├── .gitignore ├── LICENSE ├── README.md ├── base ├── base_model.py └── base_train.py ├── configs └── example.json ├── data_loader └── data_generator.py ├── figures └── diagram.png ├── mains └── example.py ├── models ├── example_model.py └── template_model.py ├── trainers ├── example_trainer.py └── template_trainer.py └── utils ├── __init__.py ├── config.py ├── dirs.py ├── logger.py └── utils.py /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | .idea 9 | # Distribution / packaging 10 | .Python 11 | env/ 12 | build/ 13 | develop-eggs/ 14 | dist/ 15 | downloads/ 16 | eggs/ 17 | .eggs/ 18 | lib/ 19 | lib64/ 20 | parts/ 21 | sdist/ 22 | var/ 23 | wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | 28 | # PyInstaller 29 | # Usually these files are written by a python script from a template 30 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 31 | *.manifest 32 | *.spec 33 | 34 | # Installer logs 35 | pip-log.txt 36 | pip-delete-this-directory.txt 37 | 38 | # Unit test / coverage reports 39 | htmlcov/ 40 | .tox/ 41 | .coverage 42 | .coverage.* 43 | .cache 44 | nosetests.xml 45 | coverage.xml 46 | *.cover 47 | .hypothesis/ 48 | 49 | # Translations 50 | *.mo 51 | *.pot 52 | 53 | # Django stuff: 54 | *.log 55 | local_settings.py 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 | # dotenv 83 | .env 84 | 85 | # virtualenv 86 | .venv 87 | venv/ 88 | ENV/ 89 | 90 | # Spyder project settings 91 | .spyderproject 92 | .spyproject 93 | 94 | # Rope project settings 95 | .ropeproject 96 | 97 | # mkdocs documentation 98 | /site 99 | 100 | # mypy 101 | .mypy_cache/ 102 | /experiments/ 103 | .idea/Tensorflow-architecture-templete.iml 104 | .idea/misc.xml 105 | .idea/modules.xml 106 | .idea/workspace.xml 107 | experiments/ 108 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Tensorflow Project Template 2 | A simple and well designed structure is essential for any Deep Learning project, so after a lot of practice and contributing in tensorflow projects here's a tensorflow project template that combines **simplcity**, **best practice for folder structure** and **good OOP design**. 3 | The main idea is that there's much stuff you do every time you start your tensorflow project, so wrapping all this shared stuff will help you to change just the core idea every time you start a new tensorflow project. 4 | 5 | **So, here's a simple tensorflow template that help you get into your main project faster and just focus on your core (Model, Training, ...etc)** 6 | # Table Of Contents 7 | 8 | - [In a Nutshell](#in-a-nutshell) 9 | - [In Details](#in-details) 10 | - [Project architecture](#project-architecture) 11 | - [Folder structure](#folder-structure) 12 | - [ Main Components](#main-components) 13 | - [Models](#models) 14 | - [Trainer](#trainer) 15 | - [Data Loader](#data-loader) 16 | - [Logger](#logger) 17 | - [Configuration](#configuration) 18 | - [Main](#main) 19 | - [Future Work](#future-work) 20 | - [Contributing](#contributing) 21 | - [Acknowledgments](#acknowledgments) 22 | 23 | # In a Nutshell 24 | In a nutshell here's how to use this template, so **for example** assume you want to implement VGG model so you should do the following: 25 | - In models folder create a class named VGG that inherit the "base_model" class 26 | 27 | ```python 28 | 29 | class VGGModel(BaseModel): 30 | def __init__(self, config): 31 | super(VGGModel, self).__init__(config) 32 | #call the build_model and init_saver functions. 33 | self.build_model() 34 | self.init_saver() 35 | ``` 36 | - Override these two functions "build_model" where you implement the vgg model, and "init_saver" where you define a tensorflow saver, then call them in the initalizer. 37 | 38 | ```python 39 | def build_model(self): 40 | # here you build the tensorflow graph of any model you want and also define the loss. 41 | pass 42 | 43 | def init_saver(self): 44 | # here you initalize the tensorflow saver that will be used in saving the checkpoints. 45 | self.saver = tf.train.Saver(max_to_keep=self.config.max_to_keep) 46 | 47 | ``` 48 | 49 | - In trainers folder create a VGG trainer that inherit from "base_train" class 50 | ```python 51 | 52 | class VGGTrainer(BaseTrain): 53 | def __init__(self, sess, model, data, config, logger): 54 | super(VGGTrainer, self).