlcov/ 43 | .tox/ 44 | .coverage 45 | .coverage.* 46 | .cache 47 | .pytest_cache/ 48 | nosetests.xml 49 | coverage.xml 50 | *.cover 51 | .hypothesis/ 52 | 53 | # Translations 54 | *.mo 55 | *.pot 56 | 57 | # Flask stuff: 58 | instance/ 59 | .webassets-cache 60 | 61 | # Scrapy stuff: 62 | .scrapy 63 | 64 | # Sphinx documentation 65 | docs/_build/ 66 | 67 | # PyBuilder 68 | target/ 69 | 70 | # Jupyter Notebook 71 | .ipynb_checkpoints 72 | 73 | # pyenv 74 | .python-version 75 | 76 | # celery beat schedule file 77 | celerybeat-schedule.* 78 | 79 | # SageMath parsed files 80 | *.sage.py 81 | 82 | # Environments 83 | .env 84 | .venv 85 | env/ 86 | venv/ 87 | ENV/ 88 | env.bak/ 89 | venv.bak/ 90 | 91 | # Spyder project settings 92 | .spyderproject 93 | .spyproject 94 | 95 | # Rope project settings 96 | .ropeproject 97 | 98 | # mkdocs documentation 99 | /site 100 | 101 | # mypy 102 | .mypy_cache/ 103 | 104 | 105 | # End of https://www.gitignore.io/api/python 106 | 107 | # Custom 108 | .DS_Store 109 | data/AVA/raw/ava_imgs_zpped.7z.* 110 | data/AVA/images/* 111 | src/train_outputs/* 112 | .idea/ 113 | .pyre 114 | models 115 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Train Neural Networks on Amazon EC2 with GPU support 2 | 3 | Workflow that shows how to train neural networks on EC2 instances with GPU support. The goal is to present a simple and stable setup to train on GPU instances by using **Docker** and the NVIDIA Container Runtime **nvidia-docker**. A minimal example is given to train a small CNN built in Keras on MNIST. We achieve a 30-fold speedup in training time when training on GPU versus CPU. 4 | 5 | 6 | ## Getting started 7 | 8 | 1. Install [Docker](https://docs.docker.com/install/) 9 | 10 | 2. Install [Docker Machine](https://docs.docker.com/machine/install-machine/) 11 | 12 | 3. Install [AWS Command Line Interface](https://docs.aws.amazon.com/cli/latest/userguide/installing.html) 13 | 14 | 15 | ## Train locally on CPU 16 | 17 | 1. Build Docker image for CPU 18 | ``` 19 | docker build -t docker-keras . -f Dockerfile.cpu 20 | ``` 21 | 22 | 2. Run training container (**NB:** you might have to increase the container resources [[link](https://docs.docker.com/config/containers/resource_constraints/)]) 23 | ``` 24 | docker run docker-keras 25 | ``` 26 | 27 | 28 | ## Train remote on GPU 29 | 30 | 1. Configure your AWS CLI. Ensure that your account has limits for GPU instances [[link](https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/ec2-resource-limits.html)] 31 | 32 | ``` 33 | aws configure 34 | ``` 35 | 36 | 2. Launch EC2 instance with **Docker Machine**. Choose an Ubuntu AMI based on your region (https://cloud-images.ubuntu.com/locator/ec2/). 37 | For example, to launch a **p2.xlarge** EC2 instance named **ec2-p2** with a Tesla K80 GPU run 38 | (**NB:** change region, VPC ID and AMI ID as per your setup) 39 | 40 | ``` 41 | docker-machine create --driver amazonec2 \ 42 | --amazonec2-region eu-west-1 \ 43 | --amazonec2-ami ami-58d7e821 \ 44 | --amazonec2-instance-type p2.xlarge \ 45 | --amazonec2-vpc-id vpc-abc \ 46 | ec2-p2 47 | ``` 48 | 49 | 50 | 3. ssh into instance 51 | 52 | ``` 53 | docker-machine ssh ec2-p2 54 | ``` 55 | 56 | 4. Update NVIDIA drivers and install **nvidia-docker** (see this [blog post](https://towardsdatascience.com/using-docker-to-set-up-a-deep-learning-environment-on-aws-6af37a78c551) for more details) 57 | 58 | ``` 59 | # update NVIDIA drivers 60 | sudo add-apt-repository ppa:graphics-drivers/ppa -y 61 | sudo apt-get update 62 | sudo apt-get install -y nvidia-375 nvidia-settings nvidia-modprobe 63 | 64 | # install nvidia-docker 65 | wget -P /tmp https://github.com/NVIDIA/nvidia-docker/releases/download/v1.0.1/nvidia-docker_1.0.1-1_amd64.deb 66 | sudo dpkg -i /tmp/nvidia-docker_1.0.1-1_amd64.deb && rm /tmp/nvidia-docker_1.0.1-1_amd64.deb 67 | ``` 68 | 69 | 70 | 5. Run training container on GPU instance 71 | 72 | ``` 73 | sudo nvidia-docker run idealo/nvidia-docker-keras 74 | ``` 75 | 76 | This will pull the Docker image `idealo/nvidia-docker-keras` from [DockerHub](https://hub.docker.com/r/idealo/nvidia-docker-keras) and start the training. 77 | The corresponding Dockerfile can be found under `Dockerfile.gpu` for reference. 78 | 79 | 80 | 81 | ## Training time comparison 82 | 83 | We trained MNIST for 3 epochs (~98% accuracy on validation set): 84 | 85 | • MacBook Pro (2.8 GHz Intel Core i7, 16GB RAM): **620 seconds** 86 | 87 | • p2.xlarge (Tesla K80): **41 seconds** 88 | 89 | • p3.2xlarge (Tesla V100): **20 seconds** 90 | 91 | 92 | ## Copyright 93 | 94 | See [LICENSE](LICENSE) for details. 95 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Copyright 2018 idealo internet GmbH. All rights reserved. 2 | 3 | Apache License 4 | Version 2.0, January 2004 5 | http://www.apache.org/licenses/ 6 | 7 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 8 | 9 | 1. Definitions. 10 | 11 | "License" shall mean the terms and conditions for use, reproduction, 12 | and distribution as defined by Sections 1 through 9 of this document. 13 | 14 | "Licensor" shall mean the copyright owner or entity authorized by 15 | the copyright owner that is granting the License. 