diff --git a/Pytorch-Lightning/LightningModule/index.html b/Pytorch-Lightning/LightningModule/index.html
index 4d39b7b7..27fc9b5d 100644
--- a/Pytorch-Lightning/LightningModule/index.html
+++ b/Pytorch-Lightning/LightningModule/index.html
@@ -181,7 +181,7 @@
                 <h1 id="lightning-module">Lightning module</h1>
 <p>[<a href="https://github.com/williamFalcon/pytorch-lightning/blob/master/pytorch_lightning/root_module/root_module.py">Github Code</a>]</p>
 <p>A lightning module is a strict superclass of nn.Module, it provides a standard interface for the trainer to interact with the model.</p>
-<p>The easiest thing to do is copy <a href="../lightning_module_template.py">this template</a> and modify accordingly. </p>
+<p>The easiest thing to do is copy <a href="../../examples/new_project_templates/lightning_module_template.py">this template</a> and modify accordingly. </p>
 <p>Otherwise, to Define a Lightning Module, implement the following methods:</p>
 <p><strong>Required</strong>:  </p>
 <ul>
diff --git a/Pytorch-Lightning/lightning_module_template.py b/Pytorch-Lightning/lightning_module_template.py
deleted file mode 100644
index 152bf5a9..00000000
--- a/Pytorch-Lightning/lightning_module_template.py
+++ /dev/null
@@ -1,225 +0,0 @@
-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 test_tube import HyperOptArgumentParser
-from torch import optim
-
-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__(hparams)
-
-        self.batch_size = hparams.batch_size
-
-        # 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, data_batch, batch_i):
-        """
-        Lightning calls this inside the training loop
-        :param data_batch:
-        :return:
-        """
-        # forward pass
-        x, y = data_batch
-        x = x.view(x.size(0), -1)
-        y_hat = self.forward(x)
-
-        # calculate loss
-        loss_val = self.loss(y, y_hat)
-
-        output = OrderedDict({
-            'loss': loss_val,
-            'tqdm_metrics': {}
-        })
-        return output
-
-    def validation_step(self, data_batch, batch_i):
-        """
-        Lightning calls this inside the validation loop
-        :param data_batch:
-        :return:
-        """
-        x, y = data_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)
-
-        output = OrderedDict({
-            'val_loss': loss_val,
-            'val_acc': torch.tensor(val_acc),
-        })
-        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:
-        """
-        val_loss_mean = 0
-        val_acc_mean = 0
-        for output in outputs:
-            val_loss_mean += output['val_loss']
-            val_acc_mean += output['val_acc']
-
-        val_loss_mean /= len(outputs)
-        val_acc_mean /= len(outputs)
-        tqdm_dic = {'val_loss': val_loss_mean.item(), 'val_acc': val_acc_mean.item()}
-        return tqdm_dic
-
-    def update_tng_log_metrics(self, logs):
-        return logs
-
-    # ---------------------
-    # MODEL SAVING
-    # ---------------------
-    def get_save_dict(self):
-        checkpoint = {'state_dict': self.state_dict()}
-        return checkpoint
-
-    def load_model_specific(self, checkpoint):
-        self.load_state_dict(checkpoint['state_dict'])
-        pass
-
-    # ---------------------
-    # TRAINING SETUP
-    # ---------------------
-    def configure_optimizers(self):
-        """
-        return whatever optimizers we want here
-        :return: list of optimizers
-        """
-        optimizer = optim.Adam(lr=self.hparams.learning_rate)
-        return [optimizer]
-
-    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)
-
-        loader = torch.utils.data.DataLoader(
-            dataset=dataset,
-            batch_size=self.hparams.batch_size,
-            shuffle=True
-        )
-
-        return loader
-
-    @property
-    def tng_dataloader(self):
-        if self._tng_dataloader is None:
-            try:
-                self._tng_dataloader = self.__dataloader(train=True)
-            except Exception as e:
-                print(e)
-                raise e
-        return self._tng_dataloader
-
-    @property
-    def val_dataloader(self):
-        if self._val_dataloader is None:
-            try:
-                self._val_dataloader = self.__dataloader(train=False)
-            except Exception as e:
-                print(e)
-                raise e
-        return self._val_dataloader
-
-    @property
-    def test_dataloader(self):
-        if self._test_dataloader is None:
-            try:
-                self._test_dataloader = self.__dataloader(train=False)
-            except Exception as e:
-                print(e)
-                raise e
-        return self._test_dataloader
-
-    @staticmethod
-    def add_model_specific_args(parent_parser, root_dir):
-        """
-        Parameters you define here will be available to your model through self.hparams
-        :param parent_parser:
-        :param root_dir:
-        :return:
-        """
-        parser = HyperOptArgumentParser(strategy=parent_parser.strategy, parents=[parent_parser])
-
-        # param overwrites
-        # parser.set_defaults(gradient_clip=5.0)
-
-        # network params
-        parser.opt_list('--drop_prob', default=0.2, options=[0.2, 0.5], type=float, tunable=False)
-        parser.add_argument('--in_features', default=28*28)
-        parser.add_argument('--out_features', default=10)
-        parser.add_argument('--hidden_dim', default=50000) # use 500 for CPU, 50000 for GPU to see speed difference
-
-        # data
-        parser.add_argument('--data_root', default=os.path.join(root_dir, 'mnist'), type=str)
-
-        # training params (opt)
-        parser.opt_list('--learning_rate', default=0.001, type=float, options=[0.0001, 0.0005, 0.001, 0.005],
-                        tunable=False)
-        parser.opt_list('--batch_size', default=256, type=int, options=[32, 64, 128, 256], tunable=False)
-        parser.opt_list('--optimizer_name', default='adam', type=str, options=['adam'], tunable=False)
-        return parser
diff --git a/index.html b/index.html
index 0bd7587c..6dc23b5f 100644
--- a/index.html
+++ b/index.html
@@ -57,7 +57,9 @@
     
         <ul>
         
-            <li><a class="toctree-l3" href="#quick-start">Quick start</a></li>
+            <li><a class="toctree-l3" href="#main-docs">Main Docs</a></li>
+        
+            <li><a class="toctree-l3" href="#new-project-quick-start">New project Quick Start</a></li>
         
             <li><a class="toctree-l3" href="#quick-start-examples">Quick start examples</a></li>
         
@@ -167,11 +169,20 @@
             <div class="section">
               
                 <h1 id="pytorch-lightning-documentation">PYTORCH-LIGHTNING DOCUMENTATION</h1>
-<h6 id="quick-start">Quick start</h6>
+<h6 id="main-docs">Main Docs</h6>
 <ul>
-<li><a href="Pytorch-Lightning/LightningModule/">Define a LightningModule</a>  </li>
-<li>Set up the trainer   </li>
+<li><a href="Pytorch-Lightning/LightningModule">LightningModule</a>  </li>
+<li><a href="Trainer/">Trainer</a>  </li>
 </ul>
+<h6 id="new-project-quick-start">New project Quick Start</h6>
+<ol>
+<li><a href="https://github.com/williamFalcon/pytorch-lightning/blob/master/examples/new_project_templates/lightning_module_template.py">Define a LightningModule</a>  </li>
+<li>Pick a trainer      <ul>
+<li><a href="https://github.com/williamFalcon/pytorch-lightning/blob/master/examples/new_project_templates/trainer_cpu_template.py">Basic CPU Trainer</a> </li>
+<li><a href="https://github.com/williamFalcon/pytorch-lightning/blob/master/examples/new_project_templates/trainer_gpu_cluster_template.py">GPU cluster Trainer</a></li>
+</ul>
+</li>
+</ol>
 <h6 id="quick-start-examples">Quick start examples</h6>
 <ul>
 <li>CPU example   </li>
@@ -273,5 +284,5 @@
 
 <!--
 MkDocs version : 1.0.4
-Build Date UTC : 2019-06-27 18:22:11
+Build Date UTC : 2019-06-27 18:32:34
 -->
diff --git a/search/search_index.json b/search/search_index.json
index 34cf4c3f..f261189b 100644
--- a/search/search_index.json
+++ b/search/search_index.json
@@ -1 +1 @@
-{"config":{"lang":["en"],"prebuild_index":false,"separator":"[\\s\\-]+"},"docs":[{"location":"","text":"PYTORCH-LIGHTNING DOCUMENTATION Quick start Define a LightningModule Set up the trainer Quick start examples CPU example Single GPU example Multi-gpu example SLURM cluster grid search example Training loop Accumulate gradients Check GPU usage Check which gradients are nan Check validation every n epochs Display metrics in progress bar Force training for min or max epochs Inspect gradient norms Hooks Learning rate annealing Make model overfit on subset of data Multiple optimizers (like GANs) Set how much of the training set to check (1-100%) training_step function Validation loop Display metrics in progress bar hooks Set how much of the validation set to check (1-100%) Set validation check frequency within 1 training epoch (1-100%) validation_step function Why does validation run first for 5 steps? Distributed training Single-gpu Multi-gpu Multi-node 16-bit mixed precision Checkpointing Model saving Model loading Computing cluster (SLURM) Automatic checkpointing Automatic saving, loading Running grid search on a cluster Walltime auto-resubmit","title":"PYTORCH-LIGHTNING DOCUMENTATION"},{"location":"#pytorch-lightning-documentation","text":"","title":"PYTORCH-LIGHTNING DOCUMENTATION"},{"location":"#quick-start","text":"Define a LightningModule Set up the trainer","title":"Quick start"},{"location":"#quick-start-examples","text":"CPU example Single GPU example Multi-gpu example SLURM cluster grid search example","title":"Quick start examples"},{"location":"#training-loop","text":"Accumulate gradients Check GPU usage Check which gradients are nan Check validation every n epochs Display metrics in progress bar Force training for min or max epochs Inspect gradient norms Hooks Learning rate annealing Make model overfit on subset of data Multiple optimizers (like GANs) Set how much of the training set to check (1-100%) training_step function","title":"Training loop"},{"location":"#validation-loop","text":"Display metrics in progress bar hooks Set how much of the validation set to check (1-100%) Set validation check frequency within 1 training epoch (1-100%) validation_step function Why does validation run first for 5 steps?","title":"Validation loop"},{"location":"#distributed-training","text":"Single-gpu Multi-gpu Multi-node 16-bit mixed precision","title":"Distributed training"},{"location":"#checkpointing","text":"Model saving Model loading","title":"Checkpointing"},{"location":"#computing-cluster-slurm","text":"Automatic checkpointing Automatic saving, loading Running grid search on a cluster Walltime auto-resubmit","title":"Computing cluster (SLURM)"},{"location":"Pytorch-Lightning/LightningModule/","text":"Lightning module [ Github Code ] A lightning module is a strict superclass of nn.Module, it provides a standard interface for the trainer to interact with the model. The easiest thing to do is copy this template and modify