| **paddlepalm** | an open source NLP pretraining and multitask learning framework, built on paddlepaddle. |
| **paddlepalm** | an open source NLP pretraining and multitask learning framework, built on paddlepaddle. |
...
@@ -204,7 +211,7 @@ To run with multi-task learning mode:
...
@@ -204,7 +211,7 @@ To run with multi-task learning mode:
3. build multi-task forward graph with `multi_head_trainer.build_forward` method.
3. build multi-task forward graph with `multi_head_trainer.build_forward` method.
4. use `paddlepalm.optimizer` (and `paddlepalm.lr_sched` if is necessary) to create a *optimizer*, then build backward through `multi_head_trainer.build_backward`.
4. use `paddlepalm.optimizer` (and `paddlepalm.lr_sched` if is necessary) to create a *optimizer*, then build backward through `multi_head_trainer.build_backward`.
5. fit all prepared readers and data to multi_head_trainer with `multi_head_trainer.fit_readers` method.
5. fit all prepared readers and data to multi_head_trainer with `multi_head_trainer.fit_readers` method.
6.randomly initialize model parameters with `multi_head_trainer.random_init_params` (and `multi_head_trainer.load_pretrain` if needed), then do training with `multi_head_trainer.train`.
6.load pretrain model with `multi_head_trainer.load_pretrain`, or load checkpoint with `multi_head_trainer.load_ckpt` or nothing to do for training from scratch, then do training with `multi_head_trainer.train`.
The save/load and predict operations of a multi_head_trainer is the same as a trainer.
The save/load and predict operations of a multi_head_trainer is the same as a trainer.
@@ -17,18 +17,18 @@ PaddlePALM (PArallel Learning from Multi-tasks) 是一个灵活，通用且易
...
@@ -17,18 +17,18 @@ PaddlePALM (PArallel Learning from Multi-tasks) 是一个灵活，通用且易
#### 特点:
#### 特点:
-**Easy-to-use:** with PALM, *8 steps* to achieve a typical NLP task. Moreover, the model backbone, dataset reader and task output layers have been decoupled, which allows the replacement of any component to other candidates with quite minor changes of your code.
-**Multi-task Learning friendly:***6 steps* to achieve multi-task learning for prepared tasks.
-**支持多任务学习：***6个步骤*即可实现多任务学习任务。
-**Large Scale and Pre-training freiendly:** automatically utilize multi-gpus (if exists) to accelerate training and inference. Minor codes is required for distributed training on clusters.
-**Popular NLP Backbones and Pre-trained models:** multiple state-of-the-art general purpose model architectures and pretrained models (e.g., BERT,ERNIE,RoBERTa,...) are built-in.
-**Easy to Customize:** support customized development of any component (e.g, backbone, task head, reader and optimizer) with reusement of pre-defined ones, which gives developers high flexibility and effeciency to adapt for diverse NLP scenes.
You can easily re-produce following competitive results with minor codes, which covers most of NLP tasks such as classification, matching, sequence labeling, reading comprehension, dialogue understanding and so on. More details can be found in `examples`.
| **paddlepalm** | an open source NLP pretraining and multitask learning framework, built on paddlepaddle. |
<palign="center">
| **paddlepalm.reader** | a collection of elastic task-specific dataset readers. |
<em>PALM架构图</em>
| **paddlepalm.backbone** | a collection of classic NLP representation models, e.g., BERT, ERNIE, RoBERTa. |
</p>
| **paddlepalm.head** | a collection of task-specific output layers. |
</p>
| **paddlepalm.lr_sched** | a collection of learning rate schedualers. |
| **paddlepalm.optimizer** | a collection of optimizers. |
| **paddlepalm.downloader** | a download module for pretrained models with configure and vocab files. |
| **paddlepalm.Trainer** | the core unit to start a single task training/predicting session. A trainer is to build computation graph, manage training and evaluation process, achieve model/checkpoint saving and pretrain_model/checkpoint loading.|
| **paddlepalm.MultiHeadTrainer** | the core unit to start a multi-task training/predicting session. A MultiHeadTrainer is built based on several Trainers. Beyond the inheritance of Trainer, it additionally achieves model backbone reuse across tasks, trainer sampling for multi-task learning, and multi-head inference for effective evaluation and prediction. |
PaddlePALM support both python2 and python3, linux and windows, CPU and GPU. The preferred way to install PaddlePALM is via `pip`. Just run following commands in your shell.
