accelerate config

import os
from accelerate.utils import write_basic_config

write_basic_config()  # Write a config file
os._exit(00)  # Restart the notebook

import os, re, torch, PIL
import numpy as np

from torch.optim.lr_scheduler import OneCycleLR
from torch.utils.data import DataLoader, Dataset
from torchvision.transforms import Compose, RandomResizedCrop, Resize, ToTensor

from accelerate import Accelerator
from accelerate.utils import set_seed
from timm import create_model

import os

data_dir = "../../images"
fnames = os.listdir(data_dir)
fname = fnames[0]
print(fname)

beagle_32.jpg

import re


def extract_label(fname):
    stem = fname.split(os.path.sep)[-1]
    return re.search(r"^(.*)_\d+\.jpg$", stem).groups()[0]

extract_label(fname)

"beagle"

class PetsDataset(Dataset):
    def __init__(self, file_names, image_transform=None, label_to_id=None):
        self.file_names = file_names
        self.image_transform = image_transform
        self.label_to_id = label_to_id

    def __len__(self):
        return len(self.file_names)

    def __getitem__(self, idx):
        fname = self.file_names[idx]
        raw_image = PIL.Image.open(fname)
        image = raw_image.convert("RGB")
        if self.image_transform is not None:
            image = self.image_transform(image)
        label = extract_label(fname)
        if self.label_to_id is not None:
            label = self.label_to_id[label]
        return {"image": image, "label": label}

fnames = [os.path.join("../../images", fname) for fname in fnames if fname.endswith(".jpg")]

all_labels = [extract_label(fname) for fname in fnames]
id_to_label = list(set(all_labels))
id_to_label.sort()
label_to_id = {lbl: i for i, lbl in enumerate(id_to_label)}

def get_dataloaders(batch_size: int = 64):
    "Builds a set of dataloaders with a batch_size"
    random_perm = np.random.permutation(len(fnames))
    cut = int(0.8 * len(fnames))
    train_split = random_perm[:cut]
    eval_split = random_perm[cut:]

    # For training a simple RandomResizedCrop will be used
    train_tfm = Compose([RandomResizedCrop((224, 224), scale=(0.5, 1.0)), ToTensor()])
    train_dataset = PetsDataset([fnames[i] for i in train_split], image_transform=train_tfm, label_to_id=label_to_id)

    # For evaluation a deterministic Resize will be used
    eval_tfm = Compose([Resize((224, 224)), ToTensor()])
    eval_dataset = PetsDataset([fnames[i] for i in eval_split], image_transform=eval_tfm, label_to_id=label_to_id)

    # Instantiate dataloaders
    train_dataloader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size, num_workers=4)
    eval_dataloader = DataLoader(eval_dataset, shuffle=False, batch_size=batch_size * 2, num_workers=4)
    return train_dataloader, eval_dataloader

from torch.optim.lr_scheduler import CosineAnnealingLR

def training_loop(mixed_precision="fp16", seed: int = 42, batch_size: int = 64):
    set_seed(seed)
    accelerator = Accelerator(mixed_precision=mixed_precision)

    train_dataloader, eval_dataloader = get_dataloaders(batch_size)
    model = create_model("resnet50d", pretrained=True, num_classes=len(label_to_id))

    for param in model.parameters():
        param.requires_grad = False
    for param in model.get_classifier().parameters():
        param.requires_grad = True

    mean = torch.tensor(model.default_cfg["mean"])[None, :, None, None]
    std = torch.tensor(model.default_cfg["std"])[None, :, None, None]

    mean = mean.to(accelerator.device)
    std = std.to(accelerator.device)

    optimizer = torch.optim.Adam(params=model.parameters(), lr=3e-2 / 25)
    lr_scheduler = OneCycleLR(optimizer=optimizer, max_lr=3e-2, epochs=5, steps_per_epoch=len(train_dataloader))

    model, optimizer, train_dataloader, eval_dataloader, lr_scheduler = accelerator.prepare(
        model, optimizer, train_dataloader, eval_dataloader, lr_scheduler
    )

