How to effectively learn TensorLayerX¶
No matter what stage you are in, we recommend you to spend just 10 minutes to read the source code of TensorLayerX and the Understand layer / Your layer in this website, you will find the abstract methods are very simple for everyone. Reading the source codes helps you to better understand TensorFlow, MindSpore, PaddlePaddle and allows you to implement your own methods easily. For discussion, we recommend Gitter, Help Wanted Issues, QQ group and Wechat group.
For people who new to deep learning, the contributors provided a number of tutorials in this website, these tutorials will guide you to understand convolutional neural network, recurrent neural network, generative adversarial networks and etc. If your already understand the basic of deep learning, we recommend you to skip the tutorials and read the example codes on Github , then implement an example from scratch.
For people from industry, the contributors provided mass format-consistent examples covering computer vision, natural language processing and reinforcement learning. Besides, there are also many TensorFlow users already implemented product-level examples including image captioning, semantic/instance segmentation, machine translation, chatbot and etc., which can be found online. It is worth noting that a wrapper especially for computer vision Tf-Slim can be connected with TensorLayerX seamlessly. Therefore, you may able to find the examples that can be used in your project.
For people from academia, TensorLayerX was originally developed by PhD students who facing issues with other libraries on implement novel algorithm. Installing TensorLayer in editable mode is recommended, so you can extend your methods in TensorLayerX. For research related to image processing such as image captioning, visual QA and etc., you may find it is very helpful to use the existing Tf-Slim pre-trained models with TensorLayerX (a specially layer for connecting Tf-Slim is provided).
Install Master Version¶
To use all new features of TensorLayerX, you need to install the master version from Github. Before that, you need to make sure you already installed git.
[stable version] pip3 install tensorlayerX [master version] pip3 install git+https://github.com/tensorlayer/TensorLayerX.git
Download the TensorLayerX folder from OpenI.
Before editing the TensorLayerX
If your script and TensorLayerX folder are in the same folder, when you edit the
.pyinside TensorLayerX folder, your script can access the new features.
If your script and TensorLayerX folder are not in the same folder, you need to run the following command in the folder contains
setup.pybefore you edit
.pyinside TensorLayerX folder.pip install -e .
Note that, the
tlx.files.load_npz() can only able to load the npz model saved by
If you have a series of model parameters want to load into your TensorLayerX model, you can first assign your parameters into a list in order,
tlx.files.assign_params() to load the parameters into your TensorLayerX model.