def __init__(self, batch_size, num_features, num_layers, J, dim_input, clip_grad_norm, logger):
self.logger = logger
self.clip_grad_norm = clip_grad_norm
self.batch_size = batch_size
self.J = J
self.Split = Split_GNN(batch_size, num_features, num_layers, J+2, dim_input=dim_input)
self.Tsp = GNN(num_features, num_layers, J+2, dim_input=dim_input)
self.Merge = GNN(num_features, num_layers, J+2, dim_input=dim_input)
self.optimizer_split = optim.RMSprop(self.Split.parameters())
self.optimizer_tsp = optim.Adamax(self.Tsp.parameters(), lr=1e-3)
self.optimizer_merge = optim.Adamax(self.Merge.parameters(), lr=1e-3)
self.test_gens = []
self.test_gens_labels = []
def main():
# Training settings
parser = argparse.ArgumentParser(description='PyTorch implementation of pre-training of graph neural networks')
parser.add_argument('--device', type=int, default=0,
help='which gpu to use if any (default: 0)')
parser.add_argument('--batch_size', type=int, default=256,
help='input batch size for training (default: 256)')
parser.add_argument('--epochs', type=int, default=100,
help='number of epochs to train (default: 100)')
parser.add_argument('--lr', type=float, default=0.001,
help='learning rate (default: 0.001)')
parser.add_argument('--decay', type=float, default=0,
help='weight decay (default: 0)')
parser.add_argument('--num_layer', type=int, default=5,
help='number of GNN message passing layers (default: 5).')
parser.add_argument('--emb_dim', type=int, default=300,
help='embedding dimensions (default: 300)')
parser.add_argument('--dropout_ratio', type=float, default=0,
help='dropout ratio (default: 0)')
parser.add_argument('--JK', type=str, default="last",
help='how the node features across layers are combined. last, sum, max or concat')
parser.add_argument('--dataset', type=str, default = 'zinc_standard_agent', help='root directory of dataset. For now, only classification.')
parser.add_argument('--output_model_file', type = str, default = '', help='filename to output the pre-trained model')
parser.add_argument('--gnn_type', type=str, default="gin")
parser.add_argument('--num_workers', type=int, default = 8, help='number of workers for dataset loading')
args = parser.parse_args()
torch.manual_seed(0)
np.random.seed(0)
device = torch.device("cuda:" + str(args.device)) if torch.cuda.is_available() else torch.device("cpu")
if torch.cuda.is_available():
torch.cuda.manual_seed_all(0)
#set up dataset
dataset = MoleculeDataset("dataset/" + args.dataset, dataset=args.dataset, transform = NegativeEdge())
print(dataset[0])
loader = DataLoaderAE(dataset, batch_size=args.batch_size, shuffle=True, num_workers = args.num_workers)
#set up model
model = GNN(args.num_layer, args.emb_dim, JK = args.JK, drop_ratio = args.dropout_ratio, gnn_type = args.gnn_type)
model.to(device)
#set up optimizer
optimizer = optim.Adam(model.parameters(), lr=args.lr, weight_decay=args.decay)
print(optimizer)
for epoch in range(1, args.epochs+1):
print("====epoch " + str(epoch))
train_acc, train_loss = train(args, model, device, loader, optimizer)
print(train_acc)
print(train_loss)
if not args.output_model_file == "":
torch.save(model.state_dict(), args.output_model_file + ".pth")
def set_model_and_load_model(args, device, load_epoch = 2):
#set up models, one for pre-training and one for context embeddings
model = GNN(args.num_layer, args.emb_dim, JK = args.JK, drop_ratio = args.dropout_ratio, gnn_type = args.gnn_type).to(device)
linear_pred_atoms = Linear(args.emb_dim, 119, device)
linear_pred_bonds = Linear(args.emb_dim, 4, device)
model.load_state_dict(torch.load(args.output_model_file + "_epoch" + str(load_epoch) + ".pth"))
linear_pred_atoms.load_state_dict(torch.load(args.output_model_file + "_epoch_" + str(load_epoch) + "_linear_atom.pth"))
linear_pred_bonds.load_state_dict(torch.load(args.output_model_file + "_epoch_" + str(load_epoch) + "_linear_bond.pth"))
return model, linear_pred_atoms, linear_pred_bonds
def get_accuracy(params):
gnn_graph = utils.build_gnn_graph(dataset, params)
model = GNN(gnn_graph).to(device)
setting = utils.from_json("json/setting.json")[args.dataset]
optimizer = torch.optim.Adam(model.parameters(),
lr=setting["learning_rate"],
weight_decay=setting["weight_decay"])
fitter = Fitter(model, data, optimizer)
history = fitter.run(verbose=args.verbose)
reward = max(history.val.acc)
return reward
def evaluate(params, dataset, device='cuda:0', val_test='test'):
data = Dataset(dataset)
gnn_graph = utils.build_gnn_graph(data, params)
model = GNN(gnn_graph).to(device)
# logger.info(dataset)
setting = utils.from_json("json/setting.json")[dataset]
optimizer = torch.optim.Adam(model.parameters(),
lr=setting["learning_rate"],
weight_decay=setting["weight_decay"])
fitter = Fitter(model, data[0].to(device), optimizer)
history = fitter.run(val_test=val_test, verbose=False)
return max(history.val.acc)
def __init__(self, params):
self.p = params
self.device = torch.device('cpu' if self.p.gpu ==
-1 else f'cuda:{params.gpu}')
#self.device = torch.device('cpu')
self.data, self.num_classes, self.num_genes, self.id2label = load(
self.p)
#self.data['human']['hot_mat'] = torch.rand(self.data['human']['hot_mat'].shape)
#self.data['mouse']['hot_mat'] = torch.rand(self.data['mouse']['hot_mat'].shape)
#print(self.data['shared_gene_tensor'])
#print(torch.min(self.data['shared_gene_tensor']))
#print(torch.max(self.data['shared_gene_tensor']))
#print(len(self.data['shared_gene_tensor']))
#print(self.data['human_gene_tensor'])
#print(len(self.data['human_gene_tensor']))
#print(self.data['mouse_gene_tensor'])
#print(len(self.data['mouse_gene_tensor']))
self.model = GNN(in_feats=self.p.dense_dim,
shared_gene=self.data['shared_gene_tensor'],
human_gene=self.data['human_gene_tensor'],
mouse_gene=self.data['mouse_gene_tensor'],
n_hidden=self.p.hidden_dim,
n_class=self.num_classes,
n_layer=self.p.n_layers,
activation=F.relu,
dropout=self.p.dropout,
weighted=self.p.weighted,
device=self.device,
gene_num=self.num_genes).to(self.device)
total_trainable_params = sum(p.numel()
for p in self.model.parameters()
if p.requires_grad)
print(f'{total_trainable_params:,} training parameters.')
