def eval_with_partition(args):
model_load_path = args.model_load_path
print("Starting evaluating model stored at", model_load_path)
device = torch.device("cuda")
dataset = PygNodePropPredDataset(name=args.dataset, root=args.data_folder)
graph = dataset[0]
adj = SparseTensor(row=graph.edge_index[0], col=graph.edge_index[1])
if args.self_loop:
adj = adj.set_diag()
graph.edge_index = add_self_loops(edge_index=graph.edge_index,
num_nodes=graph.num_nodes)[0]
split_idx = dataset.get_idx_split()
evaluator = Evaluator(args.dataset)
args.in_channels = graph.x.size(-1)
args.num_tasks = dataset.num_classes
# print('%s' % args)
model = DeeperGCN(args).to(device)
ckpt = torch.load(model_load_path)
model.load_state_dict(ckpt['model_state_dict'])
res = test_with_partition(model,
graph,
adj,
split_idx,
num_clusters=args.eval_cluster_number,
partition_method=args.partition_method,
evaluator=evaluator,
device=device)
print(res)
return res
def main():
args = ArgsInit().args
dataset = PygNodePropPredDataset(name=args.dataset)
graph = dataset[0]
if args.self_loop:
graph.edge_index = add_self_loops(edge_index=graph.edge_index,
num_nodes=graph.num_nodes)[0]
split_idx = dataset.get_idx_split()
evaluator = Evaluator(args.dataset)
args.in_channels = graph.x.size(-1)
args.num_tasks = dataset.num_classes
print(args)
model = DeeperGCN(args)
print(model)
model.load_state_dict(torch.load(args.model_load_path)['model_state_dict'])
result = test(model, graph.x, graph.edge_index, graph.y, split_idx,
evaluator)
print(result)
model.print_params(final=True)
def eval_model(params):
model_load_path, args = params
if os.path.isdir(args.model_load_path):
model_load_dir = args.model_load_path
model_load_path = os.path.join(model_load_dir, model_load_path)
print("Starting evaluating model stored at", model_load_path)
dataset = PygNodePropPredDataset(name=args.dataset, root=args.data_folder)
graph = dataset[0]
if args.self_loop:
graph.edge_index = add_self_loops(edge_index=graph.edge_index,
num_nodes=graph.num_nodes)[0]
split_idx = dataset.get_idx_split()
evaluator = Evaluator(args.dataset)
args.in_channels = graph.x.size(-1)
args.num_tasks = dataset.num_classes
model = DeeperGCN(args)
ckpt = torch.load(model_load_path, map_location=torch.device('cpu'))
model.load_state_dict(ckpt['model_state_dict'])
test_res = test(model, graph.x, graph.edge_index, graph.y, split_idx,
evaluator)
test_res["model_load_path"] = model_load_path
return test_res
def main():
args = ArgsInit().args
if args.use_gpu:
device = torch.device("cuda:" + str(args.device)) if torch.cuda.is_available() else torch.device("cpu")
else:
device = torch.device("cpu")
dataset = OGBNDataset(dataset_name=args.dataset)
args.num_tasks = dataset.num_tasks
args.nf_path = dataset.extract_node_features(args.aggr)
evaluator = Evaluator(args.dataset)
valid_data_list = []
for i in range(args.num_evals):
parts = dataset.random_partition_graph(dataset.total_no_of_nodes,
cluster_number=args.valid_cluster_number)
valid_data = dataset.generate_sub_graphs(parts,
cluster_number=args.valid_cluster_number)
valid_data_list.append(valid_data)
model = DeeperGCN(args)
model.load_state_dict(torch.load(args.model_load_path)['model_state_dict'])
model.to(device)
