加速 PyTorch 模型训练的 9 个技巧(收藏)

from pytorch_lightning import Trainer
model = LightningModule(…)
trainer = Trainer()
trainer.fit(model)

 dataset = MNIST(root=self.hparams.data_root, train=train, download=True)
 loader = DataLoader(dataset, batch_size=32, shuffle=True)
 for batch in loader:
   x, y = batch
   model.training_step(x, y)
   ...

# slow
 loader = DataLoader(dataset, batch_size=32, shuffle=True)
 # fast (use 10 workers)
 loader = DataLoader(dataset, batch_size=32, shuffle=True, num_workers=10)

# clear last step
optimizer.zero_grad()

# 16 accumulated gradient steps
scaled_loss = 0
for accumulated_step_i in range(16):
     out = model.forward()
     loss = some_loss(out,y)    
     loss.backward()
      scaled_loss += loss.item()
      
# update weights after 8 steps. effective batch = 8*16
optimizer.step()

# loss is now scaled up by the number of accumulated batches
actual_loss = scaled_loss / 16

trainer = Trainer(accumulate_grad_batches=16)
trainer.fit(model)

 losses = []
 ...
 losses.append(loss)
 
 print(f'current loss: {torch.mean(losses)'})

![1_CER3v8cok2UOBNsmnBrzPQ](9 Tips For Training Lightning-Fast Neural Networks In Pytorch.assets/1_CER3v8cok2UOBNsmnBrzPQ.gif)# bad
 losses.append(loss)
 # good
losses.append(loss.item())

# put model on GPU
model.cuda(0)
 
# put data on gpu (cuda on a variable returns a cuda copy)
x = x.cuda(0)
 
# runs on GPU now
model(x)

# ask lightning to use gpu 0 for training
trainer = Trainer(gpus=[0])
trainer.fit(model)

# expensive
x = x.cuda(0)# very expensive
x = x.cpu()
x = x.cuda(0)

# really bad idea. Stops all the GPUs until they all catch up
torch.cuda.empty_cache()

# enable 16-bit on the model and the optimizer
model, optimizers = amp.initialize(model, optimizers, opt_level='O2')
 
# when doing .backward, let amp do it so it can scale the loss
with amp.scale_loss(loss, optimizer) as scaled_loss:                     
    scaled_loss.backward()

trainer = Trainer(amp_level='O2', use_amp=False)
trainer.fit(model)

# copy model on each GPU and give a fourth of the batch to each
model = DataParallel(model, devices=[0, 1, 2 ,3])
 
# out has 4 outputs (one for each gpu)
out = model(x.cuda(0))

# ask lightning to use 4 GPUs for training
trainer = Trainer(gpus=[0, 1, 2, 3])
trainer.fit(model)

# each model is sooo big we can't fit both in memory
encoder_rnn.cuda(0)
decoder_rnn.cuda(1)
 
# run input through encoder on GPU 0
encoder_out = encoder_rnn(x.cuda(0))
 
# run output through decoder on the next GPU
out = decoder_rnn(encoder_out.cuda(1))
 
# normally we want to bring all outputs back to GPU 0
out = out.cuda(0)

class MyModule(LightningModule):
    def __init__():
        self.encoder = RNN(...)
        self.decoder = RNN(...)
    def forward(x):
        # models won't be moved after the first forward because
        # they are already on the correct GPUs
        self.encoder.cuda(0)
        self.decoder.cuda(1)
        out = self.encoder(x)
        out = self.decoder(out.cuda(1))
         
# don't pass GPUs to trainer
model = MyModule()
trainer = Trainer()
trainer.fit(model)

# change these lines
self.encoder = RNN(...)
self.decoder = RNN(...)
 
# to these
# now each RNN is based on a different gpu set
self.encoder = DataParallel(self.encoder, devices=[0, 1, 2, 3])
self.decoder = DataParallel(self.encoder, devices=[4, 5, 6, 7])
 
# in forward...
out = self.encoder(x.cuda(0))
 
# notice inputs on first gpu in device
sout = self.decoder(out.cuda(4))  # <--- the 4 here

def tng_dataloader():
     d = MNIST()
      
     # 4: Add distributed sampler
     # sampler sends a portion of tng data to each machine
     dist_sampler = DistributedSampler(dataset)
     dataloader = DataLoader(d, shuffle=False, sampler=dist_sampler)
      
def main_process_entrypoint(gpu_nb):
     # 2: set up connections  between all gpus across all machines
     # all gpus connect to a single GPU "root"
     # the default uses env://
     world = nb_gpus * nb_nodes
     dist.init_process_group("nccl", rank=gpu_nb, world_size=world)
      
     # 3: wrap model in DPP
     torch.cuda.set_device(gpu_nb)
     model.cuda(gpu_nb)
     model = DistributedDataParallel(model, device_ids=[gpu_nb])
      
     # train your model now...
      
if  __name__ == '__main__':
     # 1: spawn number of processes
     # your cluster will call main for each machine
     mp.spawn(main_process_entrypoint, nprocs=8)

# train on 1024 gpus across 128 nodes
trainer = Trainer(nb_gpu_nodes=128, gpus=[0, 1, 2, 3, 4, 5, 6, 7])

# train on 4 gpus on the same machine MUCH faster than DataParallel
trainer = Trainer(distributed_backend='ddp', gpus=[0, 1, 2, 3])