self.optimizer = torch.optim.Adam(self.model.parameters(),
lr=params.lr,
weight_decay=self.p.weight_decay)
self.domain_criterion = torch.nn.CrossEntropyLoss()
if self.p.num_neighbors == 0:
self.num_neighbors = max([
self.data['mouse']['graph'].number_of_nodes(),
self.data['human']['graph'].number_of_nodes()
])
else:
self.num_neighbors = self.p.num_neighbors
self.data_loader = self.get_dataloader()
def main():
# Training settings
parser = argparse.ArgumentParser(
description=
'PyTorch implementation of pre-training of graph neural networks')
parser.add_argument('--device',
type=int,
default=0,
help='which gpu to use if any (default: 0)')
parser.add_argument('--batch_size',
type=int,
default=256,
help='input batch size for training (default: 256)')
parser.add_argument('--epochs',
type=int,
default=100,
help='number of epochs to train (default: 100)')
parser.add_argument('--lr',
type=float,
default=0.001,
help='learning rate (default: 0.001)')
parser.add_argument('--decay',
type=float,
default=0,
help='weight decay (default: 0)')
parser.add_argument(
'--num_layer',
type=int,
default=5,
help='number of GNN message passing layers (default: 5).')
parser.add_argument('--emb_dim',
type=int,
default=300,
help='embedding dimensions (default: 300)')
parser.add_argument('--dropout_ratio',
type=float,
default=0,
help='dropout ratio (default: 0)')
parser.add_argument('--mask_rate',
type=float,
default=0.15,
help='dropout ratio (default: 0.15)')
parser.add_argument(
'--mask_edge',
type=int,
default=0,
help='whether to mask edges or not together with atoms')
parser.add_argument(
'--JK',
type=str,
default="last",
help=
'how the node features are combined across layers. last, sum, max or concat'
)
parser.add_argument('--dataset',
type=str,
default='zinc_standard_agent',
help='root directory of dataset for pretraining')
parser.add_argument('--output_model_file',
type=str,
default='',
help='filename to output the model')
parser.add_argument('--gnn_type', type=str, default="gin")
parser.add_argument('--seed',
type=int,
default=0,
help="Seed for splitting dataset.")
parser.add_argument('--num_workers',
type=int,
default=8,
help='number of workers for dataset loading')
args = parser.parse_args()
torch.manual_seed(0)
np.random.seed(0)
device = torch.device(
"cuda:" +
str(args.device)) if torch.cuda.is_available() else torch.device("cpu")
if torch.cuda.is_available():
torch.cuda.manual_seed_all(0)
print("num layer: %d mask rate: %f mask edge: %d" %
(args.num_layer, args.mask_rate, args.mask_edge))
#set up dataset and transform function.
dataset = MoleculeDataset("dataset/" + args.dataset,
dataset=args.dataset,
transform=MaskAtom(num_atom_type=119,
num_edge_type=5,
mask_rate=args.mask_rate,
mask_edge=args.mask_edge))
loader = DataLoaderMasking(dataset,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers)
#set up models, one for pre-training and one for context embeddings
model = GNN(args.num_layer,
args.emb_dim,
JK=args.JK,
drop_ratio=args.dropout_ratio,
gnn_type=args.gnn_type).to(device)
linear_pred_atoms = torch.nn.Linear(args.emb_dim, 119).to(device)
linear_pred_bonds = torch.nn.Linear(args.emb_dim, 4).to(device)
model_list = [model, linear_pred_atoms, linear_pred_bonds]
#set up optimizers
optimizer_model = optim.Adam(model.parameters(),
lr=args.lr,
weight_decay=args.decay)
optimizer_linear_pred_atoms = optim.Adam(linear_pred_atoms.parameters(),
lr=args.lr,
weight_decay=args.decay)
optimizer_linear_pred_bonds = optim.Adam(linear_pred_bonds.parameters(),
lr=args.lr,
weight_decay=args.decay)
optimizer_list = [
optimizer_model, optimizer_linear_pred_atoms,
optimizer_linear_pred_bonds
]
for epoch in range(1, args.epochs + 1):
print("====epoch " + str(epoch))
train_loss, train_acc_atom, train_acc_bond = train(
args, model_list, loader, optimizer_list, device)
print(train_loss, train_acc_atom, train_acc_bond)
if not args.output_model_file == "":
torch.save(model.state_dict(), args.output_model_file + ".pth")
torch.manual_seed(tt.arg.seed)
torch.cuda.manual_seed_all(tt.arg.seed)
random.seed(tt.arg.seed)
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
tt.arg.log_dir_user = tt.arg.log_dir if tt.arg.log_dir_user is None else tt.arg.log_dir_user
tt.arg.log_dir = tt.arg.log_dir_user
if not os.path.exists('asset/checkpoints'):
os.makedirs('asset/checkpoints')
if not os.path.exists('asset/checkpoints/' + tt.arg.experiment):
os.makedirs('asset/checkpoints/' + tt.arg.experiment)
enc_module = EmbeddingImagenet(emb_size=tt.arg.emb_size)
gnn_module = GNN(d_in=enc_module.emb_size)
if tt.arg.dataset == 'mini':
train_loader = MiniImagenetLoader(root=tt.arg.dataset_root,
partition='train')
valid_loader = MiniImagenetLoader(root=tt.arg.dataset_root,
partition='val')
elif tt.arg.dataset == 'cub':
train_loader = CUBLoader(root=tt.arg.dataset_root, partition='train')
valid_loader = CUBLoader(root=tt.arg.dataset_root, partition='val')
else:
print('Unknown dataset!')
data_loader = {'train': train_loader, 'val': valid_loader}
# create trainer
def main():
# Training settings
parser = argparse.ArgumentParser(
description=
'PyTorch implementation of pre-training of graph neural networks')
parser.add_argument('--device',
type=int,
default=0,
help='which gpu to use if any (default: 0)')
parser.add_argument('--batch_size',
type=int,
default=32,
help='input batch size for training (default: 256)')
parser.add_argument('--epochs',
type=int,
default=100,
help='number of epochs to train (default: 100)')
parser.add_argument('--lr',
type=float,
default=0.001,
help='learning rate (default: 0.001)')
parser.add_argument('--decay',
type=float,
default=0,
help='weight decay (default: 0)')
parser.add_argument(
'--num_layer',
type=int,
default=5,
help='number of GNN message passing layers (default: 5).')
parser.add_argument('--emb_dim',
type=int,
default=300,
help='embedding dimensions (default: 300)')
parser.add_argument('--dropout_ratio',
type=float,
default=0,
help='dropout ratio (default: 0)')
parser.add_argument('--mask_rate',
type=float,
default=0.15,
help='dropout ratio (default: 0.15)')
parser.add_argument(
'--JK',
type=str,
default="last",
help=
'how the node features are combined across layers. last, sum, max or concat'
)
parser.add_argument('--gnn_type', type=str, default="gsan")
parser.add_argument('--model_file',
type=str,
default='',
help='filename to output the model')
parser.add_argument('--seed',
type=int,
default=0,
help="Seed for splitting dataset.")
parser.add_argument('--num_workers',
type=int,
default=8,
help='number of workers for dataset loading')
args = parser.parse_args()
torch.manual_seed(0)
np.random.seed(0)
device = torch.device(
"cuda:" +
str(args.device)) if torch.cuda.is_available() else torch.device("cpu")
if torch.cuda.is_available():
torch.cuda.manual_seed_all(0)
print("num layer: %d mask rate: %f" % (args.num_layer, args.mask_rate))
#set up dataset
root_unsupervised = 'dataset/unsupervised'
dataset = BioDataset(root_unsupervised,
data_type='unsupervised',
transform=MaskEdge(mask_rate=args.mask_rate))
print(dataset)
loader = DataLoaderMasking(dataset,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers)
#set up models, one for pre-training and one for context embeddings
model = GNN(args.num_layer,
args.emb_dim,
JK=args.JK,
drop_ratio=args.dropout_ratio,
gnn_type=args.gnn_type).to(device)
#Linear layer for classifying different edge types
linear_pred_edges = torch.nn.Linear(args.emb_dim, 7).to(device)
model_list = [model, linear_pred_edges]
#set up optimizers
optimizer_model = optim.Adam(model.parameters(),
lr=args.lr,
weight_decay=args.decay)
optimizer_linear_pred_edges = optim.Adam(linear_pred_edges.parameters(),
lr=args.lr,
weight_decay=args.decay)
optimizer_list = [optimizer_model, optimizer_linear_pred_edges]
for epoch in range(1, args.epochs + 1):
print("====epoch " + str(epoch))
train_loss, train_acc = train(args, model_list, loader, optimizer_list,
device)
print("loss :", train_loss, "accuracy :", train_acc)
if not args.model_file == "":
torch.save(model.state_dict(), args.model_file + ".pth")
import dgl
import torch
import numpy as np
from model import GNN, EMB_SIZE
device = 'cuda'
model = GNN(5, device).to(device)
# build a fake graph. Copying from other code
g = dgl.DGLGraph()
# add 34 nodes into the graph; nodes are labeled from 0~33
g.add_nodes(34)
# all 78 edges as a list of tuples
edge_list = [(1, 0), (2, 0), (2, 1), (3, 0), (3, 1), (3, 2), (4, 0), (5, 0),
(6, 0), (6, 4), (6, 5), (7, 0), (7, 1), (7, 2), (7, 3), (8, 0),
(8, 2), (9, 2), (10, 0), (10, 4), (10, 5), (11, 0), (12, 0),
(12, 3), (13, 0), (13, 1), (13, 2), (13, 3), (16, 5), (16, 6),
(17, 0), (17, 1), (19, 0), (19, 1), (21, 0), (21, 1), (25, 23),
(25, 24), (27, 2),
(27, 23), (27, 24), (28, 2), (29, 23), (29, 26), (30, 1), (30, 8),
(31, 0), (31, 24), (31, 25), (31, 28), (32, 2), (32, 8), (32, 14),
(32, 15), (32, 18), (32, 20), (32, 22), (32, 23), (32, 29),
(32, 30), (32, 31), (33, 8), (33, 9), (33, 13), (33, 14),
(33, 15), (33, 18), (33, 19), (33, 20), (33, 22), (33, 23),