16 | 17 | "Legal Entity" shall mean the union of the acting entity and all 18 | other entities that control, are controlled by, or are under common 19 | control with that entity. For the purposes of this definition, 20 | "control" means (i) the power, direct or indirect, to cause the 21 | direction or management of such entity, whether by contract or 22 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 23 | outstanding shares, or (iii) beneficial ownership of such entity. 24 | 25 | "You" (or "Your") shall mean an individual or Legal Entity 26 | exercising permissions granted by this License. 27 | 28 | "Source" form shall mean the preferred form for making modifications, 29 | including but not limited to software source code, documentation 30 | source, and configuration files. 31 | 32 | "Object" form shall mean any form resulting from mechanical 33 | transformation or translation of a Source form, including but 34 | not limited to compiled object code, generated documentation, 35 | and conversions to other media types. 36 | 37 | "Work" shall mean the work of authorship, whether in Source or 38 | Object form, made available under the License, as indicated by a 39 | copyright notice that is included in or attached to the work 40 | (an example is provided in the Appendix below). 41 | 42 | "Derivative Works" shall mean any work, whether in Source or Object 43 | form, that is based on (or derived from) the Work and for which the 44 | editorial revisions, annotations, elaborations, or other modifications 45 | represent, as a whole, an original work of authorship. For the purposes 46 | of this License, Derivative Works shall not include works that remain 47 | separable from, or merely link (or bind by name) to the interfaces of, 48 | the Work and Derivative Works thereof. 49 | 50 | "Contribution" shall mean any work of authorship, including 51 | the original version of the Work and any modifications or additions 52 | to that Work or Derivative Works thereof, that is intentionally 53 | submitted to Licensor for inclusion in the Work by the copyright owner 54 | or by an individual or Legal Entity authorized to submit on behalf of 55 | the copyright owner. For the purposes of this definition, "submitted" 56 | means any form of electronic, verbal, or written communication sent 57 | to the Licensor or its representatives, including but not limited to 58 | communication on electronic mailing lists, source code control systems, 59 | and issue tracking systems that are managed by, or on behalf of, the 60 | Licensor for the purpose of discussing and improving the Work, but 61 | excluding communication that is conspicuously marked or otherwise 62 | designated in writing by the copyright owner as "Not a Contribution." 63 | 64 | "Contributor" shall mean Licensor and any individual or Legal Entity 65 | on behalf of whom a Contribution has been received by Licensor and 66 | subsequently incorporated within the Work. 67 | 68 | 2. Grant of Copyright License. Subject to the terms and conditions of 69 | this License, each Contributor hereby grants to You a perpetual, 70 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 71 | copyright license to reproduce, prepare Derivative Works of, 72 | publicly display, publicly perform, sublicense, and distribute the 73 | Work and such Derivative Works in Source or Object form. 74 | 75 | 3. Grant of Patent License. Subject to the terms and conditions of 76 | this License, each Contributor hereby grants to You a perpetual, 77 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 78 | (except as stated in this section) patent license to make, have made, 79 | use, offer to sell, sell, import, and otherwise transfer the Work, 80 | where such license applies only to those patent claims licensable 81 | by such Contributor that are necessarily infringed by their 82 | Contribution(s) alone or by combination of their Contribution(s) 83 | with the Work to which such Contribution(s) was submitted. If You 84 | institute patent litigation against any entity (including a 85 | cross-claim or counterclaim in a lawsuit) alleging that the Work 86 | or a Contribution incorporated within the Work constitutes direct 87 | or contributory patent infringement, then any patent licenses 88 | granted to You under this License for that Work shall terminate 89 | as of the date such litigation is filed. 90 | 91 | 4. Redistribution. You may reproduce and distribute copies of the 92 | Work or Derivative Works thereof in any medium, with or without 93 | modifications, and in Source or Object form, provided that You 94 | meet the following conditions: 95 | 96 | (a) You must give any other recipients of the Work or 97 | Derivative Works a copy of this License; and 98 | 99 | (b) You must cause any modified files to carry prominent notices 100 | stating that You changed the files; and 101 | 102 | (c) You must retain, in the Source form of any Derivative Works 103 | that You distribute, all copyright, patent, trademark, and 104 | attribution notices from the Source form of the Work, 105 | excluding those notices that do not pertain to any part of 106 | the Derivative Works; and 107 | 108 | (d) If the Work includes a "NOTICE" text file as part of its 109 | distribution, then any Derivative Works that You distribute must 110 | include a readable copy of the attribution notices contained 111 | within such NOTICE file, excluding those notices that do not 112 | pertain to any part of the Derivative Works, in at least one 113 | of the following places: within a NOTICE text file distributed 114 | as part of the Derivative Works; within the Source form or 115 | documentation, if provided along with the Derivative Works; or, 116 | within a display generated by the Derivative Works, if and 117 | wherever such third-party notices normally appear. The contents 118 | of the NOTICE file are for informational purposes only and 119 | do not modify the License. You may add Your own attribution 120 | notices within Derivative Works that You distribute, alongside 121 | or as an addendum to the NOTICE text from the Work, provided 122 | that such additional attribution notices cannot be construed 123 | as modifying the License. 