From b7fa5987c98288d0c7fafaa639dc38a1828628b0 Mon Sep 17 00:00:00 2001 From: Miguel Sousa Date: Thu, 26 Sep 2024 10:50:38 -0700 Subject: [PATCH] Replace hardcoded default values in argparse help strings --- distributed/FSDP/T5_training.py | 8 ++++---- distributed/ddp-tutorial-series/multigpu.py | 3 ++- .../ddp-tutorial-series/multigpu_torchrun.py | 3 ++- distributed/ddp-tutorial-series/multinode.py | 3 ++- distributed/ddp-tutorial-series/single_gpu.py | 7 ++++--- distributed/rpc/batch/reinforce.py | 6 +++--- distributed/rpc/rl/main.py | 6 +++--- gat/main.py | 20 +++++++++---------- gcn/main.py | 18 ++++++++--------- imagenet/main.py | 14 ++++++------- legacy/snli/util.py | 8 ++++---- mnist/main.py | 12 +++++------ mnist_forward_forward/main.py | 6 +++--- mnist_hogwild/main.py | 14 ++++++------- mnist_rnn/main.py | 12 +++++------ reinforcement_learning/actor_critic.py | 6 +++--- reinforcement_learning/reinforce.py | 6 +++--- siamese_network/main.py | 12 +++++------ vae/main.py | 8 ++++---- word_language_model/generate.py | 4 ++-- word_language_model/main.py | 2 +- 21 files changed, 91 insertions(+), 87 deletions(-) diff --git a/distributed/FSDP/T5_training.py b/distributed/FSDP/T5_training.py index 4ab136eace..3b256d2f01 100644 --- a/distributed/FSDP/T5_training.py +++ b/distributed/FSDP/T5_training.py @@ -198,13 +198,13 @@ def fsdp_main(args): # Training settings parser = argparse.ArgumentParser(description='PyTorch T5 FSDP Example') parser.add_argument('--batch-size', type=int, default=4, metavar='N', - help='input batch size for training (default: 64)') + help='input batch size for training (default: %(default)s)') parser.add_argument('--test-batch-size', type=int, default=4, metavar='N', - help='input batch size for testing (default: 1000)') + help='input batch size for testing (default: %(default)s)') parser.add_argument('--epochs', type=int, default=2, metavar='N', - help='number of epochs to train (default: 3)') + help='number of epochs to train (default: %(default)s)') parser.add_argument('--seed', type=int, default=1, metavar='S', - help='random seed (default: 1)') + help='random seed (default: %(default)s)') parser.add_argument('--track_memory', action='store_false', default=True, help='track the gpu memory') parser.add_argument('--run_validation', action='store_false', default=True, diff --git a/distributed/ddp-tutorial-series/multigpu.py b/distributed/ddp-tutorial-series/multigpu.py index 7e11633305..84865b3140 100644 --- a/distributed/ddp-tutorial-series/multigpu.py +++ b/distributed/ddp-tutorial-series/multigpu.py @@ -97,7 +97,8 @@ def main(rank: int, world_size: int, save_every: int, total_epochs: int, batch_s parser = argparse.ArgumentParser(description='simple distributed training job') parser.add_argument('total_epochs', type=int, help='Total epochs to train the model') parser.add_argument('save_every', type=int, help='How often to save a snapshot') - parser.add_argument('--batch_size', default=32, type=int, help='Input batch size on each device (default: 32)') + parser.add_argument('--batch_size', default=32, type=int, + help='Input batch size on each device (default: %(default)s)') args = parser.parse_args() world_size = torch.cuda.device_count() diff --git a/distributed/ddp-tutorial-series/multigpu_torchrun.py b/distributed/ddp-tutorial-series/multigpu_torchrun.py index 32d6254d2d..fd198da4aa 100644 --- a/distributed/ddp-tutorial-series/multigpu_torchrun.py +++ b/distributed/ddp-tutorial-series/multigpu_torchrun.py @@ -105,7 +105,8 @@ def main(save_every: int, total_epochs: int, batch_size: int, snapshot_path: str parser = argparse.ArgumentParser(description='simple distributed training job') parser.add_argument('total_epochs', type=int, help='Total epochs to train the model') parser.add_argument('save_every', type=int, help='How often to save a snapshot') - parser.add_argument('--batch_size', default=32, type=int, help='Input batch size on each device (default: 32)') + parser.add_argument('--batch_size', default=32, type=int, + help='Input