accordingly. Otherwise, to Define a Lightning Module, implement the following methods: Required : training_step validation_step validation_end configure_optimizers get_save_dict load_model_specific tng_dataloader tng_dataloader test_dataloader Optional : update_tng_log_metrics add_model_specific_args training_ste**p def training_step(self, data_batch, batch_nb) In this step you'd normally do the forward pass and calculate the loss for a batch. You can also do fancier things like multiple forward passes or something specific to your model. Params Param description data_batch The output of your dataloader. A tensor, tuple or list batch_nb Integer displaying which batch this is Return Dictionary or OrderedDict key value is required loss tensor scalar Y prog Dict for progress bar display. Must have only tensors N Example def training_step(self, data_batch, batch_nb): x, y, z = data_batch # implement your own out = self.forward(x) loss = self.loss(out, x) output = { 'loss': loss, # required 'prog': {'tng_loss': loss, 'batch_nb': batch_nb} # optional } # return a dict return output validation_step def validation_step(self, data_batch, batch_nb) In this step you'd normally do the forward pass and calculate the loss for a batch. You can also do fancier things like multiple forward passes or something specific to your model. This is most likely the same as your training_step. But unlike training step, the outputs from here will go to validation_end for collation. Params Param description data_batch The output of your dataloader. A tensor, tuple or list batch_nb Integer displaying which batch this is Return Return description optional dict Dict of OrderedDict with metrics to display in progress bar. All keys must be tensors. Y Example def validation_step(self, data_batch, batch_nb): x, y, z = data_batch # implement your own out = self.forward(x) loss = self.loss(out, x) # calculate acc labels_hat = torch.argmax(out, dim=1) val_acc = torch.sum(y == labels_hat).item() / (len(y) * 1.0) # all optional... # return whatever you need for the collation function validation_end output = OrderedDict({ 'val_loss': loss_val, 'val_acc': torch.tensor(val_acc), # everything must be a tensor }) # return an optional dict return output validation_end def validation_end(self, outputs) Called at the end of the validation loop with the output of each validation_step. Params Param description outputs List of outputs you defined in validation_step Return Return description optional dict Dict of OrderedDict with metrics to display in progress bar Y Example 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: \"\"\" val_loss_mean = 0 val_acc_mean = 0 for output in outputs: val_loss_mean += output['val_loss'] val_acc_mean += output['val_acc'] val_loss_mean /= len(outputs) val_acc_mean /= len(outputs) tqdm_dic = {'val_loss': val_loss_mean.item(), 'val_acc': val_acc_mean.item()} return tqdm_dic configure_optimizers def configure_optimizers(self) Set up as many optimizers as you need. Normally you'd need one. But in the case of GANs or something more esoteric you might have multiple. Lightning will call .backward() and .step() on each one. If you use 16 bit precision it will also handle that. Return List - List of optimizers Example # most cases def configure_optimizers(self): opt = Adam(lr=0.01) return [opt] # gan example def configure_optimizers(self): generator_opt = Adam(lr=0.01) disriminator_opt = Adam(lr=0.02) return [generator_opt, disriminator_opt] get_save_dict def get_save_dict(self) Called by lightning to checkpoint your model. Lightning saves current epoch, current batch nb, etc... All you have to return is what specifically about your lightning model you want to checkpoint. Return Dictionary - No required keys. Most of the time as described in this example. Example def get_save_dict(self): # 99% of use cases this is all you need to return checkpoint = {'state_dict': self.state_dict()} return checkpoint load_model_specific def load_model_specific(self, checkpoint) Called by lightning to restore your model. This is your chance to restore your model using the keys you added in get_save_dict. Lightning will automatically restore current epoch, batch nb, etc. Return Nothing Example def load_model_specific(self, checkpoint): # you defined 'state_dict' in get_save_dict() self.load_state_dict(checkpoint['state_dict']) tng_dataloader @property def tng_dataloader(self) Called by lightning during training loop. Define it as a property. Return Pytorch DataLoader Example @property def tng_dataloader(self): if self._tng_dataloader is None: try: transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))]) dataset = MNIST(root='/path/to/mnist/', train=True, transform=transform, download=True) loader = torch.utils.data.DataLoader( dataset=dataset, batch_size=self.hparams.batch_size, shuffle=True ) self._tng_dataloader = loader except Exception as e: raise e return self._tng_dataloader val_dataloader @property def tng_dataloader(self) Called by lightning during validation loop. Define it as a property. Return Pytorch DataLoader Example @property def val_dataloader(self): if self._val_dataloader is None: try: transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))]) dataset = MNIST(root='/path/to/mnist/', train=False, transform=transform, download=True) loader = torch.utils.data.DataLoader( dataset=dataset, batch_size=self.hparams.batch_size, shuffle=True ) self._val_dataloader = loader except Exception as e: raise e return self._val_dataloader test_dataloader @property def test_dataloader(self) Called by lightning during test loop. Define it as a property. Return Pytorch DataLoader Example @property def test_dataloader(self): if self._test_dataloader is None: try: transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))]) dataset = MNIST(root='/path/to/mnist/', train=False, transform=transform, download=True) loader = torch.utils.data.DataLoader( dataset=dataset, batch_size=self.hparams.batch_size, shuffle=True ) self._test_dataloader = loader except Exception as e: raise e return self._test_dataloader update_tng_log_metrics def update_tng_log_metrics(self, logs) Called by lightning right before it logs metrics for this batch. This is a chance to ammend or add to the metrics about to be logged. Return Dict Example def update_tng_log_metrics(self, logs): # modify or add to logs return logs add_model_specific_args @staticmethod def add_model_specific_args(parent_parser, root_dir) Lightning has a list of default argparse commands. This method is your chance to add or modify commands specific to your model. The argument parser is available anywhere in your model by calling self.hparams Return An argument parser Example @staticmethod def add_model_specific_args(parent_parser, root_dir): parser = HyperOptArgumentParser(strategy=parent_parser.strategy, parents=[parent_parser]) # param overwrites # parser.set_defaults(gradient_clip=5.0) # network params parser.opt_list('--drop_prob', default=0.2, options=[0.2, 0.5], type=float, tunable=False) parser.add_argument('--in_features', default=28*28) parser.add_argument('--out_features', default=10) parser.add_argument('--hidden_dim', default=50000) # use 500 for CPU, 50000 for GPU to see speed difference # data parser.add_argument('--data_root', default=os.path.join(root_dir, 'mnist'), type=str) # training params (opt) parser.opt_list('--learning_rate', default=0.001, type=float, options=[0.0001, 0.0005, 0.001, 0.005], tunable=False) parser.opt_list('--batch_size', default=256, type=int, options=[32, 64, 128, 256], tunable=False) parser.opt_list('--optimizer_name', default='adam', type=str, options=['adam'], tunable=False) return parser","title":"Lightning module"},{"location":"Pytorch-Lightning/LightningModule/#lightning-module","text":"[ Github Code ] A lightning module is a strict superclass of nn.Module, it provides a standard interface for the trainer to interact with the model. The easiest thing to do is copy this template and modify accordingly. Otherwise, to Define a Lightning Module, implement the following methods: Required : training_step validation_step validation_end configure_optimizers get_save_dict load_model_specific tng_dataloader tng_dataloader test_dataloader Optional : update_tng_log_metrics add_model_specific_args","title":"Lightning module"},{"location":"Pytorch-Lightning/LightningModule/#training_step","text":"def training_step(self, data_batch, batch_nb) In this step you'd normally do the forward pass and calculate the loss for a batch. You can also do fancier things like multiple forward passes or something specific to your model. Params Param description data_batch The output of your dataloader. A tensor, tuple or list batch_nb Integer displaying which batch this is Return Dictionary or OrderedDict key value is required loss tensor scalar Y prog Dict for progress bar display. Must have only tensors N Example def training_step(self, data_batch, batch_nb): x, y, z = data_batch # implement your own out = self.forward(x) loss = self.loss(out, x) output = { 'loss': loss, # required 'prog': {'tng_loss': loss, 'batch_nb': batch_nb} # optional } # return a dict return output","title":"training_ste**p"},{"location":"Pytorch-Lightning/LightningModule/#validation_step","text":"def validation_step(self, data_batch, batch_nb) In this step you'd normally do the forward pass and calculate the loss for a batch. You can also do fancier things like multiple forward passes or something specific to your model. This is most likely the same as your training_step. But unlike training step, the outputs from here will go to validation_end for collation. Params Param description data_batch The output of your dataloader. A tensor, tuple or list batch_nb Integer displaying which batch this is Return Return description optional dict Dict of OrderedDict with metrics to display in progress bar. All keys must be tensors. Y Example def validation_step(self, data_batch, batch_nb): x, y, z = data_batch # implement your own out = self.forward(x) loss = self.loss(out, x) # calculate acc labels_hat = torch.argmax(out, dim=1) val_acc = torch.sum(y == labels_hat).item() / (len(y) * 1.0) # all optional... # return whatever you need for the collation function validation_end output = OrderedDict({ 'val_loss': loss_val, 'val_acc': torch.tensor(val_acc), # everything must be a tensor }) # return an optional dict return output","title":"validation_step"},{"location":"Pytorch-Lightning/LightningModule/#validation_end","text":"def validation_end(self, outputs) Called at the end of the validation loop with the output of each validation_step. Params Param description outputs List of outputs you defined in validation_step Return Return description optional dict Dict of OrderedDict with metrics to display in progress bar Y Example 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: \"\"\" val_loss_mean = 0 val_acc_mean = 0 for output in outputs: val_loss_mean += output['val_loss'] val_acc_mean += output['val_acc'] val_loss_mean /= len(outputs) val_acc_mean /= len(outputs) tqdm_dic = {'val_loss': val_loss_mean.item(), 