PaddlePALM 支持 python2 和 python3, linux 和 windows, CPU 和 GPU。安装PaddlePALM的首选方法是通过`pip`。只需运行以下命令：
We incorporate many pretrained models to initialize model backbone parameters. Training big NLP model, e.g., 12-layer transformers, with pretrained models is practically much more effective than that with randomly initialized parameters. To see all the available pretrained models and download, run following code in python interpreter (input command `python` in shell):
1.use `paddlepalm.reader` to create a *reader* for dataset loading and input features generation, then call `reader.load_data` method to load your training data.
3.register your *reader* with your *backbone* through `reader.register_with` method. After this step, your reader is able to yield input features used by backbone.
5.create a task *trainer* with `paddlepalm.Trainer`, then build forward graph with backbone and task head (created in step 2 and 4) through `trainer.build_forward`.
6.use `paddlepalm.optimizer` (and `paddlepalm.lr_sched` if is necessary) to create a *optimizer*, then build backward through `trainer.build_backward`.
8.load pretrain model with `trainer.load_pretrain`, or load checkpoint with `trainer.load_ckpt` or nothing to do for training from scratch, then do training with `trainer.train`.
To save models/checkpoints and logs during training, just call `trainer.set_saver` method. More implementation details see [this](https://github.com/PaddlePaddle/PALM/tree/master/examples).
To do predict/evaluation after a training stage, just create another three reader, backbone and head instance with `phase='predict'` (repeat step 1~4 above). Then do predicting with `predict` method in trainer (no need to create another trainer). More implementation details see [this](https://github.com/PaddlePaddle/PALM/tree/master/examples/predict).
### multi-task learning
多任务学习模式下运行:
To run with multi-task learning mode:
1.repeatedly create components (i.e., reader, backbone and head) for each task followed with step 1~5 above.
1.重复创建组件（每个任务按照上述第1~5步执行）。
2.create empty trainers (each trainer is corresponded to one task) and pass them to create a `MultiHeadTrainer`.
3.build multi-task forward graph with `multi_head_trainer.build_forward` method.
3.使用`multi_head_trainer.build_forward`构建多任务前向图。
4.use `paddlepalm.optimizer` (and `paddlepalm.lr_sched` if is necessary) to create a *optimizer*, then build backward through `multi_head_trainer.build_backward`.
6.randomly initialize model parameters with `multi_head_trainer.random_init_params` (and `multi_head_trainer.load_pretrain` if needed), then do training with `multi_head_trainer.train`.
The save/load and predict operations of a multi_head_trainer is the same as a trainer.
multi_head_trainer的保存/加载和预测操作与trainer相同。
For more implementation details with `multi_head_trainer`, see
更多实现`multi_head_trainer`的细节, 请见
-[ATIS: joint training of dialogue intent recognition and slot filling](https://github.com/PaddlePaddle/PALM/tree/master/examples/multi-task)
-[ATIS: joint training of dialogue intent recognition and slot filling](https://github.com/PaddlePaddle/PALM/tree/master/examples/multi-task)
-[MRQA: learning reading comprehension auxilarized with mask language model]()(初次发版先不用加)
-[MRQA: learning reading comprehension auxilarized with mask language model]()(初次发版先不用加)
## License
This tutorial is contributed by [PaddlePaddle](https://github.com/PaddlePaddle/Paddle) and licensed under the [Apache-2.0 license](https://github.com/PaddlePaddle/models/blob/develop/LICENSE).