result = multi_evaluate(valid_data_list, dataset, model, evaluator, device)
print(result)
model.print_params(final=True)
def main():
args = ArgsInit().args
if args.use_gpu:
device = torch.device("cuda:" +
str(args.device)) if torch.cuda.is_available(
) else torch.device("cpu")
else:
device = torch.device('cpu')
dataset = PygGraphPropPredDataset(name=args.dataset)
args.num_tasks = dataset.num_tasks
print(args)
if args.feature == 'full':
pass
elif args.feature == 'simple':
print('using simple feature')
# only retain the top two node/edge features
dataset.data.x = dataset.data.x[:, :2]
dataset.data.edge_attr = dataset.data.edge_attr[:, :2]
split_idx = dataset.get_idx_split()
evaluator = Evaluator(args.dataset)
train_loader = DataLoader(dataset[split_idx["train"]],
batch_size=args.batch_size,
shuffle=False,
num_workers=args.num_workers)
valid_loader = DataLoader(dataset[split_idx["valid"]],
batch_size=args.batch_size,
shuffle=False,
num_workers=args.num_workers)
test_loader = DataLoader(dataset[split_idx["test"]],
batch_size=args.batch_size,
shuffle=False,
num_workers=args.num_workers)
model = DeeperGCN(args)
model.load_state_dict(torch.load(args.model_load_path)['model_state_dict'])
model.to(device)
train_result = eval(model, device, train_loader,
evaluator)[dataset.eval_metric]
valid_result = eval(model, device, valid_loader,
evaluator)[dataset.eval_metric]
test_result = eval(model, device, test_loader,
evaluator)[dataset.eval_metric]
print({
'Train': train_result,
'Validation': valid_result,
'Test': test_result
})
model.print_params(final=True)
def main():
args = ArgsInit().args
if args.use_gpu:
device = torch.device("cuda:" +
str(args.device)) if torch.cuda.is_available(
) else torch.device("cpu")
else:
device = torch.device('cpu')
if args.not_extract_node_feature:
dataset = PygGraphPropPredDataset(name=args.dataset,
transform=add_zeros)
else:
extract_node_feature_func = partial(extract_node_feature,
reduce=args.aggr)
dataset = PygGraphPropPredDataset(name=args.dataset,
transform=extract_node_feature_func)
args.num_tasks = dataset.num_classes
evaluator = Evaluator(args.dataset)
split_idx = dataset.get_idx_split()
train_loader = DataLoader(dataset[split_idx["train"]],
batch_size=args.batch_size,
shuffle=False,
num_workers=args.num_workers)
valid_loader = DataLoader(dataset[split_idx["valid"]],
batch_size=args.batch_size,
shuffle=False,
num_workers=args.num_workers)
test_loader = DataLoader(dataset[split_idx["test"]],
batch_size=args.batch_size,
shuffle=False,
num_workers=args.num_workers)
print(args)
model = DeeperGCN(args)
model.load_state_dict(torch.load(args.model_load_path)['model_state_dict'])
model.to(device)
train_accuracy = eval(model, device, train_loader, evaluator)
valid_accuracy = eval(model, device, valid_loader, evaluator)
test_accuracy = eval(model, device, test_loader, evaluator)
print({
'Train': train_accuracy,
'Validation': valid_accuracy,
'Test': test_accuracy
})
model.print_params(final=True)
def main():
args = ArgsInit().args
if args.use_gpu:
device = torch.device("cuda:" +
str(args.device)) if torch.cuda.is_available(
) else torch.device("cpu")
else:
device = torch.device('cpu')
dataset = PygNodePropPredDataset(name=args.dataset)
data = dataset[0]