'val_acc': val_acc_mean.item()} return tqdm_dic","title":"validation_end"},{"location":"Pytorch-Lightning/LightningModule/#configure_optimizers","text":"def configure_optimizers(self) Set up as many optimizers as you need. Normally you'd need one. But in the case of GANs or something more esoteric you might have multiple. Lightning will call .backward() and .step() on each one. If you use 16 bit precision it will also handle that.","title":"configure_optimizers"},{"location":"Pytorch-Lightning/LightningModule/#return","text":"List - List of optimizers Example # most cases def configure_optimizers(self): opt = Adam(lr=0.01) return [opt] # gan example def configure_optimizers(self): generator_opt = Adam(lr=0.01) disriminator_opt = Adam(lr=0.02) return [generator_opt, disriminator_opt]","title":"Return"},{"location":"Pytorch-Lightning/LightningModule/#get_save_dict","text":"def get_save_dict(self) Called by lightning to checkpoint your model. Lightning saves current epoch, current batch nb, etc... All you have to return is what specifically about your lightning model you want to checkpoint.","title":"get_save_dict"},{"location":"Pytorch-Lightning/LightningModule/#return_1","text":"Dictionary - No required keys. Most of the time as described in this example. Example def get_save_dict(self): # 99% of use cases this is all you need to return checkpoint = {'state_dict': self.state_dict()} return checkpoint","title":"Return"},{"location":"Pytorch-Lightning/LightningModule/#load_model_specific","text":"def load_model_specific(self, checkpoint) Called by lightning to restore your model. This is your chance to restore your model using the keys you added in get_save_dict. Lightning will automatically restore current epoch, batch nb, etc.","title":"load_model_specific"},{"location":"Pytorch-Lightning/LightningModule/#return_2","text":"Nothing Example def load_model_specific(self, checkpoint): # you defined 'state_dict' in get_save_dict() self.load_state_dict(checkpoint['state_dict'])","title":"Return"},{"location":"Pytorch-Lightning/LightningModule/#tng_dataloader","text":"@property def tng_dataloader(self) Called by lightning during training loop. Define it as a property.","title":"tng_dataloader"},{"location":"Pytorch-Lightning/LightningModule/#return_3","text":"Pytorch DataLoader Example @property def tng_dataloader(self): if self._tng_dataloader is None: try: transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))]) dataset = MNIST(root='/path/to/mnist/', train=True, transform=transform, download=True) loader = torch.utils.data.DataLoader( dataset=dataset, batch_size=self.hparams.batch_size, shuffle=True ) self._tng_dataloader = loader except Exception as e: raise e return self._tng_dataloader","title":"Return"},{"location":"Pytorch-Lightning/LightningModule/#val_dataloader","text":"@property def tng_dataloader(self) Called by lightning during validation loop. Define it as a property.","title":"val_dataloader"},{"location":"Pytorch-Lightning/LightningModule/#return_4","text":"Pytorch DataLoader Example @property def val_dataloader(self): if self._val_dataloader is None: try: transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))]) dataset = MNIST(root='/path/to/mnist/', train=False, transform=transform, download=True) loader = torch.utils.data.DataLoader( dataset=dataset, batch_size=self.hparams.batch_size, shuffle=True ) self._val_dataloader = loader except Exception as e: raise e return self._val_dataloader","title":"Return"},{"location":"Pytorch-Lightning/LightningModule/#test_dataloader","text":"@property def test_dataloader(self) Called by lightning during test loop. Define it as a property.","title":"test_dataloader"},{"location":"Pytorch-Lightning/LightningModule/#return_5","text":"Pytorch DataLoader Example @property def test_dataloader(self): if self._test_dataloader is None: try: transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))]) dataset = MNIST(root='/path/to/mnist/', train=False, transform=transform, download=True) loader = torch.utils.data.DataLoader( dataset=dataset, batch_size=self.hparams.batch_size, shuffle=True ) self._test_dataloader = loader except Exception as e: raise e return self._test_dataloader","title":"Return"},{"location":"Pytorch-Lightning/LightningModule/#update_tng_log_metrics","text":"def update_tng_log_metrics(self, logs) Called by lightning right before it logs metrics for this batch. This is a chance to ammend or add to the metrics about to be logged.","title":"update_tng_log_metrics"},{"location":"Pytorch-Lightning/LightningModule/#return_6","text":"Dict Example def update_tng_log_metrics(self, logs): # modify or add to logs return logs","title":"Return"},{"location":"Pytorch-Lightning/LightningModule/#add_model_specific_args","text":"@staticmethod def add_model_specific_args(parent_parser, root_dir) Lightning has a list of default argparse commands. This method is your chance to add or modify commands specific to your model. The argument parser is available anywhere in your model by calling self.hparams","title":"add_model_specific_args"},{"location":"Pytorch-Lightning/LightningModule/#return_7","text":"An argument parser Example @staticmethod def add_model_specific_args(parent_parser, root_dir): parser = HyperOptArgumentParser(strategy=parent_parser.strategy, parents=[parent_parser]) # param overwrites # parser.set_defaults(gradient_clip=5.0) # network params parser.opt_list('--drop_prob', default=0.2, options=[0.2, 0.5], type=float, tunable=False) parser.add_argument('--in_features', default=28*28) parser.add_argument('--out_features', default=10) parser.add_argument('--hidden_dim', default=50000) # use 500 for CPU, 50000 for GPU to see speed difference # data parser.add_argument('--data_root', default=os.path.join(root_dir, 'mnist'), type=str) # training params (opt) parser.opt_list('--learning_rate', default=0.001, type=float, options=[0.0001, 0.0005, 0.001, 0.005], tunable=False) parser.opt_list('--batch_size', default=256, type=int, options=[32, 64, 128, 256], tunable=False) parser.opt_list('--optimizer_name', default='adam', type=str, options=['adam'], tunable=False) return parser","title":"Return"},{"location":"Trainer/","text":"Trainer [ Github Code ] The lightning trainer abstracts best practices for running a training, val, test routine. It calls parts of your model when it wants to hand over full control and otherwise makes training assumptions which are now standard practice in AI research. This is the basic use of the trainer: from pytorch_lightning import Trainer model = LightningTemplate() trainer = Trainer() trainer.fit(model) But of course the fun is in all the advanced things it can do: Checkpointing Model saving Model loading Computing cluster (SLURM) Automatic checkpointing Automatic saving, loading Running grid search on a cluster Walltime auto-resubmit Debugging Fast dev run Inspect gradient norms Log GPU usage Make model overfit on subset of data Print the parameter count by layer Pring which gradients are nan Distributed training 16-bit mixed precision Multi-GPU Multi-node Single GPU Self-balancing architecture Experiment Logging Display metrics in progress bar Log arbitrary metrics Log metric row every k batches Process position Save a snapshot of all hyperparameters Snapshot code for a training run Write logs file to csv every k batches Training loop Accumulate gradients Anneal Learning rate Force training for min or max epochs Force disable early stop Use multiple optimizers (like GANs) Set how much of the training set to check (1-100%) Validation loop Check validation every n epochs Set how much of the validation set to check Set how much of the test set to check Set validation check frequency within 1 training epoch Set the number of validation sanity steps","title":"Trainer"},{"location":"Trainer/#trainer","text":"[ Github Code ] The lightning trainer abstracts best practices for running a training, val, test routine. It calls parts of your model when it wants to hand over full control and otherwise makes training assumptions which are now standard practice in AI research. This is the basic use of the trainer: from pytorch_lightning import Trainer model = LightningTemplate() trainer = Trainer() trainer.fit(model) But of course the fun is in all the advanced things it can do: Checkpointing Model saving Model loading Computing cluster (SLURM) Automatic checkpointing Automatic saving, loading Running grid search on a cluster Walltime auto-resubmit Debugging Fast dev run Inspect gradient norms Log GPU usage Make model overfit on subset of data Print the parameter count by layer Pring which gradients are nan Distributed training 16-bit mixed precision Multi-GPU Multi-node Single GPU Self-balancing architecture Experiment Logging Display metrics in progress bar Log arbitrary metrics Log metric row every k batches Process position Save a snapshot of all hyperparameters Snapshot code for a training run Write logs file to csv every k batches Training loop Accumulate gradients Anneal Learning rate Force training for min or max epochs Force disable early stop Use multiple optimizers (like GANs) Set how much of the training set to check (1-100%) Validation loop Check validation every n epochs Set how much of the validation set to check Set how much of the test set to check Set validation check frequency within 1 training epoch Set the number of validation sanity steps","title":"Trainer"},{"location":"Trainer/Checkpointing/","text":"","title":"Checkpointing"},{"location":"Trainer/Distributed training/","text":"Lightning makes multi-gpu training and 16 bit training trivial. Note: None of the flags below require changing anything about your lightningModel definition. 