changes examples to pl_examples for name connflict

pl_examples/basic_examples/README.md

@@ -0,0 +1,39 @@
+# Basic Examples   
+Use these examples to test how lightning works.   
+
+#### Test on CPU  
+```bash
+python cpu_template.py
+```
+
+---   
+#### Train on a single GPU
+```bash
+python gpu_template.py --gpus 1
+```   
+
+---    
+#### DataParallel (dp)   
+Train on multiple GPUs using DataParallel.
+
+```bash
+python gpu_template.py --gpus 2 --distributed_backend dp
+```   
+
+---
+#### DistributedDataParallel (ddp)    
+
+Train on multiple GPUs using DistributedDataParallel   
+```bash
+python gpu_template.py --gpus 2 --distributed_backend ddp
+```
+
+---
+#### DistributedDataParallel+DP (ddp2)    
+
+Train on multiple GPUs using DistributedDataParallel + dataparallel.
+On a single node, uses all GPUs for 1 model. Then shares gradient information
+across nodes.   
+```bash
+python gpu_template.py --gpus 2 --distributed_backend ddp2
+```

pl_examples/basic_examples/cpu_template.py

@@ -0,0 +1,53 @@
+"""
+Runs a model on a single node across N-gpus.
+"""
+import os
+import numpy as np
+import torch
+
+from argparse import ArgumentParser
+from pytorch_lightning import Trainer
+from pl_examples.basic_examples.lightning_module_template import LightningTemplateModel
+
+SEED = 2334
+torch.manual_seed(SEED)
+np.random.seed(SEED)
+
+
+def main(hparams):
+    """
+    Main training routine specific for this project
+    :param hparams:
+    """
+    # ------------------------
+    # 1 INIT LIGHTNING MODEL
+    # ------------------------
+    model = LightningTemplateModel(hparams)
+
+    # ------------------------
+    # 2 INIT TRAINER
+    # ------------------------
+    trainer = Trainer()
+
+    # ------------------------
+    # 3 START TRAINING
+    # ------------------------
+    trainer.fit(model)
+
+
+if __name__ == '__main__':
+    # ------------------------
+    # TRAINING ARGUMENTS
+    # ------------------------
+    # these are project-wide arguments
+    root_dir = os.path.dirname(os.path.realpath(__file__))
+    parent_parser = ArgumentParser(add_help=False)
+
+    # each LightningModule defines arguments relevant to it
+    parser = LightningTemplateModel.add_model_specific_args(parent_parser, root_dir)
+    hyperparams = parser.parse_args()
+
+    # ---------------------
+    # RUN TRAINING
+    # ---------------------
+    main(hyperparams)

pl_examples/basic_examples/gpu_template.py

@@ -0,0 +1,78 @@
+"""
+Runs a model on a single node across N-gpus.
+"""
+import os
+import numpy as np
+import torch
+
+from argparse import ArgumentParser
+from pytorch_lightning import Trainer
+from pl_examples.basic_examples.lightning_module_template import LightningTemplateModel
+
+SEED = 2334
+torch.manual_seed(SEED)
+np.random.seed(SEED)
+
+
+def main(hparams):
+    """
+    Main training routine specific for this project
+    :param hparams:
+    """
+    # ------------------------
+    # 1 INIT LIGHTNING MODEL
+    # ------------------------
+    model = LightningTemplateModel(hparams)
+
+    # ------------------------
+    # 2 INIT TRAINER
+    # ------------------------
+    trainer = Trainer(
+        gpus=hparams.gpus,
+        distributed_backend=hparams.distributed_backend,
+        use_amp=hparams.use_16bit
+    )
+
+    # ------------------------
+    # 3 START TRAINING
+    # ------------------------
+    trainer.fit(model)
+
+
+if __name__ == '__main__':
+    # ------------------------
+    # TRAINING ARGUMENTS
+    # ------------------------
+    # these are project-wide arguments
+
+    root_dir = os.path.dirname(os.path.realpath(__file__))
+    parent_parser = ArgumentParser(add_help=False)
+
+    # gpu args
+    parent_parser.add_argument(
+        '--gpus',
+        type=int,
+        default=2,
+        help='how many gpus'
+    )
+    parent_parser.add_argument(
+        '--distributed_backend',
+        type=str,
+        default='dp',
+        help='supports three options dp, ddp, ddp2'
+    )
+    parent_parser.add_argument(
+        '--use_16bit',
+        dest='use_16bit',
+        action='store_true',
+        help='if true uses 16 bit precision'
+    )
+
+    # each LightningModule defines arguments relevant to it
+    parser = LightningTemplateModel.add_model_specific_args(parent_parser, root_dir)
+    hyperparams = parser.parse_args()
+
+    # ---------------------
+    # RUN TRAINING
+    # ---------------------
+    main(hyperparams)

