Last active
March 6, 2019 18:43
-
-
Save vfdev-5/3ed8cc7339a874f056013bf7706796db to your computer and use it in GitHub Desktop.
TypeError: _queue_reduction(): incompatible function arguments. The following argument types are supported:
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from __future__ import print_function | |
import argparse | |
import random | |
import torch | |
import torch.nn as nn | |
import torch.optim as optim | |
import torch.nn.functional as F | |
import torch.nn.parallel as parallel | |
import torch.distributed as dist | |
import torch.multiprocessing as mp | |
import torch.utils.data.distributed as data_dist | |
from torch.utils.data import DataLoader, BatchSampler | |
from torchvision.models.resnet import resnet18 | |
from torchvision import datasets, transforms | |
USE_DISTRIBUTED=True | |
class Net(nn.Module): | |
def __init__(self): | |
super(Net, self).__init__() | |
self.backbone = resnet18(pretrained=False, num_classes=10) | |
self.backbone.conv1 = nn.Conv2d(1, 64, kernel_size=3, stride=1, padding=1, bias=False) | |
# self.backbone.maxpool = nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1, bias=False) | |
# following module is not used | |
self.maxpool = nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1, bias=False) | |
def forward(self, x): | |
x = self.backbone(x) | |
return F.log_softmax(x, dim=-1) | |
def train(args, model, device, train_loader, optimizer, epoch): | |
model.train() | |
for batch_idx, (data, target) in enumerate(train_loader): | |
data, target = data.to(device, non_blocking=True), target.to(device, non_blocking=True) | |
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())) | |
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=10, metavar='N', | |
help='number of epochs to train (default: 10)') | |
parser.add_argument('--lr', type=float, default=0.01, metavar='LR', | |
help='learning rate (default: 0.01)') | |
parser.add_argument('--momentum', type=float, default=0.5, metavar='M', | |
help='SGD momentum (default: 0.5)') | |
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') | |
parser.add_argument("--local_rank", type=int, default=0) | |
args = parser.parse_args() | |
local_rank = args.local_rank | |
if USE_DISTRIBUTED: | |
dist.init_process_group(backend='nccl') | |
torch.cuda.device(local_rank) | |
device = torch.device('cuda:{}'.format(local_rank)) | |
torch.backends.cudnn.benchmark = True | |
torch.manual_seed(args.seed) | |
train_sampler = None | |
train_dataset = datasets.MNIST('.', train=True, download=True, | |
transform=transforms.Compose([ | |
transforms.ToTensor(), | |
transforms.Normalize((0.1307,), (0.3081,)) | |
])) | |
if USE_DISTRIBUTED: | |
train_sampler = data_dist.DistributedSampler(train_dataset) | |
kwargs = {'num_workers': 1, 'pin_memory': True} | |
train_loader = torch.utils.data.DataLoader(train_dataset, | |
batch_size=args.batch_size, | |
sampler=train_sampler, **kwargs) | |
model = Net().to(device) | |
if USE_DISTRIBUTED: | |
model = parallel.DistributedDataParallel(model, | |
device_ids=[local_rank], | |
output_device=local_rank) | |
optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum=args.momentum) | |
for epoch in range(1, args.epochs + 1): | |
train(args, model, device, train_loader, optimizer, epoch) | |
if (args.save_model): | |
torch.save(model.state_dict(),"mnist_cnn.pt") | |
if __name__ == '__main__': | |
main() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment