tflearn
Deep learning library featuring a higher-level API for TensorFlow.
Science Score: 23.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
○Academic publication links
-
✓Committers with academic emails
9 of 128 committers (7.0%) from academic institutions -
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (12.5%) to scientific vocabulary
Keywords
Keywords from Contributors
Repository
Deep learning library featuring a higher-level API for TensorFlow.
Basic Info
- Host: GitHub
- Owner: tflearn
- License: other
- Language: Python
- Default Branch: master
- Homepage: http://tflearn.org
- Size: 1.52 MB
Statistics
- Stars: 9,619
- Watchers: 454
- Forks: 2,401
- Open Issues: 579
- Releases: 8
Topics
Metadata Files
README.md
TFLearn: Deep learning library featuring a higher-level API for TensorFlow.
TFlearn is a modular and transparent deep learning library built on top of Tensorflow. It was designed to provide a higher-level API to TensorFlow in order to facilitate and speed-up experimentations, while remaining fully transparent and compatible with it.
TFLearn features include:
- Easy-to-use and understand high-level API for implementing deep neural networks, with tutorial and examples.
- Fast prototyping through highly modular built-in neural network layers, regularizers, optimizers, metrics...
- Full transparency over Tensorflow. All functions are built over tensors and can be used independently of TFLearn.
- Powerful helper functions to train any TensorFlow graph, with support of multiple inputs, outputs and optimizers.
- Easy and beautiful graph visualization, with details about weights, gradients, activations and more...
- Effortless device placement for using multiple CPU/GPU.
The high-level API currently supports most of recent deep learning models, such as Convolutions, LSTM, BiRNN, BatchNorm, PReLU, Residual networks, Generative networks... In the future, TFLearn is also intended to stay up-to-date with latest deep learning techniques.
Note: Latest TFLearn (v0.5) is only compatible with TensorFlow v2.0 and over.
Overview
```python
Classification
tflearn.initgraph(numcores=8, gpumemoryfraction=0.5)
net = tflearn.inputdata(shape=[None, 784]) net = tflearn.fullyconnected(net, 64) net = tflearn.dropout(net, 0.5) net = tflearn.fullyconnected(net, 10, activation='softmax') net = tflearn.regression(net, optimizer='adam', loss='categoricalcrossentropy')
model = tflearn.DNN(net) model.fit(X, Y) ```
```python
Sequence Generation
net = tflearn.inputdata(shape=[None, 100, 5000]) net = tflearn.lstm(net, 64) net = tflearn.dropout(net, 0.5) net = tflearn.fullyconnected(net, 5000, activation='softmax') net = tflearn.regression(net, optimizer='adam', loss='categorical_crossentropy')
model = tflearn.SequenceGenerator(net, dictionary=idx, seq_maxlen=100) model.fit(X, Y) model.generate(50, temperature=1.0) ```
There are many more examples available here.
Compatibility
TFLearn is based on the original tensorflow v1 graph API. When using TFLearn, make sure to import tensorflow that way:
import tflearn
import tensorflow.compat.v1 as tf
Installation
TensorFlow Installation
TFLearn requires Tensorflow (version 2.0+) to be installed.
To install TensorFlow, simply run:
pip install tensorflow
or, with GPU-support:
pip install tensorflow-gpu
For more details see TensorFlow installation instructions
TFLearn Installation
To install TFLearn, the easiest way is to run
For the bleeding edge version (recommended):
python
pip install git+https://github.com/tflearn/tflearn.git
For the latest stable version:
python
pip install tflearn
Otherwise, you can also install from source by running (from source folder):
python
python setup.py install
- For more details, please see the Installation Guide.
Getting Started
See Getting Started with TFLearn to learn about TFLearn basic functionalities or start browsing TFLearn Tutorials.
Examples
There are many neural network implementation available, see Examples.
Documentation
Model Visualization
Graph
Loss & Accuracy (multiple runs)
Layers
Contributions
This is the first release of TFLearn, if you find any bug, please report it in the GitHub issues section.
Improvements and requests for new features are more than welcome! Do not hesitate to twist and tweak TFLearn, and send pull-requests.
For more info: Contribute to TFLearn.