16-bit mixed precision 16 bit precision can cut your memory footprint by half. If using volta architecture GPUs it can give a dramatic training speed-up as well. First, install apex (if install fails, look here ): $ git clone https://github.com/NVIDIA/apex $ cd apex $ pip install -v --no-cache-dir --global-option=\"--cpp_ext\" --global-option=\"--cuda_ext\" ./ then set this use_amp to True. # DEFAULT trainer = Trainer(amp_level='O2', use_amp=False) Single-gpu Make sure you're on a GPU machine. # set these flags os.environ[\"CUDA_DEVICE_ORDER\"] = \"PCI_BUS_ID\" os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\" # DEFAULT trainer = Trainer(gpus=[0]) multi-gpu Make sure you're on a GPU machine. You can set as many GPUs as you want. In this setting, the model will run on all 8 GPUs at once using DataParallel under the hood. # set these flags os.environ[\"CUDA_DEVICE_ORDER\"] = \"PCI_BUS_ID\" os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0,1,2,3,4,5,6,7\" # DEFAULT trainer = Trainer(gpus=[0,1,2,3,4,5,6,7]) Multi-node COMING SOON. Self-balancing architecture Here lightning distributes parts of your module across available GPUs to optimize for speed and memory. COMING SOON.","title":"Distributed training"},{"location":"Trainer/Distributed training/#16-bit-mixed-precision","text":"16 bit precision can cut your memory footprint by half. If using volta architecture GPUs it can give a dramatic training speed-up as well. First, install apex (if install fails, look here ): $ git clone https://github.com/NVIDIA/apex $ cd apex $ pip install -v --no-cache-dir --global-option=\"--cpp_ext\" --global-option=\"--cuda_ext\" ./ then set this use_amp to True. # DEFAULT trainer = Trainer(amp_level='O2', use_amp=False)","title":"16-bit mixed precision"},{"location":"Trainer/Distributed training/#single-gpu","text":"Make sure you're on a GPU machine. # set these flags os.environ[\"CUDA_DEVICE_ORDER\"] = \"PCI_BUS_ID\" os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\" # DEFAULT trainer = Trainer(gpus=[0])","title":"Single-gpu"},{"location":"Trainer/Distributed training/#multi-gpu","text":"Make sure you're on a GPU machine. You can set as many GPUs as you want. In this setting, the model will run on all 8 GPUs at once using DataParallel under the hood. # set these flags os.environ[\"CUDA_DEVICE_ORDER\"] = \"PCI_BUS_ID\" os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0,1,2,3,4,5,6,7\" # DEFAULT trainer = Trainer(gpus=[0,1,2,3,4,5,6,7])","title":"multi-gpu"},{"location":"Trainer/Distributed training/#multi-node","text":"COMING SOON.","title":"Multi-node"},{"location":"Trainer/Distributed training/#self-balancing-architecture","text":"Here lightning distributes parts of your module across available GPUs to optimize for speed and memory. COMING SOON.","title":"Self-balancing architecture"},{"location":"Trainer/Logging/","text":"Lighting offers a few options for logging information about model, gpu usage, etc (via test-tube). It also offers printing options for training monitoring. Display metrics in progress bar # DEFAULT trainer = Trainer(progress_bar=True) Log metric row every k batches Every k batches lightning will make an entry in the metrics log # DEFAULT (ie: save a .csv log file every 10 batches) trainer = Trainer(add_log_row_interval=10) Process position When running multiple models on the same machine we want to decide which progress bar to use. Lightning will stack progress bars according to this value. # DEFAULT trainer = Trainer(process_position=0) # if this is the second model on the node, show the second progress bar below trainer = Trainer(process_position=1) Save a snapshot of all hyperparameters Whenever you call .save() on the test-tube experiment it logs all the hyperparameters in current use. Give lightning a test-tube Experiment object to automate this for you. from test-tube import Experiment exp = Experiment(...) Trainer(experiment=exp) Snapshot code for a training run Whenever you call .save() on the test-tube experiment it snapshows all code and pushes to a git tag. Give lightning a test-tube Experiment object to automate this for you. from test-tube import Experiment exp = Experiment(create_git_tag=True) Trainer(experiment=exp) Write logs file to csv every k batches Every k batches, lightning will write the new logs to disk # DEFAULT (ie: save a .csv log file every 100 batches) trainer = Trainer(log_save_interval=100)","title":"Logging"},{"location":"Trainer/Logging/#display-metrics-in-progress-bar","text":"# DEFAULT trainer = Trainer(progress_bar=True)","title":"Display metrics in progress bar"},{"location":"Trainer/Logging/#log-metric-row-every-k-batches","text":"Every k batches lightning will make an entry in the metrics log # DEFAULT (ie: save a .csv log file every 10 batches) trainer = Trainer(add_log_row_interval=10)","title":"Log metric row every k batches"},{"location":"Trainer/Logging/#process-position","text":"When running multiple models on the same machine we want to decide which progress bar to use. Lightning will stack progress bars according to this value. # DEFAULT trainer = Trainer(process_position=0) # if this is the second model on the node, show the second progress bar below trainer = Trainer(process_position=1)","title":"Process position"},{"location":"Trainer/Logging/#save-a-snapshot-of-all-hyperparameters","text":"Whenever you call .save() on the test-tube experiment it logs all the hyperparameters in current use. Give lightning a test-tube Experiment object to automate this for you. from test-tube import Experiment exp = Experiment(...) Trainer(experiment=exp)","title":"Save a snapshot of all hyperparameters"},{"location":"Trainer/Logging/#snapshot-code-for-a-training-run","text":"Whenever you call .save() on the test-tube experiment it snapshows all code and pushes to a git tag. Give lightning a test-tube Experiment object to automate this for you. from test-tube import Experiment exp = Experiment(create_git_tag=True) Trainer(experiment=exp)","title":"Snapshot code for a training run"},{"location":"Trainer/Logging/#write-logs-file-to-csv-every-k-batches","text":"Every k batches, lightning will write the new logs to disk # DEFAULT (ie: save a .csv log file every 100 batches) trainer = Trainer(log_save_interval=100)","title":"Write logs file to csv every k batches"},{"location":"Trainer/SLURM Managed Cluster/","text":"","title":"SLURM Managed Cluster"},{"location":"Trainer/Training Loop/","text":"The lightning training loop handles everything except the actual computations of your model. To decide what will happen in your training loop, define the training_step function . Below are all the things lightning automates for you in the training loop. Accumulated gradients Accumulated gradients runs K small batches of size N before doing a backwards pass. The effect is a large effective batch size of size KxN. # DEFAULT (ie: no accumulated grads) trainer = Trainer(accumulate_grad_batches=1) Anneal Learning rate Cut the learning rate by 10 at every epoch listed in this list. # DEFAULT (don't anneal) trainer = Trainer(lr_scheduler_milestones=None) # cut LR by 10 at 100, 200, and 300 epochs trainer = Trainer(lr_scheduler_milestones=[100, 200, 300]) Force training for min or max epochs It can be useful to force training for a minimum number of epochs or limit to a max number # DEFAULT trainer = Trainer(min_nb_epochs=1, max_nb_epochs=1000) Force disable early stop Use this to turn off early stopping and run training to the max_epoch # DEFAULT trainer = Trainer(enable_early_stop=True) Inspect gradient norms Looking at grad norms can help you figure out where training might be going wrong. # DEFAULT (-1 doesn't track norms) trainer = Trainer(track_grad_norm=-1) # track the LP norm (P=2 here) trainer = Trainer(track_grad_norm=2) Set how much of the training set to check If you don't want to check 100% of the training set (for debugging or if it's huge), set this flag # DEFAULT trainer = Trainer(train_percent_check=1.0) # check 10% only trainer = Trainer(train_percent_check=0.1)","title":"Training Loop"},{"location":"Trainer/Training Loop/#accumulated-gradients","text":"Accumulated gradients runs K small batches of size N before doing a backwards pass. The effect is a large effective batch size of size KxN. # DEFAULT (ie: no accumulated grads) trainer = Trainer(accumulate_grad_batches=1)","title":"Accumulated gradients"},{"location":"Trainer/Training Loop/#anneal-learning-rate","text":"Cut the learning rate by 10 at every epoch listed in this list. # DEFAULT (don't anneal) trainer = Trainer(lr_scheduler_milestones=None) # cut LR by 10 at 100, 200, and 300 epochs trainer = Trainer(lr_scheduler_milestones=[100, 200, 300])","title":"Anneal Learning rate"},{"location":"Trainer/Training Loop/#force-training-for-min-or-max-epochs","text":"It can be useful to force training for a minimum number of epochs or limit to a max number # DEFAULT trainer = Trainer(min_nb_epochs=1, max_nb_epochs=1000)","title":"Force training for min or max epochs"},{"location":"Trainer/Training Loop/#force-disable-early-stop","text":"Use this to turn off early stopping and run training to the max_epoch # DEFAULT trainer = Trainer(enable_early_stop=True)","title":"Force disable early stop"},{"location":"Trainer/Training Loop/#inspect-gradient-norms","text":"Looking at grad norms can help you figure out where training might be going wrong. # DEFAULT (-1 doesn't track norms) trainer = Trainer(track_grad_norm=-1) # track the LP norm (P=2 here) trainer = Trainer(track_grad_norm=2)","title":"Inspect gradient norms"},{"location":"Trainer/Training Loop/#set-how-much-of-the-training-set-to-check","text":"If you don't want to check 100% of the training set (for debugging or if it's huge), set this flag # DEFAULT trainer = Trainer(train_percent_check=1.0) # check 10% only trainer = Trainer(train_percent_check=0.1)","title":"Set how much of the training set to check"},{"location":"Trainer/Validation loop/","text":"The lightning validation loop handles everything except the actual computations of your model. To decide what will happen in your validation loop, define the validation_step function . Below are all the things lightning automates for you in the validation loop. Note Lightning will run 5 steps of validation in the beginning of training as a sanity check so you don't have to wait until a full epoch to catch possible validation issues. Check validation every n epochs If you have a small dataset you might want to check validation every n epochs # DEFAULT trainer = Trainer(check_val_every_n_epoch=1) Set how much of the validation set to check If you don't want to check 100% of the validation set (for debugging or if it's huge), set this flag # DEFAULT trainer = Trainer(val_percent_check=1.0) # check 10% only trainer = Trainer(val_percent_check=0.1) Set how much of the test set to check If you don't want to check 100% of the test set (for debugging or if it's huge), set this flag # DEFAULT trainer = Trainer(test_percent_check=1.0) # check 10% only trainer = Trainer(test_percent_check=0.1) Set validation check frequency within 1 training epoch For large datasets it's often desirable to check validation multiple times within a training loop # DEFAULT trainer = Trainer(val_check_interval=0.95) # check every .25 of an epoch trainer = Trainer(val_check_interval=0.25) Set the number of validation sanity steps Lightning runs a few steps of validation in the beginning of training. This avoids crashing in the validation loop sometime deep into a lengthy training loop. # DEFAULT trainer = Trainer(nb_sanity_val_steps=5)","title":"Validation loop"},{"location":"Trainer/Validation loop/#check-validation-every-n-epochs","text":"If you have a small dataset you might want to check validation every n epochs # DEFAULT trainer = Trainer(check_val_every_n_epoch=1)","title":"Check validation every n epochs"},{"location":"Trainer/Validation loop/#set-how-much-of-the-validation-set-to-check","text":"If you don't want to check 100% of the validation set (for debugging or if it's huge), set this flag # DEFAULT trainer = Trainer(val_percent_check=1.0) # check 10% only trainer = Trainer(val_percent_check=0.1)","title":"Set how much of the validation set to check"},{"location":"Trainer/Validation loop/#set-how-much-of-the-test-set-to-check","text":"If you don't want to check 100% of the test set (for debugging or if it's huge), set this flag # DEFAULT trainer = Trainer(test_percent_check=1.0) # check 