split_idx = dataset.get_idx_split()
evaluator = Evaluator(args.dataset)
x = data.x.to(device)
y_true = data.y.to(device)
edge_index = data.edge_index.to(device)
edge_index = to_undirected(edge_index, data.num_nodes)
if args.self_loop:
edge_index = add_self_loops(edge_index, num_nodes=data.num_nodes)[0]
args.in_channels = data.x.size(-1)
args.num_tasks = dataset.num_classes
print(args)
model = DeeperGCN(args)
model.load_state_dict(torch.load(args.model_load_path)['model_state_dict'])
model.to(device)
result = test(model, x, edge_index, y_true, split_idx, evaluator)
train_accuracy, valid_accuracy, test_accuracy = result
print({
'Train': train_accuracy,
'Validation': valid_accuracy,
'Test': test_accuracy
})
model.print_params(final=True)
def main():
args = ArgsInit().args
if args.use_gpu:
device = torch.device("cuda:" +
str(args.device)) if torch.cuda.is_available(
) else torch.device("cpu")
else:
device = torch.device('cpu')
dataset = PygLinkPropPredDataset(name=args.dataset)
data = dataset[0]
# Data(edge_index=[2, 2358104], edge_weight=[2358104, 1], edge_year=[2358104, 1], x=[235868, 128])
split_edge = dataset.get_edge_split()
evaluator = Evaluator(args.dataset)
x = data.x.to(device)
edge_index = data.edge_index.to(device)
args.in_channels = data.x.size(-1)
args.num_tasks = 1
print(args)
model = DeeperGCN(args).to(device)
predictor = LinkPredictor(args).to(device)
model.load_state_dict(torch.load(args.model_load_path)['model_state_dict'])
model.to(device)
predictor.load_state_dict(
torch.load(args.predictor_load_path)['model_state_dict'])
predictor.to(device)
hits = ['Hits@10', 'Hits@50', 'Hits@100']
result = test(model, predictor, x, edge_index, split_edge, evaluator,
args.batch_size)
for k in hits:
train_result, valid_result, test_result = result[k]
print('{}--Train: {}, Validation: {}, Test: {}'.format(
k, train_result, valid_result, test_result))
def test_model(model_path):
args = ArgsInit().args
dataset = PygNodePropPredDataset(name=args.dataset)
graph = dataset[0]
num_parts = 10
data_list = list(
RandomNodeSampler(graph, num_parts=num_parts, shuffle=True))
number_of_train = int(0.9 * num_parts)
train_data_list = data_list[0:number_of_train]
test_data_list = data_list[number_of_train:]
args.in_channels = graph.x.size(-1)
args.num_tasks = dataset.num_classes
model = DeeperGCN(args)
model.load_state_dict(torch.load(model_path))
print(test(model, test_data_list))
def main_fixed_mask(args, imp_num, resume_train_ckpt=None):
device = torch.device("cuda:" + str(args.device))
dataset = PygLinkPropPredDataset(name=args.dataset)
data = dataset[0]
# Data(edge_index=[2, 2358104], edge_weight=[2358104, 1], edge_year=[2358104, 1], x=[235868, 128])
split_edge = dataset.get_edge_split()
evaluator = Evaluator(args.dataset)
x = data.x.to(device)
edge_index = data.edge_index.to(device)
args.in_channels = data.x.size(-1)
args.num_tasks = 1
model = DeeperGCN(args).to(device)
pruning.add_mask(model, args)
predictor = LinkPredictor(args).to(device)
rewind_weight_mask, adj_spar, wei_spar = pruning.resume_change(resume_train_ckpt, model, args)
model.load_state_dict(rewind_weight_mask)
predictor.load_state_dict(resume_train_ckpt['predictor_state_dict'])