__init__(sess, model, data, config, logger) 55 | ``` 56 | - Override these two functions "train_step", "train_epoch" where you write the logic of the training process 57 | ```python 58 | 59 | def train_epoch(self): 60 | """ 61 | implement the logic of epoch: 62 | -loop on the number of iterations in the config and call the train step 63 | -add any summaries you want using the summary 64 | """ 65 | pass 66 | 67 | def train_step(self): 68 | """ 69 | implement the logic of the train step 70 | - run the tensorflow session 71 | - return any metrics you need to summarize 72 | """ 73 | pass 74 | 75 | ``` 76 | - In main file, you create the session and instances of the following objects "Model", "Logger", "Data_Generator", "Trainer", and config 77 | ```python 78 | sess = tf.Session() 79 | # create instance of the model you want 80 | model = VGGModel(config) 81 | # create your data generator 82 | data = DataGenerator(config) 83 | # create tensorboard logger 84 | logger = Logger(sess, config) 85 | ``` 86 | - Pass the all these objects to the trainer object, and start your training by calling "trainer.train()" 87 | ```python 88 | trainer = VGGTrainer(sess, model, data, config, logger) 89 | 90 | # here you train your model 91 | trainer.train() 92 | 93 | ``` 94 | **You will find a template file and a simple example in the model and trainer folder that shows you how to try your first model simply.** 95 | 96 | 97 | # In Details 98 | 99 | Project architecture 100 | -------------- 101 | 102 |
103 | 104 | 105 | 106 |
107 | 108 | 109 | Folder structure 110 | -------------- 111 | 112 | ``` 113 | ├── base 114 | │ ├── base_model.py - this file contains the abstract class of the model. 115 | │ └── base_train.py - this file contains the abstract class of the trainer. 116 | │ 117 | │ 118 | ├── model - this folder contains any model of your project. 119 | │ └── example_model.py 120 | │ 121 | │ 122 | ├── trainer - this folder contains trainers of your project. 123 | │ └── example_trainer.py 124 | │ 125 | ├── mains - here's the main(s) of your project (you may need more than one main). 126 | │ └── example_main.py - here's an example of main that is responsible for the whole pipeline. 127 | 128 | │ 129 | ├── data _loader 130 | │ └── data_generator.py - here's the data_generator that is responsible for all data handling. 131 | │ 132 | └── utils 133 | ├── logger.py 134 | └── any_other_utils_you_need 135 | 136 | ``` 137 | 138 | 139 | ## Main Components 140 | 141 | ### Models 142 | -------------- 143 | - #### **Base model** 144 | 145 | Base model is an abstract class that must be Inherited by any model you create, the idea behind this is that there's much shared stuff between all models. 146 | The base model contains: 147 | - ***Save*** -This function to save a checkpoint to the desk. 148 | - ***Load*** -This function to load a checkpoint from the desk. 149 | - ***Cur_epoch, Global_step counters*** -These variables to keep track of the current epoch and global step. 150 | - ***Init_Saver*** An abstract function to initialize the saver used for saving and loading the checkpoint, ***Note***: override this function in the model you want to implement. 151 | - ***Build_model*** Here's an abstract function to define the model, ***Note***: override this function in the model you want to implement. 152 | - #### **Your model** 153 | Here's where you implement your model. 154 | So you should : 155 | - Create your model class and inherit the base_model class 156 | - override "build_model" where you write the tensorflow model you want 157 | - override "init_save" where you create a tensorflow saver to use it to save and load checkpoint 158 | - call the "build_model" and "init_saver" in the initializer. 159 | 160 | ### Trainer 161 | -------------- 162 | - #### **Base trainer** 163 | Base trainer is an abstract class that just wrap the training process. 164 | 165 | - #### **Your trainer** 166 | Here's what you should implement in your trainer. 167 | 1. Create your trainer class and inherit the base_trainer class. 168 | 2. override these two functions "train_step", "train_epoch" where you implement the training process of each step and each epoch. 169 | ### Data Loader 170 | This class is responsible for all data handling and processing and provide an easy interface that can be used by the trainer. 