pl_examples/basic_examples/lightning_module_template.py

@@ -0,0 +1,256 @@
+"""
+Example template for defining a system
+"""
+import os
+from collections import OrderedDict
+import torch.nn as nn
+from torchvision.datasets import MNIST
+import torchvision.transforms as transforms
+import torch
+import torch.nn.functional as F
+from argparse import ArgumentParser
+from torch import optim
+from torch.utils.data import DataLoader
+from torch.utils.data.distributed import DistributedSampler
+
+import pytorch_lightning as pl
+from pytorch_lightning.root_module.root_module import LightningModule
+
+
+class LightningTemplateModel(LightningModule):
+    """
+    Sample model to show how to define a template
+    """
+
+    def __init__(self, hparams):
+        """
+        Pass in parsed HyperOptArgumentParser to the model
+        :param hparams:
+        """
+        # init superclass
+        super(LightningTemplateModel, self).__init__()
+        self.hparams = hparams
+
+        self.batch_size = hparams.batch_size
+
+        # if you specify an example input, the summary will show input/output for each layer
+        self.example_input_array = torch.rand(5, 28 * 28)
+
+        # build model
+        self.__build_model()
+
+    # ---------------------
+    # MODEL SETUP
+    # ---------------------
+    def __build_model(self):
+        """
+        Layout model
+        :return:
+        """
+        self.c_d1 = nn.Linear(in_features=self.hparams.in_features,
+                              out_features=self.hparams.hidden_dim)
+        self.c_d1_bn = nn.BatchNorm1d(self.hparams.hidden_dim)
+        self.c_d1_drop = nn.Dropout(self.hparams.drop_prob)
+
+        self.c_d2 = nn.Linear(in_features=self.hparams.hidden_dim,
+                              out_features=self.hparams.out_features)
+
+    # ---------------------
+    # TRAINING
+    # ---------------------
+    def forward(self, x):
+        """
+        No special modification required for lightning, define as you normally would
+        :param x:
+        :return:
+        """
+
+        x = self.c_d1(x)
+        x = torch.tanh(x)
+        x = self.c_d1_bn(x)
+        x = self.c_d1_drop(x)
+
+        x = self.c_d2(x)
+        logits = F.log_softmax(x, dim=1)
+
+        return logits
+
+    def loss(self, labels, logits):
+        nll = F.nll_loss(logits, labels)
+        return nll
+
+    def training_step(self, batch, batch_idx):
+        """
+        Lightning calls this inside the training loop
+        :param batch:
+        :return:
+        """
+        # forward pass
+        x, y = batch
+        x = x.view(x.size(0), -1)
+
+        y_hat = self.forward(x)
+
+        # calculate loss
+        loss_val = self.loss(y, y_hat)
+
+        # in DP mode (default) make sure if result is scalar, there's another dim in the beginning
+        if self.trainer.use_dp or self.trainer.use_ddp2:
+            loss_val = loss_val.unsqueeze(0)
+
+        tqdm_dict = {'train_loss': loss_val}
+        output = OrderedDict({
+            'loss': loss_val,
+            'progress_bar': tqdm_dict,
+            'log': tqdm_dict
+        })
+
+        # can also return just a scalar instead of a dict (return loss_val)
+        return output
+
+    def validation_step(self, batch, batch_idx):
+        """
+        Lightning calls this inside the validation loop
+        :param batch:
+        :return:
+        """
+        x, y = batch
+        x = x.view(x.size(0), -1)
+        y_hat = self.forward(x)
+
+        loss_val = self.loss(y, y_hat)
+
+        # acc
+        labels_hat = torch.argmax(y_hat, dim=1)
+        val_acc = torch.sum(y == labels_hat).item() / (len(y) * 1.0)
+        val_acc = torch.tensor(val_acc)
+
+        if self.on_gpu:
+            val_acc = val_acc.cuda(loss_val.device.index)
+
+        # in DP mode (default) make sure if result is scalar, there's another dim in the beginning
+        if self.trainer.use_dp or self.trainer.use_ddp2:
+            loss_val = loss_val.unsqueeze(0)
+            val_acc = val_acc.unsqueeze(0)
+
+        output = OrderedDict({
+            'val_loss': loss_val,
+            'val_acc': val_acc,
+        })
+