# model.load_state_dict(rewind_weight_mask)
# predictor.load_state_dict(rewind_predict_weight)
adj_spar, wei_spar = pruning.print_sparsity(model, args)
for name, param in model.named_parameters():
if 'mask' in name:
param.requires_grad = False
optimizer = torch.optim.Adam(list(model.parameters()) + list(predictor.parameters()), lr=args.lr)
#results = {}
results = {'epoch': 0 }
keys = ['highest_valid', 'final_train', 'final_test', 'highest_train']
hits = ['Hits@10', 'Hits@50', 'Hits@100']
for key in keys:
results[key] = {k: 0 for k in hits}
results['adj_spar'] = adj_spar
results['wei_spar'] = wei_spar
start_epoch = 1
for epoch in range(start_epoch, args.fix_epochs + 1):
t0 = time.time()
epoch_loss = train.train_fixed(model, predictor, x, edge_index, split_edge, optimizer, args.batch_size, args)
result = train.test(model, predictor, x, edge_index, split_edge, evaluator, args.batch_size, args)
# return a tuple
k = 'Hits@50'
train_result, valid_result, test_result = result[k]
if train_result > results['highest_train'][k]:
results['highest_train'][k] = train_result
if valid_result > results['highest_valid'][k]:
results['highest_valid'][k] = valid_result
results['final_train'][k] = train_result
results['final_test'][k] = test_result
results['epoch'] = epoch
pruning.save_all(model, predictor,
rewind_weight_mask,
optimizer,
imp_num,
epoch,
args.model_save_path,
'IMP{}_fixed_ckpt'.format(imp_num))
epoch_time = (time.time() - t0) / 60
print(time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()) + ' | ' +
'IMP:[{}] (FIX Mask) Epoch:[{}/{}] LOSS:[{:.4f}] Train :[{:.2f}] Valid:[{:.2f}] Test:[{:.2f}] | Update Test:[{:.2f}] at epoch:[{}] Time:[{:.2f}min]'
.format(imp_num, epoch, args.fix_epochs, epoch_loss, train_result * 100,
valid_result * 100,
test_result * 100,
results['final_test'][k] * 100,
results['epoch'],
epoch_time))
print("=" * 120)
print("syd final: IMP:[{}], Train:[{:.2f}] Best Val:[{:.2f}] at epoch:[{}] | Final Test Acc:[{:.2f}] Adj:[{:.2f}%] Wei:[{:.2f}%]"
.format(imp_num, results['final_train'][k] * 100,
results['highest_valid'][k] * 100,
results['epoch'],
results['final_test'][k] * 100,
results['adj_spar'],
results['wei_spar']))
print("=" * 120)
def main_get_mask(args, imp_num, rewind_weight_mask=None, rewind_predict_weight=None, resume_train_ckpt=None):
device = torch.device("cuda:" + str(args.device))
dataset = PygLinkPropPredDataset(name=args.dataset)
data = dataset[0]
# Data(edge_index=[2, 2358104], edge_weight=[2358104, 1], edge_year=[2358104, 1], x=[235868, 128])
split_edge = dataset.get_edge_split()
evaluator = Evaluator(args.dataset)
x = data.x.to(device)
edge_index = data.edge_index.to(device)
args.in_channels = data.x.size(-1)
args.num_tasks = 1
model = DeeperGCN(args).to(device)
pruning.add_mask(model, args)
predictor = LinkPredictor(args).to(device)
pruning.add_trainable_mask_noise(model, args, c=1e-4)
optimizer = torch.optim.Adam(list(model.parameters()) + list(predictor.parameters()), lr=args.lr)
results = {'epoch': 0 }
keys = ['highest_valid', 'final_train', 'final_test', 'highest_train']
hits = ['Hits@10', 'Hits@50', 'Hits@100']
for key in keys:
results[key] = {k: 0 for k in hits}
start_epoch = 1
if resume_train_ckpt:
start_epoch = resume_train_ckpt['epoch']