10% only trainer = Trainer(test_percent_check=0.1)","title":"Set how much of the test set to check"},{"location":"Trainer/Validation loop/#set-validation-check-frequency-within-1-training-epoch","text":"For large datasets it's often desirable to check validation multiple times within a training loop # DEFAULT trainer = Trainer(val_check_interval=0.95) # check every .25 of an epoch trainer = Trainer(val_check_interval=0.25)","title":"Set validation check frequency within 1 training epoch"},{"location":"Trainer/Validation loop/#set-the-number-of-validation-sanity-steps","text":"Lightning runs a few steps of validation in the beginning of training. This avoids crashing in the validation loop sometime deep into a lengthy training loop. # DEFAULT trainer = Trainer(nb_sanity_val_steps=5)","title":"Set the number of validation sanity steps"},{"location":"Trainer/debugging/","text":"These flags are useful to help debug a model. Fast dev run This flag is meant for debugging a full train/val/test loop. It'll activate callbacks, everything but only with 1 training and 1 validation batch. Use this to debug a full run of your program quickly # DEFAULT trainer = Trainer(fast_dev_run=False) Inspect gradient norms Looking at grad norms can help you figure out where training might be going wrong. # DEFAULT (-1 doesn't track norms) trainer = Trainer(track_grad_norm=-1) # track the LP norm (P=2 here) trainer = Trainer(track_grad_norm=2) Make model overfit on subset of data A useful debugging trick is to make your model overfit a tiny fraction of the data. # DEFAULT don't overfit (ie: normal training) trainer = Trainer(overfit_pct=0.0) # overfit on 1% of data trainer = Trainer(overfit_pct=0.01) Print the parameter count by layer By default lightning prints a list of parameters and submodules when it starts training. Print which gradients are nan This option prints a list of tensors with nan gradients. # DEFAULT trainer = Trainer(print_nan_grads=False) Log GPU usage Lightning automatically logs gpu usage to the test tube logs. It'll only do it at the metric logging interval, so it doesn't slow down training.","title":"Debugging"},{"location":"Trainer/debugging/#fast-dev-run","text":"This flag is meant for debugging a full train/val/test loop. It'll activate callbacks, everything but only with 1 training and 1 validation batch. Use this to debug a full run of your program quickly # DEFAULT trainer = Trainer(fast_dev_run=False)","title":"Fast dev run"},{"location":"Trainer/debugging/#inspect-gradient-norms","text":"Looking at grad norms can help you figure out where training might be going wrong. # DEFAULT (-1 doesn't track norms) trainer = Trainer(track_grad_norm=-1) # track the LP norm (P=2 here) trainer = Trainer(track_grad_norm=2)","title":"Inspect gradient norms"},{"location":"Trainer/debugging/#make-model-overfit-on-subset-of-data","text":"A useful debugging trick is to make your model overfit a tiny fraction of the data. # DEFAULT don't overfit (ie: normal training) trainer = Trainer(overfit_pct=0.0) # overfit on 1% of data trainer = Trainer(overfit_pct=0.01)","title":"Make model overfit on subset of data"},{"location":"Trainer/debugging/#print-the-parameter-count-by-layer","text":"By default lightning prints a list of parameters and submodules when it starts training.","title":"Print the parameter count by layer"},{"location":"Trainer/debugging/#print-which-gradients-are-nan","text":"This option prints a list of tensors with nan gradients. # DEFAULT trainer = Trainer(print_nan_grads=False)","title":"Print which gradients are nan"},{"location":"Trainer/debugging/#log-gpu-usage","text":"Lightning automatically logs gpu usage to the test tube logs. It'll only do it at the metric logging interval, so it doesn't slow down training.","title":"Log GPU usage"},{"location":"Trainer/hooks/","text":"","title":"Hooks"}]}
\ No newline at end of file
+{"config":{"lang":["en"],"prebuild_index":false,"separator":"[\\s\\-]+"},"docs":[{"location":"","text":"PYTORCH-LIGHTNING DOCUMENTATION Main Docs LightningModule Trainer New project Quick Start Define a LightningModule Pick a trainer Basic CPU Trainer GPU cluster Trainer Quick start examples CPU example Single GPU example Multi-gpu example SLURM cluster grid search example Training loop Accumulate gradients Check GPU usage Check which gradients are nan Check validation every n epochs Display metrics in progress bar Force training for min or max epochs Inspect gradient norms Hooks Learning rate annealing Make model overfit on subset of data Multiple optimizers (like GANs) Set how much of the training set to check (1-100%) training_step function Validation loop Display metrics in progress bar hooks Set how much of the validation set to check (1-100%) Set validation check frequency within 1 training epoch (1-100%) validation_step function Why does validation run first for 5 steps? Distributed training Single-gpu Multi-gpu Multi-node 16-bit mixed precision Checkpointing Model saving Model loading Computing cluster (SLURM) Automatic checkpointing Automatic saving, loading Running grid search on a cluster Walltime auto-resubmit","title":"PYTORCH-LIGHTNING DOCUMENTATION"},{"location":"#pytorch-lightning-documentation","text":"","title":"PYTORCH-LIGHTNING DOCUMENTATION"},{"location":"#main-docs","text":"LightningModule Trainer","title":"Main Docs"},{"location":"#new-project-quick-start","text":"Define a LightningModule Pick a trainer Basic CPU Trainer GPU cluster Trainer","title":"New project Quick Start"},{"location":"#quick-start-examples","text":"CPU example Single GPU example Multi-gpu example SLURM cluster grid search example","title":"Quick start examples"},{"location":"#training-loop","text":"Accumulate gradients Check GPU usage Check which gradients are nan Check validation every n epochs Display metrics in progress bar Force training for min or max epochs Inspect gradient norms Hooks Learning rate annealing Make model overfit on subset of data Multiple optimizers (like GANs) Set how much of the training set to check (1-100%) training_step function","title":"Training loop"},{"location":"#validation-loop","text":"Display metrics in progress bar hooks Set how much of the validation set to check (1-100%) Set validation check frequency within 1 training epoch (1-100%) validation_step function Why does validation run first for 5 steps?","title":"Validation loop"},{"location":"#distributed-training","text":"Single-gpu Multi-gpu Multi-node 16-bit mixed precision","title":"Distributed training"},{"location":"#checkpointing","text":"Model saving Model loading","title":"Checkpointing"},{"location":"#computing-cluster-slurm","text":"Automatic checkpointing Automatic saving, loading Running grid search on a cluster Walltime auto-resubmit","title":"Computing cluster (SLURM)"},{"location":"Pytorch-Lightning/LightningModule/","text":"Lightning module [ Github Code ] A lightning module is a strict superclass of nn.Module, it provides a standard interface for the trainer to interact with the model. The easiest thing to do is copy this template and modify accordingly. Otherwise, to Define a Lightning Module, implement the following methods: Required : training_step validation_step validation_end configure_optimizers get_save_dict load_model_specific tng_dataloader tng_dataloader test_dataloader Optional : update_tng_log_metrics add_model_specific_args training_ste**p def training_step(self, data_batch, batch_nb) In this step you'd normally do the forward pass and calculate the loss for a batch. You can also do fancier things like multiple forward passes or something specific to your model. Params Param description data_batch The output of your dataloader. A tensor, tuple or list batch_nb Integer displaying which batch this is Return Dictionary or OrderedDict key value is required loss tensor scalar Y prog Dict for progress bar display. Must have only tensors N Example def training_step(self, data_batch, batch_nb): x, y, z = data_batch # implement your own out = self.forward(x) loss = self.loss(out, x) output = { 'loss': loss, # required 'prog': {'tng_loss': loss, 'batch_nb': batch_nb} # optional } # return a dict return output validation_step def validation_step(self, data_batch, batch_nb) In this step you'd normally do the forward pass and calculate the loss for a batch. You can also do fancier things like multiple forward passes or something specific to your model. This is most likely the same as your training_step. But unlike training step, the outputs from here will go to validation_end for collation. Params Param description data_batch The output of your dataloader. A tensor, tuple or list batch_nb Integer displaying which batch this is Return Return description optional dict Dict of OrderedDict with metrics to display in progress bar. All keys must be tensors. Y Example def validation_step(self, data_batch, batch_nb): x, y, z = data_batch # implement your own out = self.forward(x) loss = self.loss(out, x) # calculate acc labels_hat = torch.argmax(out, dim=1) val_acc = torch.sum(y == labels_hat).item() / (len(y) * 1.0) # all optional... # return whatever you need for the collation function validation_end output = OrderedDict({ 'val_loss': loss_val, 'val_acc': torch.tensor(val_acc), # everything must be a tensor }) # return an optional dict return output validation_end def validation_end(self, outputs) Called at the end of the validation loop with the output of each validation_step. Params Param description outputs List of outputs you defined in validation_step Return Return description optional dict Dict of OrderedDict with metrics to display in progress bar Y Example 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: \"\"\" val_loss_mean = 0 val_acc_mean = 0 for output in outputs: val_loss_mean += output['val_loss'] val_acc_mean += output['val_acc'] val_loss_mean /= len(outputs) val_acc_mean /= len(outputs) tqdm_dic = {'val_loss': val_loss_mean.item(), 'val_acc': val_acc_mean.item()} return tqdm_dic configure_optimizers def configure_optimizers(self) Set up as many optimizers as you need. Normally you'd need one. But in the case of GANs or something more esoteric you might have multiple. Lightning will call .backward() and .step() on each one. If you use 16 bit precision it will also handle that. Return List - List of optimizers Example # most cases def configure_optimizers(self): opt = Adam(lr=0.01) return [opt] # gan example def configure_optimizers(self): generator_opt = Adam(lr=0.01) disriminator_opt = Adam(lr=0.02) return [generator_opt, disriminator_opt] get_save_dict def get_save_dict(self) Called by lightning to checkpoint your model. Lightning saves current epoch, current batch nb, etc... All you have to return is what specifically about your lightning model you want to checkpoint. Return Dictionary - No required keys. Most of the time as described in this example. Example def get_save_dict(self): # 99% of use cases this is all you need to return checkpoint = {'state_dict': self.state_dict()} return checkpoint load_model_specific def load_model_specific(self, checkpoint) Called by