(33, 26), (33, 27), (33, 28), (33, 29), (33, 30), (33, 31),
(33, 32)]
# add edges two lists of nodes: src and dst
src, dst = tuple(zip(*edge_list))
g.add_edges(src, dst, {'l_e': torch.ones(78).to(device)})
g.add_edges(dst, src, {'l_e': torch.zeros(78).to(device)})
list_acc.append(acc)
print(
f"Top {k}-Hit Accuracy: {np.mean(np.array(list_acc))} and std: {np.std(np.array(list_acc))}"
)
print(
f"Kendall-Tau scores is: {np.mean(np.array(list_kt))} and std: {np.std(np.array(list_kt))}"
)
#Model parameters
hidden = 20
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(f"Device selected: {device}")
model = GNN(ninput=model_size, nhid=hidden, dropout=0.6)
model.to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=0.0005)
num_epoch = 10
print("\nStaring Training")
print(f"Total Number of epoches: {num_epoch}")
for e in range(num_epoch):
print(f"Epoch number: {e+1}/{num_epochs}")
train(list_adj_train, list_adj_t_train, list_num_node_train, bc_mat_train)
with torch.no_grad():
test(list_adj_test,
list_adj_t_test,
list_num_node_test,
bc_mat_test,
def main():
"""
"""
args = parser.parse_args()
if args.cuda:
device = torch.device("cuda:0")
else:
device = torch.device("cpu")
data_dir = tools.select_data_dir()
trainset = Sudoku(data_dir, train=True)
testset = Sudoku(data_dir, train=False)
trainloader = DataLoader(trainset, batch_size=args.batch_size, collate_fn=collate)
testloader = DataLoader(testset, batch_size=args.batch_size, collate_fn=collate)
# Create network
gnn = GNN(device)
if not args.skip_training:
optimizer = torch.optim.Adam(gnn.parameters(), lr=args.learning_rate)
loss_method = nn.CrossEntropyLoss(reduction="mean")
for epoch in range(args.n_epochs):
for i, data in enumerate(trainloader, 0):
inputs, targets, src_ids, dst_ids = data
inputs, targets = inputs.to(device), targets.to(device)
src_ids, dst_ids = src_ids.to(device), dst_ids.to(device)
optimizer.zero_grad()
gnn.zero_grad()
output = gnn.forward(inputs, src_ids, dst_ids)
output = output.to(device)
output = output.view(-1, output.shape[2])
targets = targets.repeat(7, 1)
targets = targets.view(-1)
loss = loss_method(output, targets)
loss.backward()
optimizer.step()
fraction = fraction_of_solved_puzzles(gnn, testloader, device)
print("Train Epoch {}: Loss: {:.6f} Fraction: {}".format(epoch + 1, loss.item(), fraction))
tools.save_model(gnn, "7_gnn.pth")
else:
gnn = GNN(device)
tools.load_model(gnn, "7_gnn.pth", device)
# Evaluate the trained model
# Get graph iterations for some test puzzles
with torch.no_grad():
inputs, targets, src_ids, dst_ids = iter(testloader).next()
inputs, targets = inputs.to(device), targets.to(device)
src_ids, dst_ids = src_ids.to(device), dst_ids.to(device)
batch_size = inputs.size(0) // 81
outputs = gnn(inputs, src_ids, dst_ids).to(device) # [n_iters, n_nodes, 9]
solution = outputs.view(gnn.n_iters, batch_size, 9, 9, 9).to(device)
final_solution = solution[-1].argmax(dim=3).to(device)
print("Solved puzzles in the current mini-batch:")
print((final_solution.view(-1, 81) == targets.view(batch_size, 81)).all(dim=1))
# Visualize graph iteration for one of the puzzles
ix = 0
for i in range(gnn.n_iters):
tools.draw_sudoku(solution[i, 0], logits=True)
fraction_solved = fraction_of_solved_puzzles(gnn, testloader,device)
print(f"Accuracy {fraction_solved}")
def main():
# Training settings
parser = argparse.ArgumentParser(description='PyTorch implementation of pre-training of graph neural networks')
parser.add_argument('--device', type=int, default=0,
help='which gpu to use if any (default: 0)')
parser.add_argument('--batch_size', type=int, default=256,
help='input batch size for training (default: 256)')
parser.add_argument('--epochs', type=int, default=100,
help='number of epochs to train (default: 100)')
parser.add_argument('--lr', type=float, default=0.001,
help='learning rate (default: 0.001)')
parser.add_argument('--decay', type=float, default=0,
help='weight decay (default: 0)')
parser.add_argument('--num_layer', type=int, default=5,
help='number of GNN message passing layers (default: 5).')