batch size on each device (default: %(default)s)') args = parser.parse_args() main(args.save_every, args.total_epochs, args.batch_size) diff --git a/distributed/ddp-tutorial-series/multinode.py b/distributed/ddp-tutorial-series/multinode.py index 72670171b5..973cff0b23 100644 --- a/distributed/ddp-tutorial-series/multinode.py +++ b/distributed/ddp-tutorial-series/multinode.py @@ -106,7 +106,8 @@ def main(save_every: int, total_epochs: int, batch_size: int, snapshot_path: str parser = argparse.ArgumentParser(description='simple distributed training job') parser.add_argument('total_epochs', type=int, help='Total epochs to train the model') parser.add_argument('save_every', type=int, help='How often to save a snapshot') - parser.add_argument('--batch_size', default=32, type=int, help='Input batch size on each device (default: 32)') + parser.add_argument('--batch_size', default=32, type=int, + help='Input batch size on each device (default: %(default)s)') args = parser.parse_args() main(args.save_every, args.total_epochs, args.batch_size) diff --git a/distributed/ddp-tutorial-series/single_gpu.py b/distributed/ddp-tutorial-series/single_gpu.py index e91ab81cc1..1e5359a6e0 100644 --- a/distributed/ddp-tutorial-series/single_gpu.py +++ b/distributed/ddp-tutorial-series/single_gpu.py @@ -11,7 +11,7 @@ def __init__( train_data: DataLoader, optimizer: torch.optim.Optimizer, gpu_id: int, - save_every: int, + save_every: int, ) -> None: self.gpu_id = gpu_id self.model = model.to(gpu_id) @@ -75,8 +75,9 @@ def main(device, total_epochs, save_every, batch_size): parser = argparse.ArgumentParser(description='simple distributed training job') parser.add_argument('total_epochs', type=int, help='Total epochs to train the model') parser.add_argument('save_every', type=int, help='How often to save a snapshot') - parser.add_argument('--batch_size', default=32, type=int, help='Input batch size on each device (default: 32)') + parser.add_argument('--batch_size', default=32, type=int, + help='Input batch size on each device (default: %(default)s)') args = parser.parse_args() - + device = 0 # shorthand for cuda:0 main(device, args.total_epochs, args.save_every, args.batch_size) diff --git a/distributed/rpc/batch/reinforce.py b/distributed/rpc/batch/reinforce.py index 13a06315de..4d6baddcfe 100644 --- a/distributed/rpc/batch/reinforce.py +++ b/distributed/rpc/batch/reinforce.py @@ -21,11 +21,11 @@ parser = argparse.ArgumentParser(description='PyTorch RPC Batch RL example') parser.add_argument('--gamma', type=float, default=1.0, metavar='G', - help='discount factor (default: 1.0)') + help='discount factor (default: %(default)s)') parser.add_argument('--seed', type=int, default=543, metavar='N', - help='random seed (default: 543)') + help='random seed (default: %(default)s)') parser.add_argument('--num-episode', type=int, default=10, metavar='E', - help='number of episodes (default: 10)') + help='number of episodes (default: %(default)s)') args = parser.parse_args() torch.manual_seed(args.seed) diff --git a/distributed/rpc/rl/main.py b/distributed/rpc/rl/main.py index 91451ecc84..4365f37f5e 100644 --- a/distributed/rpc/rl/main.py +++ b/distributed/rpc/rl/main.py @@ -21,11 +21,11 @@ parser.add_argument('--world-size', type=int, default=2, metavar='W', help='world size for RPC, rank 0 is the agent, others are observers') parser.add_argument('--gamma', type=float, default=0.99, metavar='G', - help='discount factor (default: 0.99)') + help='discount factor (default: %(default)s)') parser.add_argument('--seed', type=int, default=543, metavar='N', - help='random seed (default: 543)') + help='random seed (default: %(default)s)') parser.add_argument('--log-interval', type=int, default=10, metavar='N', - help='interval between training status logs (default: 10)') + help='interval between training status logs (default: %(default)s)') args = parser.parse_args() torch.manual_seed(args.seed) diff --git a/gat/main.py b/gat/main.py index 9c143af8ec..87b59349d3 100644 --- a/gat/main.py +++ b/gat/main.py @@ -292,21 +292,21 @@ def test(model, criterion, input, target, mask): parser = argparse.ArgumentParser(description='PyTorch Graph Attention Network') parser.add_argument('--epochs', type=int, default=300, - help='number of epochs to train (default: 300)') + help='number of epochs to train (default: %(default)s)') parser.add_argument('--lr', type=float, default=0.005, - help='learning rate (default: 0.005)') + help='learning rate (default: %(default)s)') parser.add_argument('--l2', type=float, default=5e-4, - help='weight decay (default: 6e-4)') + help='weight decay (default: %(default)s)') parser.add_argument('--dropout-p', type=float, default=0.6, - help='dropout probability (default: 0.6)') + help='dropout probability (default: %(default)s)') parser.add_argument('--hidden-dim', type=int, default=64, - help='dimension of the hidden representation (default: 64)') + help='dimension of the hidden representation (default: %(default)s)') parser.add_argument('--num-heads', type=int, default=8, - help='number of the attention heads (default: 4)') + help='number of the attention heads (default: %(default)s)') parser.add_argument('--concat-heads', action='store_true', default=False, - help='wether to concatinate attention heads, or average over them (default: False)') + help='wether to concatinate attention heads, or average over them (default: %(default)s)') parser.add_argument('--val-every', type=int, default=20, - help='epochs to wait for print training and validation evaluation (default: 20)') + help='epochs to wait for print training and validation evaluation (default: %(default)s)') parser.add_argument('--no-cuda', action='store_true', default=False, help='disables CUDA training') parser.add_argument('--no-mps', action='store_true', default=False, @@ -314,7 +314,7 @@ def test(model, criterion, input, target, mask): parser.add_argument('--dry-run', action='store_true', default=False, help='quickly check a single pass') parser.add_argument('--seed', type=int, default=13, metavar='S', - help='random seed (default: 13)') + help='random seed (default: %(default)s)') args = parser.parse_args() torch.manual_seed(args.seed) @@ -372,4 +372,4 @@ def test(model, criterion, input, target, mask): if args.dry_run: break loss_test, acc_test = test(gat_net, criterion, (features, adj_mat), labels, idx_test) - print(f'Test set results: loss {loss_test:.4f} accuracy {acc_test:.4f}') \ No newline at end of file + print(f'Test set results: loss {loss_test:.4f} accuracy {acc_test:.4f}') diff --git a/gcn/main.py b/gcn/main.py index 5c8362b576..80b0c6ce14 100644 --- a/gcn/main.py +++ b/gcn/main.py @@ -203,19 +203,19 @@ def test(model, criterion, input, target, mask): parser = argparse.ArgumentParser(description='PyTorch Graph Convolutional Network') parser.add_argument('--epochs', type=int, default=200, - help='number of epochs to train (default: 200)') + help='number of epochs to train (default: %(default)s)') parser.add_argument('--lr', type=float, default=0.01, - help='learning rate (default: 0.01)') + help='learning rate (default: %(default)s)') parser.add_argument('--l2', type=float, default=5e-4, - help='weight decay (default: 5e-4)') + help='weight decay (default: %(default)s)') parser.add_argument('--dropout-p', type=float, default=0.5, - help='dropout probability (default: 0.5)') + help='dropout probability (default: %(default)s)') parser.add_argument('--hidden-dim', type=int, default=16, - help='dimension of the hidden representation (default: 16)') + help='dimension of the hidden representation (default: %(default)s)') parser.add_argument('--val-every', type=int, default=20, - help='epochs to wait for print training and validation evaluation (default: 20)') + help='epochs to wait for print training and validation evaluation (default: %(default)s)') parser.add_argument('--include-bias', action='store_true', default=False, - help='use bias term in convolutions (default: False)') + help='use bias term in convolutions (default: %(default)s)') parser.add_argument('--no-cuda', action='store_true', default=False, help='disables CUDA training') parser.add_argument('--no-mps', action='store_true', default=False, @@ -223,7 +223,7 @@ def test(model, criterion, input, target, mask): parser.add_argument('--dry-run', action='store_true', default=False, help='quickly check a single pass') parser.add_argument('--seed', type=int, default=42, metavar='S', - help='random seed (default: 42)') + help='random seed (default: %(default)s)') args = parser.parse_args() use_cuda = not args.no_cuda and torch.cuda.is_available() @@ -260,4 +260,4 @@ def test(model, criterion, input, target, mask): break loss_test, acc_test = test(gcn, criterion, (features, adj_mat), labels, idx_test) - print(f'Test set results: loss {loss_test:.4f} accuracy {acc_test:.4f}') \ No newline at end of file + print(f'Test set results: loss {loss_test:.4f} accuracy {acc_test:.4f}') diff --git a/imagenet/main.py b/imagenet/main.py index cc32d50733..52805271ae 100644 --- a/imagenet/main.py +++ b/imagenet/main.py @@ -27,21 +27,21 @@ parser = argparse.ArgumentParser(description='PyTorch ImageNet Training') parser.add_argument('data', metavar='DIR', nargs='?', default='imagenet', - help='path to dataset (default: imagenet)') + help='path to dataset (default: %(default)s)') parser.add_argument('-a', '--arch', metavar='ARCH', default='resnet18', choices=model_names, help='model architecture: ' + ' | '.join(model_names) + - ' (default: resnet18)') + ' (default: %(default)s)') parser.add_argument('-j', '--workers', default=4, type=int, metavar='N', - help='number of data loading workers (default: 4)') + help='number of data loading workers (default: %(default)s)') parser.add_argument('--epochs', default=90, type=int, metavar='N', help='number of total epochs to run') parser.add_argument('--start-epoch', default=0, type=int, metavar='N', help='manual epoch number (useful on restarts)') parser.add_argument('-b', '--batch-size', default=256, type=int, metavar='N', - help='mini-batch size (default: 256), this is the total ' + help='mini-batch size (default: %(default)s), this is the total ' 'batch size of all GPUs on the current node when ' 'using Data Parallel or Distributed Data Parallel') parser.add_argument('--lr', '--learning-rate', default=0.1, type=float, @@ -49,12 +49,12 @@ parser.add_argument('--momentum', default=0.9, type=float, metavar='M', help='momentum') parser.add_argument('--wd', '--weight-decay', default=1e-4, type=float, - metavar='W', help='weight decay (default: 1e-4)', + metavar='W', help='weight decay (default: %(default)s)', dest='weight_decay') parser.add_argument('-p', '--print-freq', default=10, type=int, - metavar='N', help='print frequency (default: 10)') + metavar='N', help='print frequency (default: %(default)s)') parser.add_argument('--resume', default='', type=str, metavar='PATH', - help='path to latest checkpoint (default: none)') + help='path to latest checkpoint (default: %(default)s)') parser.add_argument('-e', '--evaluate', dest='evaluate', action='store_true', help='evaluate model on validation set') parser.add_argument('--pretrained', dest='pretrained', action='store_true', diff --git a/legacy/snli/util.py b/legacy/snli/util.py index 1bc8e0b2cc..7a4552c227 100644 --- a/legacy/snli/util.py +++ b/legacy/snli/util.py @@ -23,7 +23,7 @@ def get_args(): parser.add_argument('--epochs', type=int, default=50, help='the number of total epochs to run.') parser.add_argument('--batch_size', type=int, default=128, - help='batch size. (default: 128)') + help='batch size. (default: %(default)s)') parser.add_argument('--d_embed', type=int, default=100, help='the size of each embedding vector.') parser.add_argument('--d_proj', type=int, default=300, @@ -31,10 +31,10 @@ def get_args(): parser.add_argument('--d_hidden', type=int, default=300, help='the number of features in the hidden state.') parser.add_argument('--n_layers', type=int, default=1, - help='the number of recurrent layers. (default: 