diff --git a/docs/source/conf.py b/docs/source/conf.py index ac35ef63b..c9072760b 100644 --- a/docs/source/conf.py +++ b/docs/source/conf.py @@ -20,11 +20,11 @@ # -- Project information ----------------------------------------------------- project = "RecBole" -copyright = "2020, RecBole Contributors" +copyright = "2022, RecBole Contributors" author = "AIBox RecBole group" # The full version, including alpha/beta/rc tags -release = "0.2.0" +release = "1.0.1" # -- General configuration --------------------------------------------------- diff --git a/docs/source/developer_guide/customize_trainers.rst b/docs/source/developer_guide/customize_trainers.rst index 7a457e0b6..e025bb3d9 100644 --- a/docs/source/developer_guide/customize_trainers.rst +++ b/docs/source/developer_guide/customize_trainers.rst @@ -20,7 +20,7 @@ and revise :meth:`~recbole.trainer.trainer.Trainer.evaluate` or :meth:`~recbole. Example ---------------- 1. Alternative Optimization ->>>>>>>>>>>>>>>>>>>>>>>>> +>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> Here we present a simple Trainer example, which is used for alternative optimization. We revise the :meth:`~recbole.trainer.trainer.Trainer._train_epoch` method. To begin with, we need to create a new class for @@ -105,7 +105,7 @@ Complete Code return total_loss 2. Mixed precision training ->>>>>>>>>>>>>>>>>>>>>>>>> +>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> Here we present a simple Trainer example, which is used for mixed precision training. Mixed precision training offers significant computational speedup by performing operations in half-precision @@ -164,7 +164,7 @@ Complete Code scaler.update() 3. Layer-specific learning rate ->>>>>>>>>>>>>>>>>>>>>>>>> +>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> Here we present a simple Trainer example, which is used for setting layer-specific learning rate. For pretrained model, layers closer to the input layer are more likely to have learned more general diff --git a/docs/source/get_started/distributed_training.rst b/docs/source/get_started/distributed_training.rst index 5ab4a8216..6729938d7 100644 --- a/docs/source/get_started/distributed_training.rst +++ b/docs/source/get_started/distributed_training.rst @@ -1,5 +1,5 @@ Distributed Training -=============== +======================= Now we support distributed training and evaluation. Here is a distributed training example for using RecBole. We will show you how to train and test **BPR** model on the **ml-100k** dataset in the distributed environment. diff --git a/docs/source/get_started/started/context-aware.rst b/docs/source/get_started/started/context-aware.rst index 796a701b4..6a8f76aff 100644 --- a/docs/source/get_started/started/context-aware.rst +++ b/docs/source/get_started/started/context-aware.rst @@ -1,16 +1,12 @@ Quick Start: Context-aware Recommendation -=============== +============================================ For context-aware recommendation, we choose **LR** model to show you how to train and test it on the **ml-100k** dataset from both **API** and **source code**. -.. _header-n3: - Quick-start From API --------------------- -.. _header-n4: - 1. Prepare your data: >>>>>>>>>>>>>>>>>>>>>>>>>>>>>> @@ -43,8 +39,6 @@ we set ``rating=4`` as threshold to label the interaction. For more information about label setting, please read the `Label of data `__. -.. _header-n9: - 2. Choose a model: >>>>>>>>>>>>>>>>>>>>>>>>>>>>>> @@ -66,10 +60,8 @@ If you want to run different models, you can read `Running Different Models `__ for more information. -.. _header-n14: - 3. Set training and evaluation config: ->>>>>>>>>>>>>>>>>>>>>>>>>>>>>> +>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> In RecBole, we support multiple training and evaluation methods. You can choose how to train and test model by simply setting the config. @@ -108,7 +100,7 @@ Settings `__ .. _header-n19: 4. Run the model and collect the result ->>>>>>>>>>>>>>>>>>>>>>>>>>>>>> +>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> Now you have finished all the preparations, it’s time to run the model! @@ -199,7 +191,7 @@ can read other docs for depth usage. .. _header-n29: Quick-start From Source ---------------------- +------------------------- Besides using API, you can also directly run the source code of `RecBole `__. The whole process is diff --git a/docs/source/get_started/started/general.rst b/docs/source/get_started/started/general.rst index 98af855aa..5f8cf8a08 100644 --- a/docs/source/get_started/started/general.rst +++ b/docs/source/get_started/started/general.rst @@ -1,16 +1,12 @@ Quick Start: General Recommendation -=============== +===================================== For general recommendation, we choose **BPR** model to show you how to train and test it on the **ml-100k** dataset from both **API** and **source code**. -.. _header-n3: - Quick-start From API -------------------------- -.. _header-n4: - 1. Prepare your data: >>>>>>>>>>>>>>>>>>>>>>>>> @@ -36,8 +32,6 @@ General recommendation models utilize the historical interactions between users and items to make recommendations, so it needs to specify and load the user and item columns of the dataset. -.. _header-n9: - 2. Choose a model: >>>>>>>>>>>>>>>>>>>>>>>>> @@ -59,10 +53,8 @@ If you want to run different models, you can read `Running Different Models `__ for more information. -.. _header-n14: - 3. Set training and evaluation config: ->>>>>>>>>>>>>>>>>>>>>>>>> +>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> In RecBole, we support multiple training and evaluation methods. You can choose how to train and test model by simply setting the config. @@ -101,7 +93,7 @@ Settings `__ .. _header-n40: 4. Run the model and collect the result ->>>>>>>>>>>>>>>>>>>>>>>>> +>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> Now you have finished all the preparations, it’s time to run the model! diff --git a/docs/source/get_started/started/knowledge-based.rst b/docs/source/get_started/started/knowledge-based.rst index abb85a075..62a372f32 100644 --- a/docs/source/get_started/started/knowledge-based.rst +++ b/docs/source/get_started/started/knowledge-based.rst @@ -1,5 +1,5 @@ Quick Start: Knowledge-based Recommendation -=============== +============================================= For Knowledge-based Recommendation, we choose **CKE** model to show you how to train and test it on the **ml-100k** dataset from both **API** and **source code**. @@ -90,7 +90,7 @@ for more information. .. _header-n164: 3. Set training and evaluation config: ->>>>>>>>>>>>>>>>>>>>>>>>>>>>>> +>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> In RecBole, we support multiple training and evaluation methods. You can choose how to train and test model by simply setting the config. @@ -123,7 +123,7 @@ Settings `__ .. _header-n269: 4. Run the model and collect the result ->>>>>>>>>>>>>>>>>>>>>>>>>>>>>> +>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> Now you have finished all the preparations, it’s time to run the model! diff --git a/docs/source/get_started/started/sequential.rst b/docs/source/get_started/started/sequential.rst index d601f174b..27c8504ea 100644 --- a/docs/source/get_started/started/sequential.rst +++ b/docs/source/get_started/started/sequential.rst @@ -1,11 +1,9 @@ Quick Start: Sequential Recommendation -=============== +======================================== For sequential recommendation, we choose **GRU4Rec** model to show you how to train and test it on the **ml-100k** dataset from both **API** and **source code**. -.. _header-n4: - Quick-start From API --------------------- @@ -97,7 +95,7 @@ for more information. .. _header-n16: 3. Set training and evaluation config: ->>>>>>>>>>>>>>>>>>>>>>>>> +>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> In RecBole, we support multiple training and evaluation methods. You can choose how to train and test model by simply setting the config. @@ -134,7 +132,7 @@ Settings `__ .. _header-n21: 4. Run the model and collect the result ->>>>>>>>>>>>>>>>>>>>>>>>> +>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> Now you have finished all the preparations, it’s time to run the model! diff --git a/docs/source/index.rst b/docs/source/index.rst index 9abf84990..ac8dc985f 100644 --- a/docs/source/index.rst +++ b/docs/source/index.rst @@ -89,6 +89,7 @@ Features: recbole/recbole.utils.logger recbole/recbole.utils.utils + The Team ------------------ RecBole is developed and maintained by `RUC, BUPT, ECNU `_. @@ -99,7 +100,7 @@ Here is the list of our lead developers in each development phase. They are the Time Version Lead Developers ====================== =============== ============================================= June 2020 ~ Nov. 2020 v0.1.1 `Shanlei Mu `_, `Yupeng Hou `_, `Zihan Lin `_, `Kaiyuan Li `_ -Nov. 2020 ~ Now v0.1.2 ~ v1.0.0 `Yushuo Chen `_, `Xingyu Pan `_ +Nov. 2020 ~ Now v0.1.2 ~ v1.0.1 `Yushuo Chen `_, `Xingyu Pan `_ ====================== =============== ============================================= License