124 | 125 | You may add Your own copyright statement to Your modifications and 126 | may provide additional or different license terms and conditions 127 | for use, reproduction, or distribution of Your modifications, or 128 | for any such Derivative Works as a whole, provided Your use, 129 | reproduction, and distribution of the Work otherwise complies with 130 | the conditions stated in this License. 131 | 132 | 5. Submission of Contributions. Unless You explicitly state otherwise, 133 | any Contribution intentionally submitted for inclusion in the Work 134 | by You to the Licensor shall be under the terms and conditions of 135 | this License, without any additional terms or conditions. 136 | Notwithstanding the above, nothing herein shall supersede or modify 137 | the terms of any separate license agreement you may have executed 138 | with Licensor regarding such Contributions. 139 | 140 | 6. Trademarks. This License does not grant permission to use the trade 141 | names, trademarks, service marks, or product names of the Licensor, 142 | except as required for reasonable and customary use in describing the 143 | origin of the Work and reproducing the content of the NOTICE file. 144 | 145 | 7. Disclaimer of Warranty. Unless required by applicable law or 146 | agreed to in writing, Licensor provides the Work (and each 147 | Contributor provides its Contributions) on an "AS IS" BASIS, 148 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 149 | implied, including, without limitation, any warranties or conditions 150 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 151 | PARTICULAR PURPOSE. You are solely responsible for determining the 152 | appropriateness of using or redistributing the Work and assume any 153 | risks associated with Your exercise of permissions under this License. 154 | 155 | 8. Limitation of Liability. In no event and under no legal theory, 156 | whether in tort (including negligence), contract, or otherwise, 157 | unless required by applicable law (such as deliberate and grossly 158 | negligent acts) or agreed to in writing, shall any Contributor be 159 | liable to You for damages, including any direct, indirect, special, 160 | incidental, or consequential damages of any character arising as a 161 | result of this License or out of the use or inability to use the 162 | Work (including but not limited to damages for loss of goodwill, 163 | work stoppage, computer failure or malfunction, or any and all 164 | other commercial damages or losses), even if such Contributor 165 | has been advised of the possibility of such damages. 166 | 167 | 9. Accepting Warranty or Additional Liability. While redistributing 168 | the Work or Derivative Works thereof, You may choose to offer, 169 | and charge a fee for, acceptance of support, warranty, indemnity, 170 | or other liability obligations and/or rights consistent with this 171 | License. However, in accepting such obligations, You may act only 172 | on Your own behalf and on Your sole responsibility, not on behalf 173 | of any other Contributor, and only if You agree to indemnify, 174 | defend, and hold each Contributor harmless for any liability 175 | incurred by, or claims asserted against, such Contributor by reason 176 | of your accepting any such warranty or additional liability. 177 | 178 | END OF TERMS AND CONDITIONS 179 | 180 | APPENDIX: How to apply the Apache License to your work. 181 | 182 | To apply the Apache License to your work, attach the following 183 | boilerplate notice, with the fields enclosed by brackets "[]" 184 | replaced with your own identifying information. (Don't include 185 | the brackets!) The text should be enclosed in the appropriate 186 | comment syntax for the file format. We also recommend that a 187 | file or class name and description of purpose be included on the 188 | same "printed page" as the copyright notice for easier 189 | identification within third-party archives. 190 | 191 | Copyright [yyyy] [name of copyright owner] 192 | 193 | Licensed under the Apache License, Version 2.0 (the "License"); 194 | you may not use this file except in compliance with the License. 195 | You may obtain a copy of the License at 196 | 197 | http://www.apache.org/licenses/LICENSE-2.0 198 | 199 | Unless required by applicable law or agreed to in writing, software 200 | distributed under the License is distributed on an "AS IS" BASIS, 201 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 202 | See the License for the specific language governing permissions and 203 | limitations under the License. 204 | --------------------------------------------------------------------------------