parser.add_argument('--emb_dim', type=int, default=300,
help='embedding dimensions (default: 300)')
parser.add_argument('--dropout_ratio', type=float, default=0,
help='dropout ratio (default: 0)')
parser.add_argument('--JK', type=str, default="last",
help='how the node features across layers are combined. last, sum, max or concat')
parser.add_argument('--gnn_type', type=str, default="gin")
parser.add_argument('--model_file', type = str, default = '', help='filename to output the pre-trained model')
parser.add_argument('--seed', type=int, default=0, help = "Seed for splitting dataset.")
parser.add_argument('--num_workers', type=int, default = 4, help='number of workers for dataset loading')
args = parser.parse_args()
torch.manual_seed(0)
np.random.seed(0)
device = torch.device("cuda:" + str(args.device)) if torch.cuda.is_available() else torch.device("cpu")
if torch.cuda.is_available():
torch.cuda.manual_seed_all(0)
#set up dataset
root_unsupervised = 'dataset/unsupervised'
dataset = BioDataset(root_unsupervised, data_type='unsupervised')
print(dataset)
loader = DataLoader(dataset, batch_size=args.batch_size, shuffle=True, num_workers = args.num_workers)
#set up model
gnn = GNN(args.num_layer, args.emb_dim, JK = args.JK, drop_ratio = args.dropout_ratio, gnn_type = args.gnn_type)
discriminator = Discriminator(args.emb_dim)
model = Infomax(gnn, discriminator)
model.to(device)
#set up optimizer
optimizer = optim.Adam(model.parameters(), lr=args.lr, weight_decay=args.decay)
print(optimizer)
for epoch in range(1, args.epochs+1):
print("====epoch " + str(epoch))
train_acc, train_loss = train(args, model, device, loader, optimizer)
print(train_acc)
print(train_loss)
if not args.model_file == "":
torch.save(model.gnn.state_dict(), args.model_file + ".pth")
def __init__(self,
num_gpus=1,
max_size=29,
build_backprop=True,
node_features=7,
edge_features=3,
layers=2,
hidden_size=128,
iterations=3,
input_data=None):
""" Initialize a Graph-to-coordinates network """
# tf.set_random_seed(42)
# AV: the input features (and size) in graph
self.dims = {
"max": max_size,
"nodes": node_features,
"edges": edge_features
}
# AV: hyperparams: node + edge layers; node + edge hidden size; iterations
self.hyperparams = {
"node_layers": layers,
"node_hidden": hidden_size,
"edge_layers": layers,
"edge_hidden": hidden_size,
"iterations": iterations
}
with tf.variable_scope("Inputs"):
if not input_data:
# Placeholders
placeholders = {}
placeholders["nodes"] = tf.placeholder(
tf.float32, [None, self.dims["max"], self.dims["nodes"]],
name="Nodes")
placeholders["edges"] = tf.placeholder(tf.float32, [
None, self.dims["max"], self.dims["max"],
self.dims["edges"]
],
name="Edges")
placeholders["sizes"] = tf.placeholder(tf.int32, [None],
name="Sizes")
placeholders["coordinates"] = tf.placeholder(
tf.float32, [None, self.dims["max"], 3],
name="Coordinates")
self.placeholders = placeholders
else:
self.placeholders = input_data
# Build graph neural network
V, E, mask_V, mask_E = GNN.GNN(
self.placeholders["nodes"],
self.placeholders["edges"],
self.placeholders["sizes"],
iterations=self.hyperparams["iterations"],
node_layers=self.hyperparams["node_layers"],
node_hidden=self.hyperparams["node_hidden"],
edge_layers=self.hyperparams["edge_layers"],
edge_hidden=self.hyperparams["edge_hidden"])
self.tensors = {"V": V, "E": E}
mask_D = tf.squeeze(
mask_E, 3) # AV: squeeze the edge mask to get the distance mask?
self.masks = {"V": mask_V, "E": mask_E, "D": mask_D}
tf.summary.image("EdgeOut",
E[:, :, :, :3]) # AV: why using images here?
# Build featurization
with tf.variable_scope("DistancePredictions"):
# AV: edge GNN MLP: takes initial edges and builds mlp
E = GNN.MLP(E, self.hyperparams["edge_layers"],
self.hyperparams["edge_hidden"])
self.tensors["embedding"] = tf.reduce_sum(
E, axis=[1, 2]) # compress mlp into embedding
# Make unc. distance and weight predictions
E_out = tf.layers.dense(E, 2, use_bias=True,
name="edge_out") # AV: ?
# Symmetrize
E_out = E_out + tf.transpose(
E_out, [0, 2, 1, 3]) # permuting on i,j # AV: ?
# Distance matrix prediction
D_init = tf.get_variable("D_init", (),
initializer=tf.constant_initializer([4.]))