171 | ### Logger 172 | This class is responsible for the tensorboard summary, in your trainer create a dictionary of all tensorflow variables you want to summarize then pass this dictionary to logger.summarize(). 173 | 174 | 175 | This class also supports reporting to **Comet.ml** which allows you to see all your hyper-params, metrics, graphs, dependencies and more including real-time metric. 176 | Add your API key [in the configuration file](configs/example.json#L9): 177 | 178 | For example: "comet_api_key": "your key here" 179 | 180 | 181 | ### Comet.ml Integration 182 | This template also supports reporting to Comet.ml which allows you to see all your hyper-params, metrics, graphs, dependencies and more including real-time metric. 183 | 184 | Add your API key [in the configuration file](configs/example.json#L9): 185 | 186 | 187 | For example: `"comet_api_key": "your key here"` 188 | 189 | Here's how it looks after you start training: 190 |
191 | 192 | 193 | 194 |
195 | 196 | You can also link your Github repository to your comet.ml project for full version control. 197 | [Here's a live page showing the example from this repo](https://www.comet.ml/gidim/tensorflow-project-template/caba580d8d1547ccaed982693a645507/chart) 198 | 199 | 200 | 201 | ### Configuration 202 | I use Json as configuration method and then parse it, so write all configs you want then parse it using "utils/config/process_config" and pass this configuration object to all other objects. 203 | ### Main 204 | Here's where you combine all previous part. 205 | 1. Parse the config file. 206 | 2. Create a tensorflow session. 207 | 2. Create an instance of "Model", "Data_Generator" and "Logger" and parse the config to all of them. 208 | 3. Create an instance of "Trainer" and pass all previous objects to it. 209 | 4. Now you can train your model by calling "Trainer.train()" 210 | 211 | 212 | # Future Work 213 | - Replace the data loader part with new tensorflow dataset API. 214 | 215 | 216 | # Contributing 217 | Any kind of enhancement or contribution is welcomed. 218 | 219 | 220 | # Acknowledgments 221 | Thanks for my colleague [Mo'men Abdelrazek](https://github.com/moemen95) for contributing in this work. 222 | and thanks for [Mohamed Zahran](https://github.com/moh3th1) for the review. 223 | **Thanks for Jtoy for including the repo in [Awesome Tensorflow](https://github.com/jtoy/awesome-tensorflow).** 224 | -------------------------------------------------------------------------------- /base/base_model.py: -------------------------------------------------------------------------------- 1 | import tensorflow as tf 2 | 3 | 4 | class BaseModel: 5 | def __init__(self, config): 6 | self.config = config 7 | # init the global step 8 | self.init_global_step() 9 | # init the epoch counter 10 | self.init_cur_epoch() 11 | 12 | # save function that saves the checkpoint in the path defined in the config file 13 | def save(self, sess): 14 | print("Saving model...") 15 | self.saver.save(sess, self.config.checkpoint_dir, self.global_step_tensor) 16 | print("Model saved") 17 | 18 | # load latest checkpoint from the experiment path defined in the config file 19 | def load(self, sess): 20 | latest_checkpoint = tf.train.latest_checkpoint(self.config.checkpoint_dir) 21 | if latest_checkpoint: 22 | print("Loading model checkpoint {} ...\n".format(latest_checkpoint)) 23 | self.saver.restore(sess, latest_checkpoint) 24 | print("Model loaded") 25 | 26 | # just initialize a tensorflow variable to use it as epoch counter 27 | def init_cur_epoch(self): 28 | with tf.variable_scope('cur_epoch'): 29 | self.cur_epoch_tensor = tf.Variable(0, trainable=False, name='cur_epoch') 30 | self.increment_cur_epoch_tensor = tf.assign(self.cur_epoch_tensor, self.cur_epoch_tensor + 1) 31 | 32 | # just initialize a tensorflow variable to use it as global step counter 33 | def init_global_step(self): 34 | # DON'T forget to add the global step tensor to the tensorflow trainer 35 | with tf.variable_scope('global_step'): 36 | self.global_step_tensor = tf.Variable(0, trainable=False, name='global_step') 37 | 38 | def init_saver(self): 39 | # just copy the following line in your child class 40 | # self.saver = tf.train.Saver(max_to_keep=self.config.max_to_keep) 41 | raise NotImplementedError 42 | 43 | def build_model(self): 44 | raise NotImplementedError 45 | -------------------------------------------------------------------------------- /base/base_train.py: -------------------------------------------------------------------------------- 1 | import tensorflow as tf 2 | 3 | 4 | class BaseTrain: 5 | def __init__(self, sess, model, data, config, logger): 6 | self.model = model 7 | self.logger = logger 8 | self.config = config 9 | self.sess = sess 10 | self.data = data 11 | self.init = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer()) 12 | self.sess.run(self.init) 13 | 14 | def train(self): 15 | for cur_epoch in range(self.model.cur_epoch_tensor.eval(self.sess), self.config.num_epochs + 1, 1): 16 | self.train_epoch() 17 | self.sess.run(self.model.increment_cur_epoch_tensor) 18 | 19 | def train_epoch(self): 20 | """ 21 | implement the logic of epoch: 22 | -loop over the number of iterations in the config and call the train step 23 | -add any summaries you want using the summary 24 | """ 25 | raise NotImplementedError 26 | 27 | def train_step(self): 28 | """ 29 | implement the logic of the train step 30 | - run the tensorflow session 31 | - return any metrics you need to summarize 32 | """ 33 | raise NotImplementedError 34 | -------------------------------------------------------------------------------- /configs/example.json: -------------------------------------------------------------------------------- 1 | { 2 | "exp_name": "example", 3 | "num_epochs": 10, 4 | "num_iter_per_epoch": 10, 5 | "learning_rate": 0.001, 6 | "batch_size": 16, 7 | "state_size": [784], 8 | "max_to_keep":5 9 | } -------------------------------------------------------------------------------- /data_loader/data_generator.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | 3 | 4 | class DataGenerator: 5 | def __init__(self, config): 6 | self.config = config 7 | # load data here 8 | self.input = np.ones((500, 784)) 9 | self.y = np.ones((500, 10)) 10 | 11 | def next_batch(self, batch_size): 12 | idx = np.random.choice(500, batch_size) 13 | yield self.input[idx], self.y[idx] 14 | -------------------------------------------------------------------------------- /figures/diagram.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MrGemy95/Tensorflow-Project-Template/a7e3ce2deb83095399ce48de40f7a5ceb073fe47/figures/diagram.png -------------------------------------------------------------------------------- /mains/example.py: -------------------------------------------------------------------------------- 1 | import tensorflow as tf 2 | 3 | from data_loader.data_generator import DataGenerator 4 | from models.example_model import ExampleModel 5 | from trainers.example_trainer import ExampleTrainer 6 | from utils.config import process_config 7 | from utils.dirs import create_dirs 8 | from utils.logger import Logger 9 | from utils.utils import get_args 10 | 11 | 12 | def main(): 13 | # capture the config path from the run arguments 14 | # then process the json configuration file 15 | try: 16 | args = get_args() 17 | config = process_config(args.config) 18 | 19 | except: 20 | print("missing or invalid arguments") 21 | exit(0) 22 | 23 | # create the experiments dirs 24 | create_dirs([config.summary_dir, config.checkpoint_dir]) 25 | # create tensorflow session 26 | sess = tf.Session() 27 | # create your data generator 28 | data = DataGenerator(config) 29 | 30 | # create an instance of the model you want 31 | model = ExampleModel(config) 32 | # create tensorboard logger 33 | logger = Logger(sess, config) 34 | # create trainer and pass all the previous components to it 35 | trainer = ExampleTrainer(sess, model, data, config, logger) 36 | #load model if exists 37 | model.load(sess) 38 | # here you train your model 39 | trainer.train() 40 | 41 | 42 | if __name__ == '__main__': 43 | main() 44 | -------------------------------------------------------------------------------- /models/example_model.py: -------------------------------------------------------------------------------- 1 | from base.base_model import BaseModel 2 | import tensorflow as tf 3 | 4 | 5 | class ExampleModel(BaseModel): 6 | def __init__(self, config): 7 | super(ExampleModel, self).