rewind_weight_mask = resume_train_ckpt['rewind_weight_mask']
ori_model_dict = model.state_dict()
over_lap = {k : v for k, v in resume_train_ckpt['model_state_dict'].items() if k in ori_model_dict.keys()}
ori_model_dict.update(over_lap)
model.load_state_dict(ori_model_dict)
print("Resume at IMP:[{}] epoch:[{}] len:[{}/{}]!".format(imp_num, resume_train_ckpt['epoch'], len(over_lap.keys()), len(ori_model_dict.keys())))
optimizer.load_state_dict(resume_train_ckpt['optimizer_state_dict'])
adj_spar, wei_spar = pruning.print_sparsity(model, args)
else:
rewind_weight_mask = copy.deepcopy(model.state_dict())
rewind_predict_weight = copy.deepcopy(predictor.state_dict())
for epoch in range(start_epoch, args.mask_epochs + 1):
t0 = time.time()
epoch_loss, prune_info_dict = train.train_mask(model, predictor,
x,
edge_index,
split_edge,
optimizer, args)
result = train.test(model, predictor,
x,
edge_index,
split_edge,
evaluator,
args.batch_size, args)
k = 'Hits@50'
train_result, valid_result, test_result = result[k]
if train_result > results['highest_train'][k]:
results['highest_train'][k] = train_result
if valid_result > results['highest_valid'][k]:
results['highest_valid'][k] = valid_result
results['final_train'][k] = train_result
results['final_test'][k] = test_result
results['epoch'] = epoch
pruning.save_all(model, predictor,
rewind_weight_mask,
optimizer,
imp_num,
epoch,
args.model_save_path,
'IMP{}_train_ckpt'.format(imp_num))
epoch_time = (time.time() - t0) / 60
print(time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()) + ' | ' +
'IMP:[{}] (GET Mask) Epoch:[{}/{}] LOSS:[{:.4f}] Train :[{:.2f}] Valid:[{:.2f}] Test:[{:.2f}] | Update Test:[{:.2f}] at epoch:[{}] | Adj[{:.3f}%] Wei[{:.3f}%] Time:[{:.2f}min]'
.format(imp_num, epoch, args.mask_epochs,
epoch_loss,
train_result * 100,
valid_result * 100,
test_result * 100,
results['final_test'][k] * 100,
results['epoch'],
prune_info_dict['adj_spar'],
prune_info_dict['wei_spar'],
epoch_time))
rewind_weight_mask, adj_spar, wei_spar = pruning.change(rewind_weight_mask, model, args)
print('-' * 100)
print("INFO : IMP:[{}] (GET MASK) Final Result Train:[{:.2f}] Valid:[{:.2f}] Test:[{:.2f}] | Adj:[{:.3f}%] Wei:[{:.3f}%]"
.format(imp_num, results['final_train'][k] * 100,
results['highest_valid'][k] * 100,
results['final_test'][k] * 100,
adj_spar,
wei_spar))
print('-' * 100)
return rewind_weight_mask, rewind_predict_weight
fe.to(device)
image_model.to(device)
#image_model.eval()
if WANDB:
wandb.watch(gcn1)
wandb.watch(gcn2)
wandb.watch(gcn3)
wandb.watch(image_model)
wandb.watch(fe)
#load model
dic = torch.load('/Data/leo/Pixel2Mesh_3d/2dTo3d/wandb/run-20210126_131356-1bkxbzmf/files/dic_checkpoint')
gcn1.load_state_dict(dic['gcn_state_dict'][0])
gcn1.train()
gcn2.load_state_dict(dic['gcn_state_dict'][1])
gcn2.train()
gcn3.load_state_dict(dic['gcn_state_dict'][2])
gcn3.train()
image_model.load_state_dict(dic['cnn_state_dic'])
image_model.train()
fe.load_state_dict(dic['fe_state_dic'])
fe.train()
#optimizer.load_state_dict(dic['optimizer_state_dict'])
#epoch = checkpoint['epoch']
#loss = checkpoint['loss']
optimizer = torch.optim.Adam(list(gcn1.parameters()) +
list(gcn2.parameters()) +
def main_fixed_mask(args, imp_num, final_state_dict=None, resume_train_ckpt=None):
