├── .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 |
--------------------------------------------------------------------------------