yuanbinliu / gann Goto Github PK
View Code? Open in Web Editor NEWMultiscale Graph Attention Neural Networks for Mapping Materials and Molecules
License: MIT License
Multiscale Graph Attention Neural Networks for Mapping Materials and Molecules
License: MIT License
I have download the dataset, but i can't find the opt-geometries.xyz. can you tell me where is the opt-geometries.xyz
I want to run the demo,but i can;t find where to import data
parser = argparse.ArgumentParser(
description='Crystal Graph Convolutional Neural Networks')
parser.add_argument('data_options', metavar='OPTIONS', nargs='+',
help='dataset options, started with the path to root dir, '
'then other options')
parser.add_argument('--disable-cuda', action='store_true',
help='Disable CUDA')
parser.add_argument('-j', '--workers', default=1, type=int, metavar='N',
help='number of data loading workers (default: 0)')
parser.add_argument('--epochs', default=30, type=int, metavar='N',
help='number of total epochs to run (default: 30)')
parser.add_argument('--start-epoch', default=20, type=int, metavar='N',
help='manual epoch number (useful on restarts)')
parser.add_argument('-b', '--batch-size', default=10, type=int,
metavar='N', help='mini-batch size (default: 256)')
parser.add_argument('--lr', '--learning-rate', default=0.01, type=float,
metavar='LR', help='initial learning rate (default: '
'0.01)')
parser.add_argument('--lr-milestones', default=[100], nargs='+', type=int,
metavar='N', help='milestones for scheduler (default: '
'[100])')
parser.add_argument('--momentum', default=0.9, type=float, metavar='M',
help='momentum')
parser.add_argument('--weight_decay', '--wd', default=5e-4, type=float,
metavar='W', help='weight decay (default: 0)')
parser.add_argument('--print-freq', '-p', default=10, type=int,
metavar='N', help='print frequency (default: 10)')
parser.add_argument('--resume', default='', type=str, metavar='PATH',
help='path to latest checkpoint (default: none)')
train_group = parser.add_mutually_exclusive_group()
train_group.add_argument('--train-ratio', default=0.8, type=float, metavar='N',
help='number of training data to be loaded (default none)')
train_group.add_argument('--train-size', default=None, type=int, metavar='N',
help='number of training data to be loaded (default none)')
valid_group = parser.add_mutually_exclusive_group()
valid_group.add_argument('--val-ratio', default=0.1, type=float, metavar='N',
help='percentage of validation data to be loaded (default '
'0.1)')
valid_group.add_argument('--val-size', default=None, type=int, metavar='N',
help='number of validation data to be loaded (default '
'1000)')
test_group = parser.add_mutually_exclusive_group()
test_group.add_argument('--test-ratio', default=0.1, type=float, metavar='N',
help='percentage of test data to be loaded (default 0.1)')
test_group.add_argument('--test-size', default=None, type=int, metavar='N',
help='number of test data to be loaded (default 1000)')
parser.add_argument('--optim', default='SGD', type=str, metavar='SGD',
help='choose an optimizer, SGD or Adam, (default: SGD)')
parser.add_argument('--atom-fea-len', default=64, type=int, metavar='N',
help='number of hidden atom features in conv layers')
parser.add_argument('--h-fea-len', default=128, type=int, metavar='N',
help='number of hidden features after pooling')
parser.add_argument('--disable-save-torch', action='store_true',
help='Do not save CIF PyTorch data as .pkl files')
parser.add_argument('--clean-torch', action='store_true',
help='Clean CIF PyTorch data .pkl files')
args = parser.parse_args(sys.argv[1:])
args.cuda = not args.disable_cuda and torch.cuda.is_available()
best_mae_error = 1e10
def main():
global args, best_mae_error
# load data
dataset = CIFData(*args.data_options,
disable_save_torch=args.disable_save_torch)
collate_fn = collate_pool
train_loader, val_loader, test_loader = get_train_val_test_loader(
dataset=dataset,
collate_fn=collate_fn,
batch_size=args.batch_size,
train_ratio=args.train_ratio,
num_workers=args.workers,
val_ratio=args.val_ratio,
test_ratio=args.test_ratio,
pin_memory=args.cuda,
train_size=args.train_size,
val_size=args.val_size,
test_size=args.test_size,
return_test=True)
thanks
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.