device = torch.device("cuda:" + str(args.device))
dataset = OGBNDataset(dataset_name=args.dataset)
nf_path = dataset.extract_node_features(args.aggr)
args.num_tasks = dataset.num_tasks
args.nf_path = nf_path
evaluator = Evaluator(args.dataset)
criterion = torch.nn.BCEWithLogitsLoss()
valid_data_list = []
for i in range(args.num_evals):
parts = dataset.random_partition_graph(dataset.total_no_of_nodes, cluster_number=args.valid_cluster_number)
valid_data = dataset.generate_sub_graphs(parts, cluster_number=args.valid_cluster_number)
valid_data_list.append(valid_data)
print("-" * 120)
model = DeeperGCN(args).to(device)
pruning.add_mask(model)
if final_state_dict is not None:
pruning.retrain_operation(dataset, model, final_state_dict)
adj_spar, wei_spar = pruning.print_sparsity(dataset, model)
for name, param in model.named_parameters():
if 'mask' in name:
param.requires_grad = False
optimizer = optim.Adam(model.parameters(), lr=args.lr)
results = {'highest_valid': 0, 'final_train': 0, 'final_test': 0, 'highest_train': 0, 'epoch':0}
results['adj_spar'] = adj_spar
results['wei_spar'] = wei_spar
start_epoch = 1
if resume_train_ckpt:
dataset.adj = resume_train_ckpt['adj']
start_epoch = resume_train_ckpt['epoch']
rewind_weight_mask = resume_train_ckpt['rewind_weight_mask']
ori_model_dict = model.state_dict()
over_lap = {k : v for k, v in resume_train_ckpt['model_state_dict'].items() if k in ori_model_dict.keys()}
ori_model_dict.update(over_lap)
model.load_state_dict(ori_model_dict)
print("Resume at IMP:[{}] epoch:[{}] len:[{}/{}]!".format(imp_num, resume_train_ckpt['epoch'], len(over_lap.keys()), len(ori_model_dict.keys())))
optimizer.load_state_dict(resume_train_ckpt['optimizer_state_dict'])
adj_spar, wei_spar = pruning.print_sparsity(dataset, model)
for epoch in range(start_epoch, args.epochs + 1):
# do random partition every epoch
t0 = time.time()
train_parts = dataset.random_partition_graph(dataset.total_no_of_nodes, cluster_number=args.cluster_number)
data = dataset.generate_sub_graphs(train_parts, cluster_number=args.cluster_number, ifmask=True)
epoch_loss = train.train_fixed(data, dataset, model, optimizer, criterion, device, args)
result = train.multi_evaluate(valid_data_list, dataset, model, evaluator, device)
train_result = result['train']['rocauc']
valid_result = result['valid']['rocauc']
test_result = result['test']['rocauc']
if valid_result > results['highest_valid']:
results['highest_valid'] = valid_result
results['final_train'] = train_result
results['final_test'] = test_result
results['epoch'] = epoch
final_state_dict = pruning.save_all(dataset,
model,
None,
optimizer,
imp_num,
epoch,
args.model_save_path,
'IMP{}_fixed_ckpt'.format(imp_num))
epoch_time = (time.time() - t0) / 60
print(time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()) + ' | ' +
'IMP:[{}] (FIX Mask) Epoch[{}/{}] LOSS[{:.4f}] Train[{:.2f}] Valid[{:.2f}] Test[{:.2f}] | Update Test[{:.2f}] at epoch[{}] | Adj[{:.2f}%] Wei[{:.2f}%] Time[{:.2f}min]'
.format(imp_num, epoch, args.epochs, epoch_loss, train_result * 100,
valid_result * 100,
test_result * 100,
results['final_test'] * 100,
results['epoch'],
results['adj_spar'] * 100,
results['wei_spar'] * 100,
epoch_time))
print("=" * 120)