+        # can also return just a scalar instead of a dict (return loss_val)
+        return output
+
+    def validation_end(self, outputs):
+        """
+        Called at the end of validation to aggregate outputs
+        :param outputs: list of individual outputs of each validation step
+        :return:
+        """
+        # if returned a scalar from validation_step, outputs is a list of tensor scalars
+        # we return just the average in this case (if we want)
+        # return torch.stack(outputs).mean()
+
+        val_loss_mean = 0
+        val_acc_mean = 0
+        for output in outputs:
+            val_loss = output['val_loss']
+
+            # reduce manually when using dp
+            if self.trainer.use_dp:
+                val_loss = torch.mean(val_loss)
+            val_loss_mean += val_loss
+
+            # reduce manually when using dp
+            val_acc = output['val_acc']
+            if self.trainer.use_dp or self.trainer.use_ddp2:
+                val_acc = torch.mean(val_acc)
+
+            val_acc_mean += val_acc
+
+        val_loss_mean /= len(outputs)
+        val_acc_mean /= len(outputs)
+        tqdm_dict = {'val_loss': val_loss_mean, 'val_acc': val_acc_mean}
+        result = {'progress_bar': tqdm_dict, 'log': tqdm_dict, 'val_loss': val_loss_mean}
+        return result
+
+    # ---------------------
+    # TRAINING SETUP
+    # ---------------------
+    def configure_optimizers(self):
+        """
+        return whatever optimizers we want here
+        :return: list of optimizers
+        """
+        optimizer = optim.Adam(self.parameters(), lr=self.hparams.learning_rate)
+        scheduler = optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=10)
+        return [optimizer], [scheduler]
+
+    def __dataloader(self, train):
+        # init data generators
+        transform = transforms.Compose([transforms.ToTensor(),
+                                        transforms.Normalize((0.5,), (1.0,))])
+        dataset = MNIST(root=self.hparams.data_root, train=train,
+                        transform=transform, download=True)
+
+        # when using multi-node (ddp) we need to add the  datasampler
+        train_sampler = None
+        batch_size = self.hparams.batch_size
+
+        if self.use_ddp:
+            train_sampler = DistributedSampler(dataset)
+
+        should_shuffle = train_sampler is None
+        loader = DataLoader(
+            dataset=dataset,
+            batch_size=batch_size,
+            shuffle=should_shuffle,
+            sampler=train_sampler,
+            num_workers=0
+        )
+
+        return loader
+
+    @pl.data_loader
+    def train_dataloader(self):
+        print('training data loader called')
+        return self.__dataloader(train=True)
+
+    @pl.data_loader
+    def val_dataloader(self):
+        print('val data loader called')
+        return self.__dataloader(train=False)
+
+    @pl.data_loader
+    def test_dataloader(self):
+        print('test data loader called')
+        return self.__dataloader(train=False)
+
+    @staticmethod
+    def add_model_specific_args(parent_parser, root_dir):  # pragma: no cover
+        """
+        Parameters you define here will be available to your model through self.hparams
+        :param parent_parser:
+        :param root_dir:
+        :return:
+        """
+        parser = ArgumentParser(parents=[parent_parser])
+
+        # param overwrites
+        # parser.set_defaults(gradient_clip_val=5.0)
+
+        # network params
+        parser.add_argument('--in_features', default=28 * 28, type=int)
+        parser.add_argument('--out_features', default=10, type=int)
+        # use 500 for CPU, 50000 for GPU to see speed difference
+        parser.add_argument('--hidden_dim', default=50000, type=int)
+        parser.add_argument('--drop_prob', default=0.2, type=float)
+        parser.add_argument('--learning_rate', default=0.001, type=float)
+
+        # data
+        parser.add_argument('--data_root', default=os.path.join(root_dir, 'mnist'), type=str)
+
+        # training params (opt)
+        parser.add_argument('--optimizer_name', default='adam', type=str)
+        parser.add_argument('--batch_size', default=64, type=int)
+        return parser