__init__(config) 8 | self.build_model() 9 | self.init_saver() 10 | 11 | def build_model(self): 12 | self.is_training = tf.placeholder(tf.bool) 13 | 14 | self.x = tf.placeholder(tf.float32, shape=[None] + self.config.state_size) 15 | self.y = tf.placeholder(tf.float32, shape=[None, 10]) 16 | 17 | # network architecture 18 | d1 = tf.layers.dense(self.x, 512, activation=tf.nn.relu, name="dense1") 19 | d2 = tf.layers.dense(d1, 10, name="dense2") 20 | 21 | with tf.name_scope("loss"): 22 | self.cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=self.y, logits=d2)) 23 | update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS) 24 | with tf.control_dependencies(update_ops): 25 | self.train_step = tf.train.AdamOptimizer(self.config.learning_rate).minimize(self.cross_entropy, 26 | global_step=self.global_step_tensor) 27 | correct_prediction = tf.equal(tf.argmax(d2, 1), tf.argmax(self.y, 1)) 28 | self.accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) 29 | 30 | 31 | def init_saver(self): 32 | # here you initialize the tensorflow saver that will be used in saving the checkpoints. 33 | self.saver = tf.train.Saver(max_to_keep=self.config.max_to_keep) 34 | 35 | -------------------------------------------------------------------------------- /models/template_model.py: -------------------------------------------------------------------------------- 1 | from base.base_model import BaseModel 2 | import tensorflow as tf 3 | 4 | 5 | class TemplateModel(BaseModel): 6 | def __init__(self, config): 7 | super(TemplateModel, self).__init__(config) 8 | 9 | self.build_model() 10 | self.init_saver() 11 | 12 | def build_model(self): 13 | # here you build the tensorflow graph of any model you want and also define the loss. 14 | pass 15 | 16 | def init_saver(self): 17 | # here you initialize the tensorflow saver that will be used in saving the checkpoints. 18 | # self.saver = tf.train.Saver(max_to_keep=self.config.max_to_keep) 19 | 20 | pass 21 | -------------------------------------------------------------------------------- /trainers/example_trainer.py: -------------------------------------------------------------------------------- 1 | from base.base_train import BaseTrain 2 | from tqdm import tqdm 3 | import numpy as np 4 | 5 | 6 | class ExampleTrainer(BaseTrain): 7 | def __init__(self, sess, model, data, config,logger): 8 | super(ExampleTrainer, self).__init__(sess, model, data, config,logger) 9 | 10 | def train_epoch(self): 11 | loop = tqdm(range(self.config.num_iter_per_epoch)) 12 | losses = [] 13 | accs = [] 14 | for _ in loop: 15 | loss, acc = self.train_step() 16 | losses.append(loss) 17 | accs.append(acc) 18 | loss = np.mean(losses) 19 | acc = np.mean(accs) 20 | 21 | cur_it = self.model.global_step_tensor.eval(self.sess) 22 | summaries_dict = { 23 | 'loss': loss, 24 | 'acc': acc, 25 | } 26 | self.logger.summarize(cur_it, summaries_dict=summaries_dict) 27 | self.model.save(self.sess) 28 | 29 | def train_step(self): 30 | batch_x, batch_y = next(self.data.next_batch(self.config.batch_size)) 31 | feed_dict = {self.model.x: batch_x, self.model.y: batch_y, self.model.is_training: True} 32 | _, loss, acc = self.sess.run([self.model.train_step, self.model.cross_entropy, self.model.accuracy], 33 | feed_dict=feed_dict) 34 | return loss, acc 35 | -------------------------------------------------------------------------------- /trainers/template_trainer.py: -------------------------------------------------------------------------------- 1 | from base.base_train import BaseTrain 2 | from tqdm import tqdm 3 | import numpy as np 4 | 5 | 6 | class TemplateTrainer(BaseTrain): 7 | def __init__(self, sess, model, data, config, logger): 8 | super(TemplateTrainer, self).