print("INFO final: IMP:[{}], Train:[{:.2f}] Best Val:[{:.2f}] at epoch:[{}] | Final Test Acc:[{:.2f}] | Adj:[{:.2f}%] Wei:[{:.2f}%]"
.format(imp_num, results['final_train'] * 100,
results['highest_valid'] * 100,
results['epoch'],
results['final_test'] * 100,
results['adj_spar'] * 100,
results['wei_spar'] * 100))
print("=" * 120)
def main_fixed_mask(args,
imp_num,
adj_percent,
wei_percent,
resume_train_ckpt=None):
device = torch.device("cuda:" + str(args.device))
dataset = PygNodePropPredDataset(name=args.dataset)
data = dataset[0]
split_idx = dataset.get_idx_split()
evaluator = Evaluator(args.dataset)
x = data.x.to(device)
y_true = data.y.to(device)
train_idx = split_idx['train'].to(device)
edge_index = data.edge_index.to(device)
edge_index = to_undirected(edge_index, data.num_nodes)
if args.self_loop:
edge_index = add_self_loops(edge_index, num_nodes=data.num_nodes)[0]
args.in_channels = data.x.size(-1)
args.num_tasks = dataset.num_classes
model = DeeperGCN(args).to(device)
pruning.add_mask(model, args.num_layers)
pruning.random_pruning(model, args, adj_percent, wei_percent)
adj_spar, wei_spar = pruning.print_sparsity(model, args)
for name, param in model.named_parameters():
if 'mask' in name:
param.requires_grad = False
optimizer = torch.optim.Adam(model.parameters(), lr=args.lr)
results = {
'highest_valid': 0,
'final_train': 0,
'final_test': 0,
'highest_train': 0,
'epoch': 0
}
results['adj_spar'] = adj_spar
results['wei_spar'] = wei_spar
start_epoch = 1
if resume_train_ckpt:
start_epoch = resume_train_ckpt['epoch']
ori_model_dict = model.state_dict()
over_lap = {
k: v
for k, v in resume_train_ckpt['model_state_dict'].items()
if k in ori_model_dict.keys()
}
ori_model_dict.update(over_lap)
model.load_state_dict(ori_model_dict)
print("(RP FIXED MASK) Resume at epoch:[{}] len:[{}/{}]!".format(
resume_train_ckpt['epoch'], len(over_lap.keys()),
len(ori_model_dict.keys())))
optimizer.load_state_dict(resume_train_ckpt['optimizer_state_dict'])
adj_spar, wei_spar = pruning.print_sparsity(model, args)
for epoch in range(start_epoch, args.epochs + 1):
epoch_loss = train_fixed(model, x, edge_index, y_true, train_idx,
optimizer, args)
result = test(model, x, edge_index, y_true, split_idx, evaluator)
train_accuracy, valid_accuracy, test_accuracy = result
if valid_accuracy > results['highest_valid']:
results['highest_valid'] = valid_accuracy
results['final_train'] = train_accuracy
results['final_test'] = test_accuracy
results['epoch'] = epoch
pruning.save_all(model, None, optimizer, imp_num, epoch,
args.model_save_path,
'RP{}_fixed_ckpt'.format(imp_num))
print(
time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()) + ' | ' +
'RP:[{}] (FIX Mask) Epoch:[{}/{}]\t LOSS:[{:.4f}] Train :[{:.2f}] Valid:[{:.2f}] Test:[{:.2f}] | Update Test:[{:.2f}] at epoch:[{}]'
.format(imp_num, epoch, args.epochs, epoch_loss, train_accuracy *
100, valid_accuracy * 100, test_accuracy *
100, results['final_test'] * 100, results['epoch']))
print("=" * 120)
print(
"syd final: RP:[{}], Train:[{:.2f}] Best Val:[{:.2f}] at epoch:[{}] | Final Test Acc:[{:.2f}] Adj:[{:.2f}%] Wei:[{:.2f}%]"
.format(imp_num, results['final_train'] * 100,
results['highest_valid'] * 100, results['epoch'],