    for epoch in range(5):
        model.train()
        for batch in train_dataloader:
            inputs = (batch["image"] - mean) / std
            outputs = model(inputs)
            loss = torch.nn.functional.cross_entropy(outputs, batch["label"])
            accelerator.backward(loss)
            optimizer.step()
            lr_scheduler.step()
            optimizer.zero_grad()

        model.eval()
        accurate = 0
        num_elems = 0

        for batch in eval_dataloader:
            inputs = (batch["image"] - mean) / std
            with torch.no_grad():
                outputs = model(inputs)
            predictions = outputs.argmax(dim=-1)

            accurate_preds = accelerator.gather(predictions) == accelerator.gather(batch["label"])
            num_elems += accurate_preds.shape[0]
            accurate += accurate_preds.long().sum()

        eval_metric = accurate.item() / num_elems
        accelerator.print(f"epoch {epoch}: {100 * eval_metric:.2f}")

def training_loop(mixed_precision="fp16", seed: int = 42, batch_size: int = 64):
    set_seed(seed)
    # Initialize accelerator
    accelerator = Accelerator(mixed_precision=mixed_precision)
    # Build dataloaders
    train_dataloader, eval_dataloader = get_dataloaders(batch_size)

    # Instantiate the model (you build the model here so that the seed also controls new weight initializations)
    model = create_model("resnet50d", pretrained=True, num_classes=len(label_to_id))

    # Freeze the base model
    for param in model.parameters():
        param.requires_grad = False
    for param in model.get_classifier().parameters():
        param.requires_grad = True

    # You can normalize the batches of images to be a bit faster
    mean = torch.tensor(model.default_cfg["mean"])[None, :, None, None]
    std = torch.tensor(model.default_cfg["std"])[None, :, None, None]

    # To make these constants available on the active device, set it to the accelerator device
    mean = mean.to(accelerator.device)
    std = std.to(accelerator.device)

    # Instantiate the optimizer
    optimizer = torch.optim.Adam(params=model.parameters(), lr=3e-2 / 25)

    # Instantiate the learning rate scheduler
    lr_scheduler = OneCycleLR(optimizer=optimizer, max_lr=3e-2, epochs=5, steps_per_epoch=len(train_dataloader))

    # Prepare everything
    # There is no specific order to remember, you just need to unpack the objects in the same order you gave them to the
    # prepare method.
    model, optimizer, train_dataloader, eval_dataloader, lr_scheduler = accelerator.prepare(
        model, optimizer, train_dataloader, eval_dataloader, lr_scheduler
    )

    # Now you train the model
    for epoch in range(5):
        model.train()
        for batch in train_dataloader:
            inputs = (batch["image"] - mean) / std
            outputs = model(inputs)
            loss = torch.nn.functional.cross_entropy(outputs, batch["label"])
            accelerator.backward(loss)
            optimizer.step()
            lr_scheduler.step()
            optimizer.zero_grad()

        model.eval()
        accurate = 0
        num_elems = 0
        for batch in eval_dataloader:
            inputs = (batch["image"] - mean) / std
            with torch.no_grad():
                outputs = model(inputs)
            predictions = outputs.argmax(dim=-1)
            accurate_preds = accelerator.gather(predictions) == accelerator.gather(batch["label"])
            num_elems += accurate_preds.shape[0]
            accurate += accurate_preds.long().sum()

        eval_metric = accurate.item() / num_elems
        # Use accelerator.print to print only on the main process.
        accelerator.print(f"epoch {epoch}: {100 * eval_metric:.2f}")

from accelerate import notebook_launcher

args = ("fp16", 42, 64)
notebook_launcher(training_loop, args, num_processes=2)

notebook_launcher(training_loop, args, master_addr="172.31.43.8", node_rank=0, num_nodes=2, num_processes=8)

notebook_launcher(training_loop, args, master_addr="172.31.43.8", node_rank=1, num_nodes=2, num_processes=8)

model = create_model("resnet50d", pretrained=True, num_classes=len(label_to_id))

args = (model, "fp16", 42, 64)
notebook_launcher(training_loop, args, num_processes=8)

notebook_launcher(
    training_loop,
    args,
    num_processes=2,
    max_restarts=3
)

Launching training on 2 GPUs.
epoch 0: 88.12
epoch 1: 91.73
epoch 2: 92.58
epoch 3: 93.90
epoch 4: 94.71

accelerate launch