License
MIT License
Owner
- Name: TFLearn
- Login: tflearn
- Kind: organization
- Email: aymeric.damien@gmail.com
- Website: http://tflearn.org
- Repositories: 2
- Profile: https://github.com/tflearn
GitHub Events
Total
- Issues event: 5
- Watch event: 28
- Issue comment event: 1
- Pull request event: 4
- Fork event: 14
Last Year
- Issues event: 5
- Watch event: 28
- Issue comment event: 1
- Pull request event: 4
- Fork event: 14
Committers
Last synced: 9 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| aymericdamien | a****n@g****m | 264 |
| Will Ballard | w****d@m****t | 20 |
| ichuang | i****g@m****u | 13 |
| burness | d****0@s****m | 12 |
| kengz | k****l@g****m | 9 |
| Thomas Gallice | t****e | 8 |
| jakubsimanek | s****k@s****m | 8 |
| Donghoon Lee | h****y | 5 |
| David Dao | c****o@g****m | 4 |
| Eric Perbos-Brinck | e****s@g****m | 4 |
| Jinsung-L | j****8@g****m | 4 |
| Ilari Pihlajisto | i****h@g****m | 3 |
| Hemant Rakesh | b****0@g****m | 3 |
| John Sutton | j****n@c****u | 3 |
| Nick Fyson | n****k@f****t | 3 |
| Sergey Melekhin | s****y@m****e | 3 |
| braddengross | b****s@g****m | 3 |
| mooskagh | m****h@g****m | 3 |
| ranarag | a****y@g****m | 3 |
| vishal sharma | v****a@u****u | 3 |
| wyj2046 | w****6@g****m | 3 |
| Brett Naul | b****l@g****m | 3 |
| ziky90 | z****s@s****m | 3 |
| John Allen | j****i@g****m | 3 |
| Yunfeng Wang | v****a | 2 |
| Robin Kobus | r****s@w****e | 2 |
| IslandMan93 | i****3@g****m | 2 |
| Torben Peters | w****h@g****m | 2 |
| Ethan Bennett | e****9@g****m | 2 |
| Eduardo Pinho | e****t@g****m | 2 |
| and 98 more... | ||
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 6 months ago
All Time
- Total issues: 94
- Total pull requests: 25
- Average time to close issues: 12 months
- Average time to close pull requests: 12 months
- Total issue authors: 90
- Total pull request authors: 18
- Average comments per issue: 3.22
- Average comments per pull request: 0.4
- Merged pull requests: 7
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 3
- Pull requests: 3
- Average time to close issues: N/A
- Average time to close pull requests: about 2 months
- Issue authors: 3
- Pull request authors: 2
- Average comments per issue: 0.0
- Average comments per pull request: 0.33
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- FurkanThePythoneer (2)
- Sequential-circuits (2)
- muzakkirhussain011 (2)
- igorvishnevskiy (1)
- atg1207 (1)
- lk251 (1)
- resuly (1)
- davepowell (1)
- WillingDil (1)
- l-hendriks (1)
- EchoRickZz (1)
- Uttams08 (1)
- jason4zhu (1)
- Directory (1)
- Conrad-WS (1)
Pull Request Authors
- aymericdamien (4)
- Hemantr05 (3)
- muzakkirhussain011 (2)
- WalkingDevFlag (2)
- saquib34 (2)
- IMNascimento (2)
- cassiePython (1)
- jungle-cat (1)
- brendongo (1)
- Syndicate-Labs (1)
- MihaMarkic (1)
- huntr-helper (1)
- bowang (1)
- Yashh0 (1)
- tirkarthi (1)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 1
-
Total downloads:
- pypi 3,430 last-month
- Total docker downloads: 24,160
- Total dependent packages: 2
- Total dependent repositories: 817
- Total versions: 6
- Total maintainers: 1
pypi.org: tflearn
Deep Learning Library featuring a higher-level API for TensorFlow
- Homepage: https://github.com/tflearn/tflearn
- Documentation: https://tflearn.readthedocs.io/
- License: MIT
-
Latest release: 0.5.0
published over 5 years ago
Rankings
Maintainers (1)
Dependencies
- Pillow *
- numpy *
- six *