results['final_test'] * 100, results['adj_spar'],
results['wei_spar']))
print("=" * 120)
def main_get_mask(args,
imp_num,
rewind_weight_mask=None,
resume_train_ckpt=None):
device = torch.device("cuda:" + str(args.device))
dataset = PygNodePropPredDataset(name=args.dataset)
data = dataset[0]
split_idx = dataset.get_idx_split()
evaluator = Evaluator(args.dataset)
x = data.x.to(device)
y_true = data.y.to(device)
train_idx = split_idx['train'].to(device)
edge_index = data.edge_index.to(device)
edge_index = to_undirected(edge_index, data.num_nodes)
if args.self_loop:
edge_index = add_self_loops(edge_index, num_nodes=data.num_nodes)[0]
args.in_channels = data.x.size(-1)
args.num_tasks = dataset.num_classes
print("-" * 120)
model = DeeperGCN(args).to(device)
pruning.add_mask(model, args.num_layers)
if rewind_weight_mask:
model.load_state_dict(rewind_weight_mask)
adj_spar, wei_spar = pruning.print_sparsity(model, args)
pruning.add_trainable_mask_noise(model, args, c=1e-5)
optimizer = torch.optim.Adam(model.parameters(), lr=1e-3)
results = {
'highest_valid': 0,
'final_train': 0,
'final_test': 0,
'highest_train': 0,
'epoch': 0
}
start_epoch = 1
if resume_train_ckpt:
start_epoch = resume_train_ckpt['epoch']
rewind_weight_mask = resume_train_ckpt['rewind_weight_mask']
ori_model_dict = model.state_dict()
over_lap = {
k: v
for k, v in resume_train_ckpt['model_state_dict'].items()
if k in ori_model_dict.keys()
}
ori_model_dict.update(over_lap)
model.load_state_dict(ori_model_dict)
print("Resume at IMP:[{}] epoch:[{}] len:[{}/{}]!".format(
imp_num, resume_train_ckpt['epoch'], len(over_lap.keys()),
len(ori_model_dict.keys())))
optimizer.load_state_dict(resume_train_ckpt['optimizer_state_dict'])
adj_spar, wei_spar = pruning.print_sparsity(model, args)
else:
rewind_weight_mask = copy.deepcopy(model.state_dict())
for epoch in range(start_epoch, args.mask_epochs + 1):
epoch_loss = train(model, x, edge_index, y_true, train_idx, optimizer,
args)
result = test(model, x, edge_index, y_true, split_idx, evaluator)
train_accuracy, valid_accuracy, test_accuracy = result
if valid_accuracy > results['highest_valid']:
results['highest_valid'] = valid_accuracy
results['final_train'] = train_accuracy
results['final_test'] = test_accuracy
results['epoch'] = epoch
rewind_weight_mask, adj_spar, wei_spar = pruning.get_final_mask_epoch(
model, rewind_weight_mask, args)
#pruning.save_all(model, rewind_weight_mask, optimizer, imp_num, epoch, args.model_save_path, 'IMP{}_train_ckpt'.format(imp_num))
print(
time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()) + ' | ' +
'IMP:[{}] (GET Mask) Epoch:[{}/{}]\t LOSS:[{:.4f}] Train :[{:.2f}] Valid:[{:.2f}] Test:[{:.2f}] | Update Test:[{:.2f}] at epoch:[{}] | Adj:[{:.2f}%] Wei:[{:.2f}%]'
.format(imp_num, epoch, args.mask_epochs, epoch_loss,
train_accuracy * 100, valid_accuracy * 100, test_accuracy *
100, results['final_test'] *
100, results['epoch'], adj_spar, wei_spar))
print('-' * 100)
print(
"INFO : IMP:[{}] (GET MASK) Final Result Train:[{:.2f}] Valid:[{:.2f}] Test:[{:.2f}] | Adj:[{:.2f}%] Wei:[{:.2f}%] "
.format(imp_num, results['final_train'] * 100,
results['highest_valid'] * 100, results['final_test'] * 100,
adj_spar, wei_spar))
print('-' * 100)
return rewind_weight_mask