# Enforce positivity
D = tf.nn.softplus(D_init + E_out[:, :, :, 0])
# Enforce self-distance = 0
D = self.masks["D"] * tf.linalg.set_diag(
D, tf.zeros_like(tf.squeeze(self.masks["V"], 2)))
self.tensors["D_init"] = D
tf.summary.image("DistancePred", tf.expand_dims(D, 3))
# Weights prediction
# W = tf.nn.sigmoid(E_out[:,:,:,1])
W = tf.nn.softplus(E_out[:, :, :, 1])
self.tensors["W"] = W
tf.summary.image("W", tf.expand_dims(W, 3))
self.debug_op = tf.add_check_numerics_ops()
with tf.variable_scope("Reconstruct"):
# B = self.distance_to_gram(D, self.masks["D"])
# tf.summary.image("B", tf.expand_dims(B,3))
# X = self.low_rank_approx(B)
# X = self.low_rank_approx_weighted(B, W)
# X = self.low_rank_approx_weighted(B, W)
# Minimize the objective with unrolled gradient descent
X = self.dist_nlsq(D, W, self.masks["D"])
self.tensors["X"] = X
with tf.variable_scope("Loss"):
# RMSD Loss
self.loss, self.tensors["X"] = self.rmsd(
X, self.placeholders["coordinates"], self.masks["V"])
tf.summary.scalar("LossRMSD", self.loss)
# Difference of distances
D_model = self.masks["D"] * self.distances(X)
D_target = self.masks["D"] * self.distances(
self.placeholders["coordinates"])
tf.summary.image("DistModel", tf.expand_dims(D_model, 3))
tf.summary.image("DistTarget", tf.expand_dims(D_target, 3))
tf.summary.histogram("DistModel", D_model)
tf.summary.histogram("DistTarget", D_target)
self.loss_distance_all = self.masks["D"] * tf.abs(D_model -
D_target)
self.loss_distance = tf.reduce_sum(
self.loss_distance_all) / tf.reduce_sum(self.masks["D"])
tf.summary.scalar("LossDistance", self.loss_distance)
# self.debug_op = tf.add_check_numerics_ops()
# use Adam optimiser
with tf.variable_scope("Optimization"):
opt = tf.train.AdamOptimizer(learning_rate=0.0001)
gvs = opt.compute_gradients(
self.loss_distance
) # gvs is list of (gradient, variable) pairs
gvs_clipped, global_norm = self.clip_gradients(gvs)
self.train_op = tf.cond(
tf.debugging.is_finite(
global_norm), # if global norm is finite
lambda: opt.apply_gradients(gvs_clipped), # apply gradients
lambda: tf.no_op() # otherwise do nothing
)
# self.debug_op = tf.add_check_numerics_ops()
return
content_image3 = batch['content2'].to(device)
with torch.no_grad():
start = time.time()
Style4_1 = enc_4(enc_3(enc_2(enc_1(style))))
Style5_1 = enc_5(Style4_1)
Content4_1_1 = enc_4(enc_3(enc_2(enc_1(content_image1))))
Content4_1_2 = enc_4(enc_3(enc_2(enc_1(content_image2))))
Content4_1_3 = enc_4(enc_3(enc_2(enc_1(content_image3))))
Content5_1_1 = enc_5(Content4_1_1)
Content5_1_2 = enc_5(Content4_1_2)
Content5_1_3 = enc_5(Content4_1_3)
Content4_1_1, _, _ = GNN(Content4_1_1, Content4_1_2, Content4_1_3)
Content5_1_1, _, _ = GNN_2(Content5_1_1, Content5_1_2, Content5_1_3)
Stylised = transform(Content4_1_1, Style4_1, Content5_1_1, Style5_1)
content = decoder(Stylised)
end = time.time()
content.clamp(0, 255)
content = content.cpu()
content = content[0]
content = content.transpose(1, 2)
content = content.transpose(0, 2)
content = content.numpy() * 255
output_value = np.clip(content, 0, 255).astype(np.uint8)
output_value = cv.cvtColor(output_value, cv.COLOR_RGB2BGR)
def main():
arg_bool = lambda x: x.lower() in ['true', 't', '1']
parser = argparse.ArgumentParser(description='Point Cloud Registration')
parser.add_argument('--exp_name',
type=str,
default='exp',
metavar='N',
help='Name of the experiment')
parser.add_argument('--num_iter',
type=int,
default=3,
metavar='N',
help='Number of iteration inside the network')
parser.add_argument('--emb_nn',
type=str,
default='GNN',
metavar='N',
help='Feature extraction method. [GNN, FPFH]')
parser.add_argument(
'--emb_dims',
type=int,
default=64,
metavar='N',
help='Dimension of embeddings. Must be 33 if emb_nn == FPFH')
parser.add_argument('--batch_size',
type=int,
default=16,
metavar='batch_size',
help='Size of batch)')
parser.add_argument('--test_batch_size',
type=int,
default=16,
metavar='batch_size',
help='Size of batch)')
parser.add_argument('--epochs',
type=int,
default=40,
metavar='N',
help='number of episode to train ')
parser.add_argument('--unseen',
type=arg_bool,
default='False',
help='Test on unseen categories')
parser.add_argument('--gaussian_noise',
type=arg_bool,
default='False',
help='Wheter to add gaussian noise')
parser.add_argument(
'--alpha',
type=float,
default=0.75,
metavar='N',
help='Fraction of points when sampling partial point cloud')
parser.add_argument('--factor',
type=float,
default=4,
metavar='N',
help='Divided factor for rotations')
args = parser.parse_args()
print(args)
##### make checkpoint directory and backup #####
if not os.path.exists('checkpoints'):
os.makedirs('checkpoints')
if not os.path.exists('checkpoints/' + args.exp_name):
os.makedirs('checkpoints/' + args.exp_name)
if not os.path.exists('checkpoints/' + args.exp_name + '/' + 'models'):
os.makedirs('checkpoints/' + args.exp_name + '/' + 'models')
os.system('cp main.py checkpoints' + '/' + args.exp_name + '/' +
'main.py.backup')
os.system('cp model.py checkpoints' + '/' + args.exp_name + '/' +
'model.py.backup')
os.system('cp data.py checkpoints' + '/' + args.exp_name + '/' +
'data.py.backup')
##### make checkpoint directory and backup #####
##### load data #####
train_loader = DataLoader(ModelNet40(partition='train',
alpha=args.alpha,
gaussian_noise=args.gaussian_noise,
unseen=args.unseen,
factor=args.factor),
batch_size=args.batch_size,
shuffle=True,
drop_last=True,
num_workers=8)
test_loader = DataLoader(ModelNet40(partition='test',
alpha=args.alpha,
gaussian_noise=args.gaussian_noise,
unseen=args.unseen,
factor=args.factor),
batch_size=args.test_batch_size,
shuffle=False,
drop_last=False,
num_workers=8)
##### load data #####
##### load model #####
if args.emb_nn == 'GNN':
net = IDAM(GNN(args.emb_dims), args).cuda()
elif args.emb_nn == 'FPFH':
args.emb_dims = 33
net = IDAM(FPFH(), args).cuda()
##### load model #####
##### train #####
train(args, net, train_loader, test_loader)
def main():
# Training settings
parser = argparse.ArgumentParser(
description=
'PyTorch implementation of pre-training of graph neural networks')
parser.add_argument('--device',
type=int,
default=0,
help='which gpu to use if any (default: 0)')
parser.add_argument('--batch_size',
type=int,
default=2,
help='input batch size for training (default: 256)')
parser.add_argument('--epochs',
type=int,
default=100,
help='number of epochs to train (default: 100)')
parser.add_argument('--lr',
type=float,
default=0.001,
help='learning rate (default: 0.001)')
parser.add_argument('--decay',
type=float,
default=0,
help='weight decay (default: 0)')
parser.add_argument(
'--num_layer',
type=int,
default=5,
help='number of GNN message passing layers (default: 5).')