50)') + help='the number of recurrent layers. (default: %(default)s)') parser.add_argument('--log_every', type=int, default=50, help='iteration period to output log.') - parser.add_argument('--lr',type=float, default=.001, + parser.add_argument('--lr', type=float, default=.001, help='initial learning rate.') parser.add_argument('--dev_every', type=int, default=1000, help='log period of validation results.') @@ -51,7 +51,7 @@ def get_args(): parser.add_argument('--train_embed', action='store_false', dest='fix_emb', help='enable embedding word training.') parser.add_argument('--gpu', type=int, default=0, - help='gpu id to use. (default: 0)') + help='gpu id to use. (default: %(default)s)') parser.add_argument('--save_path', type=str, default='results', help='save path of results.') parser.add_argument('--vector_cache', type=str, default=os.path.join(os.getcwd(), '.vector_cache/input_vectors.pt'), diff --git a/mnist/main.py b/mnist/main.py index 184dc4744f..d2f45fbd4f 100644 --- a/mnist/main.py +++ b/mnist/main.py @@ -73,15 +73,15 @@ 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)') + help='input batch size for training (default: %(default)s)') parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N', - help='input batch size for testing (default: 1000)') + help='input batch size for testing (default: %(default)s)') parser.add_argument('--epochs', type=int, default=14, metavar='N', - help='number of epochs to train (default: 14)') + help='number of epochs to train (default: %(default)s)') parser.add_argument('--lr', type=float, default=1.0, metavar='LR', - help='learning rate (default: 1.0)') + help='learning rate (default: %(default)s)') parser.add_argument('--gamma', type=float, default=0.7, metavar='M', - help='Learning rate step gamma (default: 0.7)') + help='Learning rate step gamma (default: %(default)s)') parser.add_argument('--no-cuda', action='store_true', default=False, help='disables CUDA training') parser.add_argument('--no-mps', action='store_true', default=False, @@ -89,7 +89,7 @@ def main(): 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)') + help='random seed (default: %(default)s)') 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, diff --git a/mnist_forward_forward/main.py b/mnist_forward_forward/main.py index a175126067..b90b04d36f 100644 --- a/mnist_forward_forward/main.py +++ b/mnist_forward_forward/main.py @@ -92,14 +92,14 @@ def train(self, x_pos, x_neg): type=int, default=1000, metavar="N", - help="number of epochs to train (default: 1000)", + help="number of epochs to train (default: %(default)s)", ) parser.add_argument( "--lr", type=float, default=0.03, metavar="LR", - help="learning rate (default: 0.03)", + help="learning rate (default: %(default)s)", ) parser.add_argument( "--no_cuda", action="store_true", default=False, help="disables CUDA training" @@ -108,7 +108,7 @@ def train(self, x_pos, x_neg): "--no_mps", action="store_true", default=False, help="disables MPS training" ) parser.add_argument( - "--seed", type=int, default=1, metavar="S", help="random seed (default: 1)" + "--seed", type=int, default=1, metavar="S", help="random seed (default: %(default)s)" ) parser.add_argument( "--save_model", diff --git a/mnist_hogwild/main.py b/mnist_hogwild/main.py index 6fa449233d..e71b929c9c 100644 --- a/mnist_hogwild/main.py +++ b/mnist_hogwild/main.py @@ -12,21 +12,21 @@ # 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)') + help='input batch size for training (default: %(default)s)') parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N', - help='input batch size for testing (default: 1000)') + help='input batch size for testing (default: %(default)s)') parser.add_argument('--epochs', type=int, default=10, metavar='N', - help='number of epochs to train (default: 10)') + help='number of epochs to train (default: %(default)s)') parser.add_argument('--lr', type=float, default=0.01, metavar='LR', - help='learning rate (default: 0.01)') + help='learning rate (default: %(default)s)') parser.add_argument('--momentum', type=float, default=0.5, metavar='M', - help='SGD momentum (default: 0.5)') + help='SGD momentum (default: %(default)s)') parser.add_argument('--seed', type=int, default=1, metavar='S', - help='random seed (default: 1)') + help='random seed (default: %(default)s)') parser.add_argument('--log-interval', type=int, default=10, metavar='N', help='how many batches to wait before logging training status') parser.add_argument('--num-processes', type=int, default=2, metavar='N', - help='how many training processes to use (default: 2)') + help='how many training processes to use (default: %(default)s)') parser.add_argument('--cuda', action='store_true', default=False, help='enables CUDA training') parser.add_argument('--mps', action='store_true', default=False, diff --git a/mnist_rnn/main.py b/mnist_rnn/main.py index 2fa64c00d6..753579fa0b 100644 --- a/mnist_rnn/main.py +++ b/mnist_rnn/main.py @@ -82,15 +82,15 @@ def main(): # Training settings parser = argparse.ArgumentParser(description='PyTorch MNIST Example using RNN') parser.add_argument('--batch-size', type=int, default=64, metavar='N', - help='input batch size for training (default: 64)') + help='input batch size for training (default: %(default)s)') parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N', - help='input batch size for testing (default: 1000)') + help='input batch size for testing (default: %(default)s)') parser.add_argument('--epochs', type=int, default=14, metavar='N', - help='number of epochs to train (default: 14)') + help='number of epochs to train (default: %(default)s)') parser.add_argument('--lr', type=float, default=0.1, metavar='LR', - help='learning rate (default: 0.1)') + help='learning rate (default: %(default)s)') parser.add_argument('--gamma', type=float, default=0.7, metavar='M', - help='learning rate step gamma (default: 0.7)') + help='learning rate step gamma (default: %(default)s)') parser.add_argument('--cuda', action='store_true', default=False, help='enables CUDA training') parser.add_argument('--mps', action="store_true", default=False, @@ -98,7 +98,7 @@ def main(): 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)') + help='random seed (default: %(default)s)') 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, diff --git a/reinforcement_learning/actor_critic.py b/reinforcement_learning/actor_critic.py index c5a3ee6d79..1987d2cf98 100644 --- a/reinforcement_learning/actor_critic.py +++ b/reinforcement_learning/actor_critic.py @@ -14,13 +14,13 @@ parser = argparse.ArgumentParser(description='PyTorch actor-critic example') parser.add_argument('--gamma', type=float, default=0.99, metavar='G', - help='discount factor (default: 0.99)') + help='discount factor (default: %(default)s)') parser.add_argument('--seed', type=int, default=543, metavar='N', - help='random seed (default: 543)') + help='random seed (default: %(default)s)') parser.add_argument('--render', action='store_true', help='render the environment') parser.add_argument('--log-interval', type=int, default=10, metavar='N', - help='interval between training status logs (default: 10)') + help='interval between training status logs (default: %(default)s)') args = parser.parse_args() diff --git a/reinforcement_learning/reinforce.py b/reinforcement_learning/reinforce.py index 961598174c..7455551247 100644 --- a/reinforcement_learning/reinforce.py +++ b/reinforcement_learning/reinforce.py @@ -12,13 +12,13 @@ parser = argparse.ArgumentParser(description='PyTorch REINFORCE example') parser.add_argument('--gamma', type=float, default=0.99, metavar='G', - help='discount factor (default: 0.99)') + help='discount factor (default: %(default)s)') parser.add_argument('--seed', type=int, default=543, metavar='N', - help='random seed (default: 543)') + help='random seed (default: %(default)s)') parser.add_argument('--render', action='store_true', help='render the environment') parser.add_argument('--log-interval', type=int, default=10, metavar='N', - help='interval between training status logs (default: 10)') + help='interval between training status logs (default: %(default)s)') args = parser.parse_args() diff --git a/siamese_network/main.py b/siamese_network/main.py index 8f420a9b01..6fa87677f4 100644 --- a/siamese_network/main.py +++ b/siamese_network/main.py @@ -238,15 +238,15 @@ def main(): # Training settings parser = argparse.ArgumentParser(description='PyTorch Siamese network Example') parser.add_argument('--batch-size', type=int, default=64, metavar='N', - help='input batch size for training (default: 64)') + help='input batch size for training (default: %(default)s)') parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N', - help='input batch size for testing (default: 1000)') + help='input batch size for testing (default: %(default)s)') parser.add_argument('--epochs', type=int, default=14, metavar='N', - help='number of epochs to train (default: 14)') + help='number of epochs to train (default: %(default)s)') parser.add_argument('--lr', type=float, default=1.0, metavar='LR', - help='learning rate (default: 1.0)') + help='learning rate (default: %(default)s)') parser.add_argument('--gamma', type=float, default=0.7, metavar='M', - help='Learning rate step gamma (default: 0.7)') + help='Learning rate step gamma (default: %(default)s)') parser.add_argument('--no-cuda', action='store_true', default=False, help='disables CUDA training') parser.add_argument('--no-mps', action='store_true', default=False, @@ -254,7 +254,7 @@ def main(): 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)') + help='random seed (default: %(default)s)') 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, diff --git a/vae/main.py b/vae/main.py index d69833fbe0..23d619f2cd 100644 --- a/vae/main.py +++ b/vae/main.py @@ -10,15 +10,15 @@ parser = argparse.ArgumentParser(description='VAE MNIST Example') parser.add_argument('--batch-size', type=int, default=128, metavar='N', - help='input batch size for training (default: 128)') + help='input batch size for training (default: %(default)s)') parser.add_argument('--epochs', type=int, default=10, metavar='N', - help='number of epochs to train (default: 10)') + help='number of epochs to train (default: %(default)s)') 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') + help='disables macOS GPU training') parser.add_argument('--seed', type=int, default=1, metavar='S', - help='random seed (default: 1)') + help='random seed (default: %(default)s)') parser.add_argument('--log-interval', type=int, default=10, metavar='N', help='how many batches to wait before logging training status') args = parser.parse_args() diff --git a/word_language_model/generate.py b/word_language_model/generate.py index 13bd8abfcd..ba0f2dae73 100644 --- a/word_language_model/generate.py +++ b/word_language_model/generate.py @@ -24,7 +24,7 @@ parser.add_argument('--cuda', action='store_true', help='use CUDA') parser.add_argument('--mps', action='store_true', default=False, - help='enables macOS GPU training') + help='enables macOS GPU training') parser.add_argument('--temperature', type=float, default=1.0, help='temperature - higher will increase diversity') parser.add_argument('--log-interval', type=int, default=100, @@ -39,7 +39,7 @@ if torch.backends.mps.is_available(): if not args.mps: print("WARNING: You have mps device, to enable macOS GPU run with --mps.") - + use_mps = args.mps and torch.backends.mps.is_available() if args.cuda: device = torch.device("cuda") diff --git a/word_language_model/main.py b/word_language_model/main.py index 23bda03e73..c3a8d47f41 100644 --- a/word_language_model/main.py +++ b/word_language_model/main.py @@ -40,7 +40,7 @@ parser.add_argument('--cuda', action='store_true', default=False, help='use CUDA') parser.add_argument('--mps', action='store_true', default=False, - help='enables macOS GPU training') + help='enables macOS GPU training') parser.add_argument('--log-interval', type=int, default=200, metavar='N', help='report interval') parser.add_argument('--save', type=str, default='model.pt',