lightning to restore your model. This is your chance to restore your model using the keys you added in get_save_dict. Lightning will automatically restore current epoch, batch nb, etc. Return Nothing Example def load_model_specific(self, checkpoint): # you defined 'state_dict' in get_save_dict() self.load_state_dict(checkpoint['state_dict']) tng_dataloader @property def tng_dataloader(self) Called by lightning during training loop. Define it as a property. Return Pytorch DataLoader Example @property def tng_dataloader(self): if self._tng_dataloader is None: try: transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))]) dataset = MNIST(root='/path/to/mnist/', train=True, transform=transform, download=True) loader = torch.utils.data.DataLoader( dataset=dataset, batch_size=self.hparams.batch_size, shuffle=True ) self._tng_dataloader = loader except Exception as e: raise e return self._tng_dataloader val_dataloader @property def tng_dataloader(self) Called by lightning during validation loop. Define it as a property. Return Pytorch DataLoader Example @property def val_dataloader(self): if self._val_dataloader is None: try: transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))]) dataset = MNIST(root='/path/to/mnist/', train=False, transform=transform, download=True) loader = torch.utils.data.DataLoader( dataset=dataset, batch_size=self.hparams.batch_size, shuffle=True ) self._val_dataloader = loader except Exception as e: raise e return self._val_dataloader test_dataloader @property def test_dataloader(self) Called by lightning during test loop. Define it as a property. Return Pytorch DataLoader Example @property def test_dataloader(self): if self._test_dataloader is None: try: transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))]) dataset = MNIST(root='/path/to/mnist/', train=False, transform=transform, download=True) loader = torch.utils.data.DataLoader( dataset=dataset, batch_size=self.hparams.batch_size, shuffle=True ) self._test_dataloader = loader except Exception as e: raise e return self._test_dataloader update_tng_log_metrics def update_tng_log_metrics(self, logs) Called by lightning right before it logs metrics for this batch. This is a chance to ammend or add to the metrics about to be logged. Return Dict Example def update_tng_log_metrics(self, logs): # modify or add to logs return logs add_model_specific_args @staticmethod def add_model_specific_args(parent_parser, root_dir) Lightning has a list of default argparse commands. This method is your chance to add or modify commands specific to your model. The argument parser is available anywhere in your model by calling self.hparams Return An argument parser Example @staticmethod def add_model_specific_args(parent_parser, root_dir): parser = HyperOptArgumentParser(strategy=parent_parser.strategy, parents=[parent_parser]) # param overwrites # parser.set_defaults(gradient_clip=5.0) # network params parser.opt_list('--drop_prob', default=0.2, options=[0.2, 0.5], type=float, tunable=False) parser.add_argument('--in_features', default=28*28) parser.add_argument('--out_features', default=10) parser.add_argument('--hidden_dim', default=50000) # use 500 for CPU, 50000 for GPU to see speed difference # data parser.add_argument('--data_root', default=os.path.join(root_dir, 'mnist'), type=str) # training params (opt) parser.opt_list('--learning_rate', default=0.001, type=float, options=[0.0001, 0.0005, 0.001, 0.005], tunable=False) parser.opt_list('--batch_size', default=256, type=int, options=[32, 64, 128, 256], tunable=False) parser.opt_list('--optimizer_name', default='adam', type=str, options=['adam'], tunable=False) return parser","title":"Lightning module"},{"location":"Pytorch-Lightning/LightningModule/#lightning-module","text":"[ Github Code ] A lightning module is a strict superclass of nn.Module, it provides a standard interface for the trainer to interact with the model. The easiest thing to do is copy this template and modify accordingly. Otherwise, to Define a Lightning Module, implement the following methods: Required : training_step validation_step validation_end configure_optimizers get_save_dict load_model_specific tng_dataloader tng_dataloader test_dataloader Optional : update_tng_log_metrics add_model_specific_args","title":"Lightning module"},{"location":"Pytorch-Lightning/LightningModule/#training_step","text":"def training_step(self, data_batch, batch_nb) In this step you'd normally do the forward pass and calculate the loss for a batch. You can also do fancier things like multiple forward passes or something specific to your model. Params Param description data_batch The output of your dataloader. A tensor, tuple or list batch_nb Integer displaying which batch this is Return Dictionary or OrderedDict key value is required loss tensor scalar Y prog Dict for progress bar display. Must have only tensors N Example def training_step(self, data_batch, batch_nb): x, y, z = data_batch # implement your own out = self.forward(x) loss = self.loss(out, x) output = { 'loss': loss, # required 'prog': {'tng_loss': loss, 'batch_nb': batch_nb} # optional } # return a dict return output","title":"training_ste**p"},{"location":"Pytorch-Lightning/LightningModule/#validation_step","text":"def validation_step(self, data_batch, batch_nb) In this step you'd normally do the forward pass and calculate the loss for a batch. You can also do fancier things like multiple forward passes or something specific to your model. This is most likely the same as your training_step. But unlike training step, the outputs from here will go to validation_end for collation. Params Param description data_batch The output of your dataloader. A tensor, tuple or list batch_nb Integer displaying which batch this is Return Return description optional dict Dict of OrderedDict with metrics to display in progress bar. All keys must be tensors. Y Example def validation_step(self, data_batch, batch_nb): x, y, z = data_batch # implement your own out = self.forward(x) loss = self.loss(out, x) # calculate acc labels_hat = torch.argmax(out, dim=1) val_acc = torch.sum(y == labels_hat).item() / (len(y) * 1.0) # all optional... # return whatever you need for the collation function validation_end output = OrderedDict({ 'val_loss': loss_val, 'val_acc': torch.tensor(val_acc), # everything must be a tensor }) # return an optional dict return output","title":"validation_step"},{"location":"Pytorch-Lightning/LightningModule/#validation_end","text":"def validation_end(self, outputs) Called at the end of the validation loop with the output of each validation_step. Params Param description outputs List of outputs you defined in validation_step Return Return description optional dict Dict of OrderedDict with metrics to display in progress bar Y Example 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: \"\"\" val_loss_mean = 0 val_acc_mean = 0 for output in outputs: val_loss_mean += output['val_loss'] val_acc_mean += output['val_acc'] val_loss_mean /= len(outputs) val_acc_mean /= len(outputs) tqdm_dic = {'val_loss': val_loss_mean.item(), 'val_acc': val_acc_mean.item()} return tqdm_dic","title":"validation_end"},{"location":"Pytorch-Lightning/LightningModule/#configure_optimizers","text":"def configure_optimizers(self) Set up as many optimizers as you need. Normally you'd need one. But in the case of GANs or something more esoteric you might have multiple. Lightning will call .backward() and .step() on each one. If you use 16 bit precision it will also handle that.","title":"configure_optimizers"},{"location":"Pytorch-Lightning/LightningModule/#return","text":"List - List of optimizers Example # most cases def configure_optimizers(self): opt = Adam(lr=0.01) return [opt] # gan example def configure_optimizers(self): generator_opt = Adam(lr=0.01) disriminator_opt = Adam(lr=0.02) return [generator_opt, disriminator_opt]","title":"Return"},{"location":"Pytorch-Lightning/LightningModule/#get_save_dict","text":"def get_save_dict(self) Called by lightning to checkpoint your model. Lightning saves current epoch, current batch nb, etc... All you have to return is what specifically about your lightning model you want to checkpoint.","title":"get_save_dict"},{"location":"Pytorch-Lightning/LightningModule/#return_1","text":"Dictionary - No required keys. Most of the time as described in this example. Example def get_save_dict(self): # 99% of use cases this is all you need to return checkpoint = {'state_dict': self.state_dict()} return checkpoint","title":"Return"},{"location":"Pytorch-Lightning/LightningModule/#load_model_specific","text":"def load_model_specific(self, checkpoint) Called by lightning to restore your model. This is your chance to restore your model using the keys you added in get_save_dict. Lightning will automatically restore current epoch, batch nb, etc.","title":"load_model_specific"},{"location":"Pytorch-Lightning/LightningModule/#return_2","text":"Nothing Example def load_model_specific(self, checkpoint): # you defined 'state_dict' in get_save_dict() self.load_state_dict(checkpoint['state_dict'])","title":"Return"},{"location":"Pytorch-Lightning/LightningModule/#tng_dataloader","text":"@property def tng_dataloader(self) Called by lightning during training loop. Define it as a property.","title":"tng_dataloader"},{"location":"Pytorch-Lightning/LightningModule/#return_3","text":"Pytorch DataLoader Example @property def tng_dataloader(self): if self._tng_dataloader is None: try: transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))]) dataset = MNIST(root='/path/to/mnist/', train=True, transform=transform, download=True) loader = torch.utils.data.DataLoader( dataset=dataset, batch_size=self.hparams.batch_size, shuffle=True ) self._tng_dataloader = loader except Exception as e: raise e return self._tng_dataloader","title":"Return"},{"location":"Pytorch-Lightning/LightningModule/#val_dataloader","text":"@property def tng_dataloader(self) Called by lightning during validation loop. Define it as a property.","title":"val_dataloader"},{"location":"Pytorch-Lightning/LightningModule/#return_4","text":"Pytorch DataLoader Example @property def val_dataloader(self): if self._val_dataloader is None: try: transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))]) dataset = MNIST(root='/path/to/mnist/', train=False, transform=transform, download=True) loader = torch.utils.data.DataLoader( dataset=dataset, batch_size=self.hparams.batch_size, shuffle=True ) self._val_dataloader = loader except Exception as e: raise e return self._val_dataloader","title":"Return"},{"location":"Pytorch-Lightning/LightningModule/#test_dataloader","text":"@property def test_dataloader(self) Called by lightning during test loop. Define it as a property.","title":"test_dataloader"},{"location":"Pytorch-Lightning/LightningModule/#return_5","text":"Pytorch DataLoader Example @property def test_dataloader(self): if self._test_dataloader is None: try: transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))]) dataset = MNIST(root='/path/to/mnist/', train=False, transform=transform, download=True) loader = torch.utils.data.DataLoader( dataset=dataset, batch_size=self.hparams.batch_size, shuffle=True ) self._test_dataloader = loader except Exception as e: raise e return self._test_dataloader","title":"Return"},{"location":"Pytorch-Lightning/LightningModule/#update_tng_log_metrics","text":"def update_tng_log_metrics(self, logs) Called by lightning right before it logs metrics for this batch. This is a chance to ammend or add to the metrics about to be logged.","title":"update_tng_log_metrics"},{"location":"Pytorch-Lightning/LightningModule/#return_6","text":"Dict Example def update_tng_log_metrics(self, logs): # modify or add to logs return logs","title":"Return"},{"location":"Pytorch-Lightning/LightningModule/#add_model_specific_args","text":"@staticmethod def add_model_specific_args(parent_parser, root_dir) Lightning has a list of default argparse commands. This method is your chance to add or modify commands specific to your model. The argument parser is available anywhere in your model by calling self.hparams","title":"add_model_specific_args"},{"location":"Pytorch-Lightning/LightningModule/#return_7","text":"An argument parser Example @staticmethod def add_model_specific_args(parent_parser, root_dir): parser = HyperOptArgumentParser(strategy=parent_parser.strategy, parents=[parent_parser]) # param overwrites # parser.set_defaults(gradient_clip=5.0) # network params parser.opt_list('--drop_prob', default=0.2, options=[0.2, 0.5], type=float, tunable=False) parser.add_argument('--in_features', default=28*28) parser.add_argument('--out_features', default=10) parser.add_argument('--hidden_dim', default=50000) # use 500 for CPU, 50000 for GPU to see speed difference # data parser.add_argument('--data_root', default=os.path.join(root_dir, 'mnist'), type=str) # training params (opt) parser.opt_list('--learning_rate', default=0.001, type=float, options=[0.0001, 0.0005, 0.001, 0.005], tunable=False) parser.opt_list('--batch_size', default=256, type=int, options=[32, 64, 128, 256], tunable=False) parser.opt_list('--optimizer_name', default='adam', type=str, options=['adam'], tunable=False) return parser","title":"Return"},{"location":"Trainer/","text":"Trainer [ Github Code ] The lightning trainer abstracts best practices for running a training, val, test routine. It calls parts of your model when it wants to hand over full control and otherwise makes training assumptions which are now standard practice in AI research. This is the basic use of the trainer: from pytorch_lightning import Trainer model = LightningTemplate() trainer = Trainer() trainer.fit(model) But of course the fun is in all the advanced things it can do: Checkpointing Model saving Model loading Computing cluster (SLURM) Automatic checkpointing Automatic saving, loading Running grid search on a cluster Walltime auto-resubmit Debugging Fast dev run Inspect gradient norms Log GPU usage Make model overfit on subset of data Print the parameter count by layer Pring which gradients are nan Distributed training 16-bit mixed precision Multi-GPU Multi-node Single GPU Self-balancing architecture Experiment Logging Display metrics in progress bar Log arbitrary metrics Log metric row every k batches Process position Save a snapshot of all hyperparameters Snapshot code for a training run Write logs file to csv every k batches Training loop Accumulate gradients Anneal Learning rate Force training for min or max epochs Force disable early stop Use multiple optimizers (like GANs) Set how much of the training set to check (1-100%) Validation loop Check validation every n epochs Set how much of the validation set to check Set how much of the test set to check Set validation check frequency within 1 training epoch Set the number of validation sanity steps","title":"Trainer"},{"location":"Trainer/#trainer","text":"[ Github Code ] The lightning trainer abstracts best practices for running a training, val, test routine. It calls parts of your model when it wants to hand over full control and otherwise makes training assumptions which are now standard practice in AI research. This is the basic use of the trainer: from pytorch_lightning import Trainer model = LightningTemplate() trainer = Trainer() trainer.fit(model) But of course the fun is in all the advanced things it can do: Checkpointing Model saving Model loading Computing cluster (SLURM) Automatic checkpointing Automatic saving, loading Running grid search on a cluster Walltime auto-resubmit Debugging Fast dev run Inspect gradient norms Log GPU usage Make model overfit on subset of data Print the parameter count by layer Pring which gradients are nan Distributed training 16-bit mixed precision Multi-GPU Multi-node Single GPU Self-balancing architecture Experiment Logging Display metrics in progress bar Log arbitrary metrics Log metric row every k batches Process position Save a snapshot of all hyperparameters Snapshot code for a training run Write logs file to csv every k batches Training loop Accumulate gradients Anneal Learning rate Force training for min or max epochs Force disable early stop Use multiple optimizers (like GANs) Set how much of the training set to check (1-100%) Validation loop Check validation every n epochs Set how much of the validation set to check Set how much of the test set to check Set validation check frequency within 1 training epoch Set the number of validation sanity steps","title":"Trainer"},{"location":"Trainer/Checkpointing/","text":"","title":"Checkpointing"},{"location":"Trainer/Distributed training/","text":"Lightning makes multi-gpu training and 16 bit training trivial. Note: None of the flags below require changing anything about your lightningModel definition. 16-bit mixed precision 16 bit precision can cut your memory footprint by half. If using volta architecture GPUs it can give a dramatic training speed-up as well. First, install apex (if install fails, look here ): $ git clone https://github.com/NVIDIA/apex $ cd apex $ pip install -v --no-cache-dir --global-option=\"--cpp_ext\" --global-option=\"--cuda_ext\" ./ then set this use_amp to True. # DEFAULT trainer = Trainer(amp_level='O2', use_amp=False) Single-gpu Make sure you're on a GPU machine. # set these flags os.environ[\"CUDA_DEVICE_ORDER\"] = \"PCI_BUS_ID\" os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\" # DEFAULT trainer = Trainer(gpus=[0]) multi-gpu Make sure you're on a GPU machine. You can set as many GPUs as you want. In this setting, the model will run on all 8 GPUs at once using DataParallel under the hood. # set these flags os.environ[\"CUDA_DEVICE_ORDER\"] = \"PCI_BUS_ID\" os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0,1,2,3,4,5,6,7\" # DEFAULT trainer = Trainer(gpus=[0,1,2,3,4,5,6,7]) Multi-node COMING SOON. Self-balancing architecture Here lightning distributes parts of your module across available GPUs to optimize for speed and memory. COMING SOON.","title":"Distributed training"},{"location":"Trainer/Distributed training/#16-bit-mixed-precision","text":"16 bit precision can cut your memory footprint by half. If using volta architecture GPUs it can give a dramatic training speed-up as well. First, install apex (if install fails, look here ): $ git clone https://github.com/NVIDIA/apex $ cd apex $ pip install -v --no-cache-dir --global-option=\"--cpp_ext\" --global-option=\"--cuda_ext\" ./ then set this use_amp to True. # DEFAULT trainer = Trainer(amp_level='O2', use_amp=False)","title":"16-bit mixed precision"},{"location":"Trainer/Distributed training/#single-gpu","text":"Make sure you're on a GPU machine. # set these flags os.environ[\"CUDA_DEVICE_ORDER\"] = \"PCI_BUS_ID\" os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\" # DEFAULT trainer = Trainer(gpus=[0])","title":"Single-gpu"},{"location":"Trainer/Distributed training/#multi-gpu","text":"Make sure you're on a GPU machine. You can set as many GPUs as you want. In this setting, the model will run on all 8 GPUs at once using DataParallel under the hood. # set these flags os.environ[\"CUDA_DEVICE_ORDER\"] = \"PCI_BUS_ID\" os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0,1,2,3,4,5,6,7\" # DEFAULT trainer = Trainer(gpus=[0,1,2,3,4,5,6,7])","title":"multi-gpu"},{"location":"Trainer/Distributed training/#multi-node","text":"COMING SOON.","title":"Multi-node"},{"location":"Trainer/Distributed training/#self-balancing-architecture","text":"Here lightning distributes parts of your module across available GPUs to optimize for speed and memory. COMING SOON.","title":"Self-balancing architecture"},{"location":"Trainer/Logging/","text":"Lighting offers a few options for logging information about model, gpu usage, etc (via test-tube). It also offers printing options for training monitoring. Display metrics in progress bar # DEFAULT trainer = Trainer(progress_bar=True) Log metric row every k batches Every k batches lightning will make an entry in the metrics log # DEFAULT (ie: save a .csv log file every 10 batches) trainer = Trainer(add_log_row_interval=10) Process position When running multiple models on the same machine we want to decide which progress bar to use. Lightning will stack progress bars according to this value. # DEFAULT trainer = Trainer(process_position=0) # if this is the second model on the node, show the second progress bar below trainer = Trainer(process_position=1) Save a snapshot of all hyperparameters Whenever you call .save() on the test-tube experiment it logs all the hyperparameters in current use. Give lightning a test-tube Experiment object to automate this for you. from test-tube import Experiment exp = Experiment(...) Trainer(experiment=exp) Snapshot code for a training run Whenever you call .save() on the test-tube experiment it snapshows all code and pushes to a git tag. Give lightning a test-tube Experiment object to automate this for you. from test-tube import Experiment exp = Experiment(create_git_tag=True) Trainer(experiment=exp) Write logs file to csv every k batches Every k batches, lightning will write the new logs to disk # DEFAULT (ie: save a .csv log file every 100 batches) trainer = Trainer(log_save_interval=100)","title":"Logging"},{"location":"Trainer/Logging/#display-metrics-in-progress-bar","text":"# DEFAULT trainer = Trainer(progress_bar=True)","title":"Display metrics in progress bar"},{"location":"Trainer/Logging/#log-metric-row-every-k-batches","text":"Every k batches lightning will make an entry in the metrics log # DEFAULT (ie: save a .csv log file every 10 batches) trainer = Trainer(add_log_row_interval=10)","title":"Log metric row every k batches"},{"location":"Trainer/Logging/#process-position","text":"When running multiple models on the same machine we want to decide which progress bar to use. Lightning will stack progress bars according to this value. # DEFAULT trainer = Trainer(process_position=0) # if this is the second model on the node, show the second progress bar below trainer = Trainer(process_position=1)","title":"Process position"},{"location":"Trainer/Logging/#save-a-snapshot-of-all-hyperparameters","text":"Whenever you call .save() on the test-tube experiment it