parser.add_argument('--l1', type=int, default=1, help='l1 (default: 1).')
parser.add_argument('--center',
type=int,
default=0,
help='center (default: 0).')
parser.add_argument('--emb_dim',
type=int,
default=300,
help='embedding dimensions (default: 300)')
parser.add_argument('--dropout_ratio',
type=float,
default=0,
help='dropout ratio (default: 0)')
parser.add_argument(
'--neg_samples',
type=int,
default=1,
help='number of negative contexts per positive context (default: 1)')
parser.add_argument(
'--JK',
type=str,
default="last",
help=
'how the node features are combined across layers. last, sum, max or concat'
)
parser.add_argument('--context_pooling',
type=str,
default="mean",
help='how the contexts are pooled (sum, mean, or max)')
parser.add_argument('--gnn_type', type=str, default="gat")
parser.add_argument('--mode',
type=str,
default="cbow",
help="cbow or skipgram")
parser.add_argument('--model_file',
type=str,
default='',
help='filename to output the model')
parser.add_argument('--num_workers',
type=int,
default=4,
help='number of workers for dataset loading')
args = parser.parse_args()
torch.manual_seed(0)
np.random.seed(0)
device = torch.device(
"cuda:" +
str(args.device)) if torch.cuda.is_available() else torch.device("cpu")
if torch.cuda.is_available():
torch.cuda.manual_seed_all(0)
print(args.mode)
#set up dataset
root_unsupervised = 'dataset/unsupervised'
dataset = BioDataset(root_unsupervised,
data_type='unsupervised',
transform=ExtractSubstructureContextPair(
l1=args.l1, center=args.center))
print(dataset[0], "\n", dataset[1], "\n", len(dataset))
print("l1: " + str(args.l1))
print("center: " + str(args.center))
loader = DataLoaderSubstructContext(dataset,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers)
#print(dataset[0])
#set up models, one for pre-training and one for context embeddings
model_substruct = GNN(args.num_layer,
args.emb_dim,
JK=args.JK,
drop_ratio=args.dropout_ratio,
gnn_type=args.gnn_type).to(device)
model_context = GNN(3,
args.emb_dim,
JK=args.JK,
drop_ratio=args.dropout_ratio,
gnn_type=args.gnn_type).to(device)
#set up optimizer for the two GNNs
optimizer_substruct = optim.Adam(model_substruct.parameters(),
lr=args.lr,
weight_decay=args.decay)
optimizer_context = optim.Adam(model_context.parameters(),
lr=args.lr,
weight_decay=args.decay)
for epoch in range(1, args.epochs + 1):
print("====epoch " + str(epoch))
train_loss, train_acc = train(args, model_substruct, model_context,
loader, optimizer_substruct,
optimizer_context, device)
print(train_loss, train_acc)
if not args.model_file == "":
torch.save(model_substruct.state_dict(), args.model_file + ".pth")
from pytorch_lightning import LightningModule, Trainer, TrainResult, seed_everything
from pytorch_lightning.loggers.csv_logs import CSVLogger
from data import Load_Dataset
from model import GNN
import argparse
parser = argparse.ArgumentParser()
parser.add_argument("Batch_Size", type=int)
parser.add_argument("Max_Epoch", type=int)
Args = parser.parse_args()
Epochs_Max = Args.Max_Epoch
Batch_Size = Args.Batch_Size
seed_everything(42)
Logger = CSVLogger("logs",
name="PPI_SAGEConv",
version=str(Batch_Size) + "_" + str(Epochs_Max))
Mod = GNN(Batch_Size, 50, 500, 200, 121)
trainer = Trainer(logger=Logger, max_epochs=Epochs_Max)
trainer.fit(Mod)
def main():
# Training settings
parser = argparse.ArgumentParser(
description=
"PyTorch implementation of pre-training of graph neural networks")
parser.add_argument("--device",
type=int,
default=0,
help="which gpu to use if any (default: 0)")
parser.add_argument(
"--batch_size",
type=int,
default=256,
help="input batch size for training (default: 256)",
)
parser.add_argument(
"--epochs",
type=int,
default=100,
help="number of epochs to train (default: 100)",
)
parser.add_argument("--lr",
type=float,
default=0.001,
help="learning rate (default: 0.001)")
parser.add_argument("--decay",
type=float,
default=0,
help="weight decay (default: 0)")
parser.add_argument(
"--num_layer",
type=int,
default=5,
help="number of GNN message passing layers (default: 5).",
)
parser.add_argument("--csize",
type=int,
default=3,
help="context size (default: 3).")