__init__(sess, model, data, config, logger) 9 | 10 | def train_epoch(self): 11 | """ 12 | implement the logic of epoch: 13 | -loop on the number of iterations in the config and call the train step 14 | -add any summaries you want using the summary 15 | """ 16 | pass 17 | 18 | def train_step(self): 19 | """ 20 | implement the logic of the train step 21 | - run the tensorflow session 22 | - return any metrics you need to summarize 23 | """ 24 | pass 25 | -------------------------------------------------------------------------------- /utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MrGemy95/Tensorflow-Project-Template/a7e3ce2deb83095399ce48de40f7a5ceb073fe47/utils/__init__.py -------------------------------------------------------------------------------- /utils/config.py: -------------------------------------------------------------------------------- 1 | import json 2 | from bunch import Bunch 3 | import os 4 | 5 | 6 | def get_config_from_json(json_file): 7 | """ 8 | Get the config from a json file 9 | :param json_file: 10 | :return: config(namespace) or config(dictionary) 11 | """ 12 | # parse the configurations from the config json file provided 13 | with open(json_file, 'r') as config_file: 14 | config_dict = json.load(config_file) 15 | 16 | # convert the dictionary to a namespace using bunch lib 17 | config = Bunch(config_dict) 18 | 19 | return config, config_dict 20 | 21 | 22 | def process_config(json_file): 23 | config, _ = get_config_from_json(json_file) 24 | config.summary_dir = os.path.join("../experiments", config.exp_name, "summary/") 25 | config.checkpoint_dir = os.path.join("../experiments", config.exp_name, "checkpoint/") 26 | return config 27 | -------------------------------------------------------------------------------- /utils/dirs.py: -------------------------------------------------------------------------------- 1 | import os 2 | 3 | 4 | def create_dirs(dirs): 5 | """ 6 | dirs - a list of directories to create if these directories are not found 7 | :param dirs: 8 | :return exit_code: 0:success -1:failed 9 | """ 10 | try: 11 | for dir_ in dirs: 12 | if not os.path.exists(dir_): 13 | os.makedirs(dir_) 14 | return 0 15 | except Exception as err: 16 | print("Creating directories error: {0}".format(err)) 17 | exit(-1) 18 | -------------------------------------------------------------------------------- /utils/logger.py: -------------------------------------------------------------------------------- 1 | import tensorflow as tf 2 | import os 3 | 4 | 5 | class Logger: 6 | def __init__(self, sess,config): 7 | self.sess = sess 8 | self.config = config 9 | self.summary_placeholders = {} 10 | self.summary_ops = {} 11 | self.train_summary_writer = tf.summary.FileWriter(os.path.join(self.config.summary_dir, "train"), 12 | self.sess.graph) 13 | self.test_summary_writer = tf.summary.FileWriter(os.path.join(self.config.summary_dir, "test")) 14 | 15 | # it can summarize scalars and images. 16 | def summarize(self, step, summarizer="train", scope="", summaries_dict=None): 17 | """ 18 | :param step: the step of the summary 19 | :param summarizer: use the train summary writer or the test one 20 | :param scope: variable scope 21 | :param summaries_dict: the dict of the summaries values (tag,value) 22 | :return: 23 | """ 24 | summary_writer = self.train_summary_writer if summarizer == "train" else self.test_summary_writer 25 | with tf.variable_scope(scope): 26 | 27 | if summaries_dict is not None: 28 | summary_list = [] 29 | for tag, value in summaries_dict.items(): 30 | if tag not in self.summary_ops: 31 | if len(value.shape) <= 1: 32 | self.summary_placeholders[tag] = tf.placeholder('float32', value.shape, name=tag) 33 | else: 34 | self.summary_placeholders[tag] = tf.placeholder('float32', [None] + list(value.shape[1:]), name=tag) 35 | if len(value.shape) <= 1: 36 | self.summary_ops[tag] = tf.summary.scalar(tag, self.summary_placeholders[tag]) 37 | else: 38 | self.summary_ops[tag] = tf.summary.image(tag, self.summary_placeholders[tag]) 39 | 40 | summary_list.append(self.sess.run(self.summary_ops[tag], {self.summary_placeholders[tag]: value})) 41 | 42 | for summary in summary_list: 43 | summary_writer.add_summary(summary, step) 44 | summary_writer.flush() 45 | -------------------------------------------------------------------------------- /utils/utils.py: -------------------------------------------------------------------------------- 1 | import argparse 2 | 3 | 4 | def get_args(): 5 | argparser = argparse.ArgumentParser(description=__doc__) 6 | argparser.add_argument( 7 | '-c', '--config', 8 | metavar='C', 9 | default='None', 10 | help='The Configuration file') 11 | args = argparser.parse_args() 12 | return args 13 | --------------------------------------------------------------------------------