logs all the hyperparameters in current use. Give lightning a test-tube Experiment object to automate this for you. from test-tube import Experiment exp = Experiment(...) Trainer(experiment=exp)","title":"Save a snapshot of all hyperparameters"},{"location":"Trainer/Logging/#snapshot-code-for-a-training-run","text":"Whenever you call .save() on the test-tube experiment it snapshows all code and pushes to a git tag. Give lightning a test-tube Experiment object to automate this for you. from test-tube import Experiment exp = Experiment(create_git_tag=True) Trainer(experiment=exp)","title":"Snapshot code for a training run"},{"location":"Trainer/Logging/#write-logs-file-to-csv-every-k-batches","text":"Every k batches, lightning will write the new logs to disk # DEFAULT (ie: save a .csv log file every 100 batches) trainer = Trainer(log_save_interval=100)","title":"Write logs file to csv every k batches"},{"location":"Trainer/SLURM Managed Cluster/","text":"","title":"SLURM Managed Cluster"},{"location":"Trainer/Training Loop/","text":"The lightning training loop handles everything except the actual computations of your model. To decide what will happen in your training loop, define the training_step function . Below are all the things lightning automates for you in the training loop. Accumulated gradients Accumulated gradients runs K small batches of size N before doing a backwards pass. The effect is a large effective batch size of size KxN. # DEFAULT (ie: no accumulated grads) trainer = Trainer(accumulate_grad_batches=1) Anneal Learning rate Cut the learning rate by 10 at every epoch listed in this list. # DEFAULT (don't anneal) trainer = Trainer(lr_scheduler_milestones=None) # cut LR by 10 at 100, 200, and 300 epochs trainer = Trainer(lr_scheduler_milestones=[100, 200, 300]) Force training for min or max epochs It can be useful to force training for a minimum number of epochs or limit to a max number # DEFAULT trainer = Trainer(min_nb_epochs=1, max_nb_epochs=1000) Force disable early stop Use this to turn off early stopping and run training to the max_epoch # DEFAULT trainer = Trainer(enable_early_stop=True) Inspect gradient norms Looking at grad norms can help you figure out where training might be going wrong. # DEFAULT (-1 doesn't track norms) trainer = Trainer(track_grad_norm=-1) # track the LP norm (P=2 here) trainer = Trainer(track_grad_norm=2) Set how much of the training set to check If you don't want to check 100% of the training set (for debugging or if it's huge), set this flag # DEFAULT trainer = Trainer(train_percent_check=1.0) # check 10% only trainer = Trainer(train_percent_check=0.1)","title":"Training Loop"},{"location":"Trainer/Training Loop/#accumulated-gradients","text":"Accumulated gradients runs K small batches of size N before doing a backwards pass. The effect is a large effective batch size of size KxN. # DEFAULT (ie: no accumulated grads) trainer = Trainer(accumulate_grad_batches=1)","title":"Accumulated gradients"},{"location":"Trainer/Training Loop/#anneal-learning-rate","text":"Cut the learning rate by 10 at every epoch listed in this list. # DEFAULT (don't anneal) trainer = Trainer(lr_scheduler_milestones=None) # cut LR by 10 at 100, 200, and 300 epochs trainer = Trainer(lr_scheduler_milestones=[100, 200, 300])","title":"Anneal Learning rate"},{"location":"Trainer/Training Loop/#force-training-for-min-or-max-epochs","text":"It can be useful to force training for a minimum number of epochs or limit to a max number # DEFAULT trainer = Trainer(min_nb_epochs=1, max_nb_epochs=1000)","title":"Force training for min or max epochs"},{"location":"Trainer/Training Loop/#force-disable-early-stop","text":"Use this to turn off early stopping and run training to the max_epoch # DEFAULT trainer = Trainer(enable_early_stop=True)","title":"Force disable early stop"},{"location":"Trainer/Training Loop/#inspect-gradient-norms","text":"Looking at grad norms can help you figure out where training might be going wrong. # DEFAULT (-1 doesn't track norms) trainer = Trainer(track_grad_norm=-1) # track the LP norm (P=2 here) trainer = Trainer(track_grad_norm=2)","title":"Inspect gradient norms"},{"location":"Trainer/Training Loop/#set-how-much-of-the-training-set-to-check","text":"If you don't want to check 100% of the training set (for debugging or if it's huge), set this flag # DEFAULT trainer = Trainer(train_percent_check=1.0) # check 10% only trainer = Trainer(train_percent_check=0.1)","title":"Set how much of the training set to check"},{"location":"Trainer/Validation loop/","text":"The lightning validation loop handles everything except the actual computations of your model. To decide what will happen in your validation loop, define the validation_step function . Below are all the things lightning automates for you in the validation loop. Note Lightning will run 5 steps of validation in the beginning of training as a sanity check so you don't have to wait until a full epoch to catch possible validation issues. Check validation every n epochs If you have a small dataset you might want to check validation every n epochs # DEFAULT trainer = Trainer(check_val_every_n_epoch=1) Set how much of the validation set to check If you don't want to check 100% of the validation set (for debugging or if it's huge), set this flag # DEFAULT trainer = Trainer(val_percent_check=1.0) # check 10% only trainer = Trainer(val_percent_check=0.1) Set how much of the test set to check If you don't want to check 100% of the test set (for debugging or if it's huge), set this flag # DEFAULT trainer = Trainer(test_percent_check=1.0) # check 10% only trainer = Trainer(test_percent_check=0.1) Set validation check frequency within 1 training epoch For large datasets it's often desirable to check validation multiple times within a training loop # DEFAULT trainer = Trainer(val_check_interval=0.95) # check every .25 of an epoch trainer = Trainer(val_check_interval=0.25) Set the number of validation sanity steps Lightning runs a few steps of validation in the beginning of training. This avoids crashing in the validation loop sometime deep into a lengthy training loop. # DEFAULT trainer = Trainer(nb_sanity_val_steps=5)","title":"Validation loop"},{"location":"Trainer/Validation loop/#check-validation-every-n-epochs","text":"If you have a small dataset you might want to check validation every n epochs # DEFAULT trainer = Trainer(check_val_every_n_epoch=1)","title":"Check validation every n epochs"},{"location":"Trainer/Validation loop/#set-how-much-of-the-validation-set-to-check","text":"If you don't want to check 100% of the validation set (for debugging or if it's huge), set this flag # DEFAULT trainer = Trainer(val_percent_check=1.0) # check 10% only trainer = Trainer(val_percent_check=0.1)","title":"Set how much of the validation set to check"},{"location":"Trainer/Validation loop/#set-how-much-of-the-test-set-to-check","text":"If you don't want to check 100% of the test set (for debugging or if it's huge), set this flag # DEFAULT trainer = Trainer(test_percent_check=1.0) # check 10% only trainer = Trainer(test_percent_check=0.1)","title":"Set how much of the test set to check"},{"location":"Trainer/Validation loop/#set-validation-check-frequency-within-1-training-epoch","text":"For large datasets it's often desirable to check validation multiple times within a training loop # DEFAULT trainer = Trainer(val_check_interval=0.95) # check every .25 of an epoch trainer = Trainer(val_check_interval=0.25)","title":"Set validation check frequency within 1 training epoch"},{"location":"Trainer/Validation loop/#set-the-number-of-validation-sanity-steps","text":"Lightning runs a few steps of validation in the beginning of training. This avoids crashing in the validation loop sometime deep into a lengthy training loop. # DEFAULT trainer = Trainer(nb_sanity_val_steps=5)","title":"Set the number of validation sanity steps"},{"location":"Trainer/debugging/","text":"These flags are useful to help debug a model. Fast dev run This flag is meant for debugging a full train/val/test loop. It'll activate callbacks, everything but only with 1 training and 1 validation batch. Use this to debug a full run of your program quickly # DEFAULT trainer = Trainer(fast_dev_run=False) Inspect gradient norms Looking at grad norms can help you figure out where training might be going wrong. # DEFAULT (-1 doesn't track norms) trainer = Trainer(track_grad_norm=-1) # track the LP norm (P=2 here) trainer = Trainer(track_grad_norm=2) Make model overfit on subset of data A useful debugging trick is to make your model overfit a tiny fraction of the data. # DEFAULT don't overfit (ie: normal training) trainer = Trainer(overfit_pct=0.0) # overfit on 1% of data trainer = Trainer(overfit_pct=0.01) Print the parameter count by layer By default lightning prints a list of parameters and submodules when it starts training. Print which gradients are nan This option prints a list of tensors with nan gradients. # DEFAULT trainer = Trainer(print_nan_grads=False) Log GPU usage Lightning automatically logs gpu usage to the test tube logs. It'll only do it at the metric logging interval, so it doesn't slow down training.","title":"Debugging"},{"location":"Trainer/debugging/#fast-dev-run","text":"This flag is meant for debugging a full train/val/test loop. It'll activate callbacks, everything but only with 1 training and 1 validation batch. Use this to debug a full run of your program quickly # DEFAULT trainer = Trainer(fast_dev_run=False)","title":"Fast dev run"},{"location":"Trainer/debugging/#inspect-gradient-norms","text":"Looking at grad norms can help you figure out where training might be going wrong. # DEFAULT (-1 doesn't track norms) trainer = Trainer(track_grad_norm=-1) # track the LP norm (P=2 here) trainer = Trainer(track_grad_norm=2)","title":"Inspect gradient norms"},{"location":"Trainer/debugging/#make-model-overfit-on-subset-of-data","text":"A useful debugging trick is to make your model overfit a tiny fraction of the data. # DEFAULT don't overfit (ie: normal training) trainer = Trainer(overfit_pct=0.0) # overfit on 1% of data trainer = Trainer(overfit_pct=0.01)","title":"Make model overfit on subset of data"},{"location":"Trainer/debugging/#print-the-parameter-count-by-layer","text":"By default lightning prints a list of parameters and submodules when it starts training.","title":"Print the parameter count by layer"},{"location":"Trainer/debugging/#print-which-gradients-are-nan","text":"This option prints a list of tensors with nan gradients. # DEFAULT trainer = Trainer(print_nan_grads=False)","title":"Print which gradients are nan"},{"location":"Trainer/debugging/#log-gpu-usage","text":"Lightning automatically logs gpu usage to the test tube logs. It'll only do it at the metric logging interval, so it doesn't slow down training.","title":"Log GPU usage"},{"location":"Trainer/hooks/","text":"","title":"Hooks"}]}
\ No newline at end of file
diff --git a/sitemap.xml.gz b/sitemap.xml.gz
index 0946004f..c21a8744 100644
Binary files a/sitemap.xml.gz and b/sitemap.xml.gz differ