How do i set Trainer parameters to run training on a CPU only machine?

[HareshKarnan]

My current setting is

trainer = pl.Trainer(gpus=None, max_epochs=args.max_epochs, log_every_n_steps=10, distributed_backend='ddp_cpu', logger=False, )

However, i get the following error :

pytorch_lightning.utilities.exceptions.MisconfigurationException: You requested GPUs: [0]
But your machine only has: []

[rohitgr7]

config looks correct. which PL version are you using? can you try v1.4.9 released recently?

[awaelchli]

As @rohitgr7 suggested, this works with PL version 1.4.9:

import torch
from torch.utils.data import DataLoader, Dataset

from pytorch_lightning import LightningModule, Trainer


class RandomDataset(Dataset):
    def __init__(self, size, length):
        self.len = length
        self.data = torch.randn(length, size)

    def __getitem__(self, index):
        return self.data[index]

    def __len__(self):
        return self.len


class BoringModel(LightningModule):
    def __init__(self):
        super().__init__()
        self.layer = torch.nn.Linear(32, 2)

    def forward(self, x):
        return self.layer(x)

    def training_step(self, batch, batch_idx):
        loss = self(batch).sum()
        self.log("train_loss", loss)
        return {"loss": loss}

    def validation_step(self, batch, batch_idx):
        loss = self(batch).sum()
        self.log("valid_loss", loss)

    def configure_optimizers(self):
        return torch.optim.SGD(self.layer.parameters(), lr=0.1)


def run():
    train_data = DataLoader(RandomDataset(32, 64), batch_size=2)
    val_data = DataLoader(RandomDataset(32, 64), batch_size=2)

    model = BoringModel()
    trainer = Trainer(
        gpus=None,
        limit_train_batches=1,
        limit_val_batches=1,
        num_sanity_val_steps=0,
        max_epochs=1,
        weights_summary=None,
        distributed_backend="ddp_cpu",
        # accelerator="ddp_cpu"  # in latest version of Lightning, use this
    )
    trainer.fit(model, train_dataloaders=train_data, val_dataloaders=val_data)


if __name__ == "__main__":
    run()

Output

GPU available: False, used: False
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
initializing ddp: GLOBAL_RANK: 0, MEMBER: 1/1
[W ProcessGroupGloo.cpp:684] Warning: Unable to resolve hostname to a (local) address. Using the loopback address as fallback. Manually set the network interface to bind to with GLOO_SOCKET_IFNAME. (function operator())
----------------------------------------------------------------------------------------------------
distributed_backend=gloo
All DDP processes registered. Starting ddp with 1 processes
----------------------------------------------------------------------------------------------------

/Users/adrian/repositories/pytorch-lightning/pytorch_lightning/trainer/data_loading.py:105: UserWarning: The dataloader, train dataloader, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 12 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.
  rank_zero_warn(
/Users/adrian/repositories/pytorch-lightning/pytorch_lightning/trainer/data_loading.py:326: UserWarning: The number of training samples (1) is smaller than the logging interval Trainer(log_every_n_steps=50). Set a lower value for log_every_n_steps if you want to see logs for the training epoch.
  rank_zero_warn(
/Users/adrian/repositories/pytorch-lightning/pytorch_lightning/trainer/data_loading.py:105: UserWarning: The dataloader, val dataloader 0, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 12 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.
  rank_zero_warn(
[W reducer.cpp:1158] Warning: find_unused_parameters=True was specified in DDP constructor, but did not find any unused parameters in the forward pass. This flag results in an extra traversal of the autograd graph every iteration,  which can adversely affect performance. If your model indeed never has any unused parameters in the forward pass, consider turning this flag off. Note that this warning may be a false positive if your model has flow control causing later iterations to have unused parameters. (function operator())
Epoch 0:  50%|█████     | 1/2 [00:00<00:00, 208.31it/s, loss=0.78, v_num=2]
Validating: 0it [00:00, ?it/s]
Epoch 0: 100%|██████████| 2/2 [00:00<00:00, 189.57it/s, loss=0.78, v_num=2]
Epoch 0: 100%|██████████| 2/2 [00:00<00:00, 162.39it/s, loss=0.78, v_num=2]
/Users/adrian/repositories/pytorch-lightning/pytorch_lightning/plugins/training_type/ddp_spawn.py:288: UserWarning: cleaning up ddp environment...
  rank_zero_warn("cleaning up ddp environment...")