You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardexpand all lines: README.md
+45-66
Original file line number
Diff line number
Diff line change
@@ -34,45 +34,43 @@
34
34
35
35
<br/>
36
36
37
-
TensorLayer is a novel TensorFlow-based deep learning and reinforcement learning library designed for researchers and engineers. It provides a large collection of customizable neural layers / functions that are key to build real-world AI applications. TensorLayer is awarded the 2017 Best Open Source Software by the [ACM Multimedia Society](https://twitter.com/ImperialDSI/status/923928895325442049).
37
+
TensorLayer is a novel TensorFlow-based deep learning and reinforcement learning library designed for researchers and engineers. It provides an extensive collection of customizable neural layers to build complex AI models. TensorLayer is awarded the 2017 Best Open Source Software by the [ACM Multimedia Society](https://twitter.com/ImperialDSI/status/923928895325442049).
38
+
TensorLayer can also be found at [iHub](https://code.ihub.org.cn/projects/328) and [Gitee](https://gitee.com/organizations/TensorLayer).
39
+
40
+
# News
38
41
39
42
🔥📰🔥 Reinforcement Learning Model Zoos: [Low-level APIs for Research](https://github.com/tensorlayer/tensorlayer/tree/master/examples/reinforcement_learning) and [High-level APIs for Production](https://github.com/tensorlayer/RLzoo)
40
43
41
44
🔥📰🔥 [Sipeed Maxi-EMC](https://github.com/sipeed/Maix-EMC): Run TensorLayer models on the **low-cost AI chip** (e.g., K210) (Alpha Version)
42
45
43
46
🔥📰🔥 [NNoM](https://github.com/majianjia/nnom): Run TensorLayer quantized models on the **MCU** (e.g., STM32) (Coming Soon)
44
47
45
-
46
48
# Features
47
49
48
-
As deep learning practitioners, we have been looking for a library that can address various development
49
-
purposes. This library is easy to adopt by providing diverse examples, tutorials and pre-trained models.
50
-
Also, it allow users to easily fine-tune TensorFlow; while being suitable for production deployment. TensorLayer aims to satisfy all these purposes. It has three key features:
50
+
TensorLayer is a new deep learning library designed with simplicity, flexibility and high-performance in mind.
51
51
52
-
-***Simplicity*** : TensorLayer lifts the low-level dataflow interface of TensorFlow to *high-level* layers / models. It is very easy to learn through the rich [example codes](https://github.com/tensorlayer/awesome-tensorlayer) contributed by a wide community.
53
-
-***Flexibility*** : TensorLayer APIs are transparent: it does not mask TensorFlow from users; but leaving massive hooks that help *low-level tuning*and *deep customization*.
54
-
-***Zero-cost Abstraction*** : TensorLayer can achieve the *full power* of TensorFlow. The following table shows the training speeds of [VGG16](http://www.robots.ox.ac.uk/~vgg/research/very_deep/) using TensorLayer and native TensorFlow on a TITAN Xp.
52
+
-***Simplicity*** : TensorLayer has a high-level layer/model abstraction which is effortless to learn. You can learn how deep learning can benefit your AI tasks in minutes through the massive [examples](https://github.com/tensorlayer/awesome-tensorlayer).
53
+
-***Flexibility*** : TensorLayer APIs are transparent and flexible, inspired by the emerging PyTorch library. Compared to the Keras abstraction, TensorLayer makes it much easier to build and train complex AI models.
54
+
-***Zero-cost Abstraction*** : Though simple to use, TensorLayer does not require you to make any compromise in the performance of TensorFlow (Check the following benchmark section for more details).
55
55
56
-
| Mode | Lib | Data Format | Max GPU Memory Usage(MB) |Max CPU Memory Usage(MB) | Avg CPU Memory Usage(MB) | Runtime (sec) |
TensorLayer is NOT yet another library in the TensorFlow world. Other wrappers like Keras and TFLearn
57
+
hide many powerful features of TensorFlow and provide little support for writing custom, complex AI models. Inspired by PyTorch, TensorLayer APIs are simple, flexible and most importantly, pythonic.
58
+
TensorLayer has a fast-growing community. It has been used by researchers and engineers all over the world, including those from Peking University,
59
+
Imperial College London, UC Berkeley, Carnegie Mellon University, Stanford University, and companies like Google, Microsoft, Alibaba, Tencent, Xiaomi, and Bloomberg.
63
60
61
+
# Multilingual documents
64
62
65
-
TensorLayer stands at a unique spot in the library landscape. Other wrapper libraries like Keras and TFLearn also provide high-level abstractions. They, however, often
66
-
hide the underlying engine from users, which make them hard to customize
67
-
and fine-tune. On the contrary, TensorLayer APIs are generally lightweight, flexible and transparent.
68
-
Users often find it easy to start with the examples and tutorials, and then dive
69
-
into TensorFlow seamlessly. In addition, TensorLayer does not create library lock-in through native supports for importing components from Keras.
63
+
TensorLayer has extensive documentation for both beginners and professionals. The documentation is available in
64
+
both English and Chinese.
70
65
71
-
TensorLayer has a fast growing usage among top researchers and engineers, from universities like Peking University,
72
-
Imperial College London, UC Berkeley, Carnegie Mellon University, Stanford University, and
73
-
University of Technology of Compiegne (UTC), and companies like Google, Microsoft, Alibaba, Tencent, Xiaomi, and Bloomberg.
You can find a large collection of tutorials, examples and real-world applications using TensorLayer within [examples](examples/) or through the following space:
78
76
@@ -82,73 +80,42 @@ You can find a large collection of tutorials, examples and real-world applicatio
82
80
</div>
83
81
</a>
84
82
85
-
# Documentation
86
-
87
-
TensorLayer has extensive documentation for both beginners and professionals. The documentation is available in
88
-
both English and Chinese. Please click the following icons to find the documents you need:
For latest code for TensorLayer 2.0, please build from the source. TensorLayer 2.0 has pre-requisites including TensorFlow 2, numpy, and others. For GPU support, CUDA and cuDNN are required.
85
+
TensorLayer 2.0 relies on TensorFlow, numpy, and others. To use GPUs, CUDA and cuDNN are required.
100
86
101
87
Install TensorFlow:
102
88
103
89
```bash
104
-
pip3 install tensorflow-gpu==2.0.0-beta1 # specific version (YOU SHOULD INSTALL THIS ONE NOW)
The following table shows the training speeds of [VGG16](http://www.robots.ox.ac.uk/~vgg/research/very_deep/) using TensorLayer and native TensorFlow on a TITAN Xp.
155
+
156
+
| Mode | Lib | Data Format | Max GPU Memory Usage(MB) |Max CPU Memory Usage(MB) | Avg CPU Memory Usage(MB) | Runtime (sec) |
Please read the [Contributor Guideline](CONTRIBUTING.md) before submitting your PRs.
@@ -201,4 +180,4 @@ If you use TensorLayer for any projects, please cite this paper：
201
180
202
181
# License
203
182
204
-
TensorLayer is released under the Apache 2.0 license. We also host TensorLayer on [iHub](https://code.ihub.org.cn/projects/328) and [Gitee](https://gitee.com/organizations/TensorLayer).
183
+
TensorLayer is released under the Apache 2.0 license.
0 commit comments