parser.add_argument("--emb_dim",
type=int,
default=300,
help="embedding dimensions (default: 300)")
parser.add_argument("--dropout_ratio",
type=float,
default=0,
help="dropout ratio (default: 0)")
parser.add_argument(
"--neg_samples",
type=int,
default=1,
help="number of negative contexts per positive context (default: 1)",
)
parser.add_argument(
"--JK",
type=str,
default="last",
help="how the node features are combined across layers."
"last, sum, max or concat",
)
parser.add_argument(
"--context_pooling",
type=str,
default="mean",
help="how the contexts are pooled (sum, mean, or max)",
)
parser.add_argument("--mode",
type=str,
default="cbow",
help="cbow or skipgram")
parser.add_argument(
"--dataset",
type=str,
default="contextPred/chem/dataset/zinc_standard_agent",
help="root directory of dataset for pretraining",
)
parser.add_argument("--output_model_file",
type=str,
default="",
help="filename to output the model")
parser.add_argument("--gnn_type", type=str, default="gin")
parser.add_argument("--seed",
type=int,
default=0,
help="Seed for splitting dataset.")
parser.add_argument(
"--num_workers",
type=int,
default=8,
help="number of workers for dataset loading",
)
args = parser.parse_args()
torch.manual_seed(0)
np.random.seed(0)
device = (torch.device("cuda:" + str(args.device))
if torch.cuda.is_available() else torch.device("cpu"))
if torch.cuda.is_available():
torch.cuda.manual_seed_all(0)
l1 = args.num_layer - 1
l2 = l1 + args.csize
print(args.mode)
print("num layer: %d l1: %d l2: %d" % (args.num_layer, l1, l2))
# set up dataset and transform function.
dataset = MoleculeDataset(
args.dataset,
dataset=os.path.basename(args.dataset),
transform=ExtractSubstructureContextPair(args.num_layer, l1, l2),
)
loader = DataLoaderSubstructContext(dataset,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers)
# set up models, one for pre-training and one for context embeddings
model_substruct = GNN(
args.num_layer,
args.emb_dim,
JK=args.JK,
drop_ratio=args.dropout_ratio,
gnn_type=args.gnn_type,
).to(device)
model_context = GNN(
int(l2 - l1),
args.emb_dim,
JK=args.JK,
drop_ratio=args.dropout_ratio,
gnn_type=args.gnn_type,
).to(device)
# set up optimizer for the two GNNs
optimizer_substruct = optim.Adam(model_substruct.parameters(),
lr=args.lr,
weight_decay=args.decay)
optimizer_context = optim.Adam(model_context.parameters(),
lr=args.lr,
weight_decay=args.decay)
for epoch in range(1, args.epochs + 1):
print("====epoch " + str(epoch))
train_loss, train_acc = train(
args,
model_substruct,
model_context,
loader,
optimizer_substruct,
optimizer_context,
device,
)
print(train_loss, train_acc)
if not args.output_model_file == "":
torch.save(model_substruct.state_dict(),
args.output_model_file + ".pth")
parser = argparse.ArgumentParser()
parser.add_argument('-c', '--cuda', type=int, required=True)
args = parser.parse_args()
embed_size = 64
dropout = 0.5
learning_rate = 0.01
num_epochs = 100
device = torch.device(
f'cuda:{args.cuda}' if torch.cuda.is_available() else 'cpu')
data_train, data_test = AMT(device)
model = GNN(*data_train.size, embed_size, dropout).to(device)
criterion = nn.MSELoss()
optimizer = optim.Adam(model.parameters(), lr=learning_rate)
for epoch in range(num_epochs):
model.train()
y_pred = model(data_train).reshape(-1)
y = data_train.edge_type.float()
loss = criterion(y_pred, y)
optimizer.zero_grad()
loss.backward()
optimizer.step()
rmse_loss_train = loss.item()**0.5
N = 20
gen.num_examples_train = 200
gen.num_examples_test = 10
gen.N = N
gen.load_dataset()
clip_grad = 40.0
iterations = 5000
batch_size = 20
num_features = 10
num_layers = 5
J = 4
rf = 10.0 # regularization factor
Split = Split_GNN(batch_size, num_features, num_layers, J + 2, dim_input=3)
Tsp = GNN(num_features, num_layers, J + 2, dim_input=3)
Merge = GNN(num_features, num_layers, J + 2, dim_input=3)
optimizer_split = optim.RMSprop(Split.parameters())
optimizer_tsp = optim.Adamax(Tsp.parameters(), lr=1e-3)
optimizer_merge = optim.Adamax(Merge.parameters(), lr=1e-3)
for it in range(iterations):
sample = gen.sample_batch(batch_size, cuda=torch.cuda.is_available())
input, W, WTSP, labels, target, cities, perms, costs = extract(sample)
scores, probs = Split(input)
variance = compute_variance(probs)
sample, log_probs_samples = sample_one(probs, mode='train')
WW, x, Phi = compute_operators(W.data, sample, J)
x = torch.cat((x.unsqueeze(2), cities), 2)
y = WW[:, :, :, 1]
