# Copyright 2023 Google LLC # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. import argparse from tqdm import tqdm import torch import torch.nn as nn import torch.nn.functional as F import torch.optim as optim from torchvision import datasets, transforms from torch.optim.lr_scheduler import StepLR from torch.utils.data.distributed import DistributedSampler class CNN(nn.Module): ''' Convolutional neural network. ''' def __init__(self): super(CNN, self).__init__() self.conv1 = nn.Conv2d(1, 32, 3, 1) self.conv2 = nn.Conv2d(32, 64, 3, 1) self.dropout1 = nn.Dropout(0.25) self.dropout2 = nn.Dropout(0.5) self.fc1 = nn.Linear(9216, 128) self.fc2 = nn.Linear(128, 10) def forward(self, x): x = self.conv1(x) x = F.relu(x) x = self.conv2(x) x = F.relu(x) x = F.max_pool2d(x, 2) x = self.dropout1(x) x = torch.flatten(x, 1) x = self.fc1(x) x = F.relu(x) x = self.dropout2(x) x = self.fc2(x) output = F.log_softmax(x, dim=1) return output def train(args, model, device, train_loader, optimizer, epoch): model.train() for batch_idx, (data, target) in tqdm(enumerate(train_loader)): data, target = data.to(device), target.to(device) optimizer.zero_grad() output = model(data) loss = F.nll_loss(output, target) loss.backward() optimizer.step() if batch_idx % args.log_interval == 0: print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format( epoch, batch_idx * len(data), len(train_loader.dataset), 100. * batch_idx / len(train_loader), loss.item())) if args.dry_run: break def test(model, device, test_loader): model.eval() test_loss = 0 correct = 0 with torch.no_grad(): for data, target in test_loader: data, target = data.to(device), target.to(device) output = model(data) test_loss += F.nll_loss(output, target, reduction='sum').item() # sum up batch loss pred = output.argmax(dim=1, keepdim=True) # get the index of the max log-probability correct += pred.eq(target.view_as(pred)).sum().item() test_loss /= len(test_loader.dataset) print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format( test_loss, correct, len(test_loader.dataset), 100. * correct / len(test_loader.dataset))) def main(): # Training settings parser = argparse.ArgumentParser(description='PyTorch MNIST Example') parser.add_argument('--batch-size', type=int, default=64, metavar='N', help='input batch size for training (default: 64)') parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N', help='input batch size for testing (default: 1000)') parser.add_argument('--epochs', type=int, default=14, metavar='N', help='number of epochs to train (default: 14)') parser.add_argument('--lr', type=float, default=1.0, metavar='LR', help='learning rate (default: 1.0)') parser.add_argument('--gamma', type=float, default=0.7, metavar='M', help='Learning rate step gamma (default: 0.7)') parser.add_argument('--no-cuda', action='store_true', default=False, help='disables CUDA training') parser.add_argument('--no-mps', action='store_true', default=False, help='disables macOS GPU training') parser.add_argument('--dry-run', action='store_true', default=False, help='quickly check a single pass') parser.add_argument('--seed', type=int, default=1, metavar='S', help='random seed (default: 1)') parser.add_argument('--log-interval', type=int, default=10, metavar='N', help='how many batches to wait before logging training status') parser.add_argument('--save-model', action='store_true', default=False, help='For Saving the current Model') args = parser.parse_args() use_cuda = not args.no_cuda and torch.cuda.is_available() use_mps = not args.no_mps and torch.backends.mps.is_available() torch.manual_seed(args.seed) # Initialize distributed training coordation. torch.distributed.init_process_group(backend="gloo") device = "cpu" if not torch.cuda.is_available() else "cuda" train_kwargs = {'batch_size': args.batch_size} test_kwargs = {'batch_size': args.test_batch_size} if use_cuda: cuda_kwargs = {'num_workers': 1, 'pin_memory': True} train_kwargs.update(cuda_kwargs) test_kwargs.update(cuda_kwargs) # Set up distributed training to use DDP. model = torch.nn.parallel.DistributedDataParallel(CNN().to(device)) transform=transforms.Compose([ transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,)) ]) train_set = datasets.MNIST('../data', train=True, download=True, transform=transform) test_set = datasets.MNIST('../data', train=False, transform=transform) # Set up distributed data sampling so each worker in our DDP set up will # process a specific subset/partition of the training data. train_sampler = DistributedSampler(dataset=train_set) train_loader = torch.utils.data.DataLoader(train_set,**train_kwargs, sampler=train_sampler) test_loader = torch.utils.data.DataLoader(test_set, **test_kwargs) optimizer = optim.Adadelta(model.parameters(), lr=args.lr) scheduler = StepLR(optimizer, step_size=1, gamma=args.gamma) for epoch in range(1, args.epochs + 1): train(args, model, device, train_loader, optimizer, epoch) test(model, device, test_loader) scheduler.step() if args.save_model: torch.save(model.state_dict(), "mnist_cnn.pt") if __name__ == '__main__': main()