def main(args):
if args.gpu < 0:
device = torch.device("cpu")
else:
device = torch.device("cuda:" + str(args.gpu))
# create dataset
config_file = json.load(open(args.cfg))
train_dir = config_file['train_dir']
dataset = config_file['dataset']
cache_io = config_file['cache_io']
napp = config_file['node_app']
eapp = config_file['edge_app']
symm_io = config_file['symm_io']
shuffle_io = config_file['shuffle_io']
n_classes = config_file['num_classes']
apply_da = config_file['data_augment']
rad_scale = config_file['rad_scale']
angle_scale = config_file['angle_scale']
length_scale = config_file['length_scale']
curve_scale = config_file['curve_scale']
poly_scale = config_file['poly_scale']
domains = config_file['domains']
batch_io = args.batch_size
epochs = args.epochs
bdir = os.path.basename(train_dir)
print(domains)
input_dim = 58
if napp:
input_dim = input_dim + 21
if eapp:
input_dim = input_dim + 9
norm_factors = {
'rad_scale': rad_scale,
'angle_scale': angle_scale,
'length_scale': length_scale,
'curve_scale': curve_scale,
'poly_scale': poly_scale
}
prefix = 'data-' + str(bdir) + ':' + str(dataset) + '_m-tag_ni-' + str(
input_dim) + '_nh-' + str(args.n_hidden) + '_lay-' + str(
args.n_layers) + '_hops-' + str(args.hops) + '_napp-' + str(
napp) + '_eapp-' + str(eapp) + '_do-' + str(
args.dropout) + '_ro-' + str(
args.readout) + '_norm-' + str(args.norm)
if args.readout == 'spp':
extra = '_ng-' + str(args.n_grid)
prefix += extra
extra = '_b-' + str(batch_io)
prefix += extra
print('saving to prefix: ', prefix)
# create train dataset
trainset = ShockGraphDataset(train_dir,
dataset,
norm_factors,
node_app=napp,
edge_app=eapp,
cache=cache_io,
symmetric=symm_io,
data_augment=apply_da,
grid=args.n_grid,
domains=domains)
# Use PyTorch's DataLoader and the collate function
# defined before.
data_loader = DataLoader(trainset,
batch_size=batch_io,
shuffle=shuffle_io,
collate_fn=partial(collate, device_name=device))
if args.ctype == 'tagconv':
print('A TAGConv Graph Classifier is being trained')
else:
print('A SGConv Graph Classifier is being trained')
model = Classifier(input_dim, args.n_hidden, n_classes, args.n_layers,
args.ctype, args.hops, args.readout, F.relu,
args.dropout, args.n_grid, args.K, args.norm, device)
loss_func = nn.CrossEntropyLoss()
# define the optimizer
optimizer = torch.optim.Adam(model.parameters(),
lr=args.lr,
weight_decay=args.weight_decay)
model = model.to(device)
model.train()
print(model)
epoch_losses = []
for epoch in tqdm(range(epochs)):
epoch_loss = 0
for iter, (bg, label) in enumerate(data_loader):
prediction = model(bg)
loss = loss_func(prediction, label)
optimizer.zero_grad()
loss.backward()
optimizer.step()
epoch_loss += loss.detach().item()
epoch_loss /= (iter + 1)
epoch_losses.append(epoch_loss)
print('Epoch {}, loss {:.6f}'.format(epoch, epoch_loss))
if (epoch + 1) % 25 == 0:
path = prefix + '_epoch_' + str(epoch + 1).zfill(3) + '.pth'
torch.save(
{
'epoch': epoch,
'model_state_dict': model.state_dict(),
'optimizer_state_dict': optimizer.state_dict(),
'loss': epoch_loss
}, path)
def main(args):
if args.gpu < 0:
device = torch.device("cpu")
else:
device = torch.device("cuda:" + str(args.gpu))
# create dataset
config_file = json.load(open(args.cfg))
train_dir = config_file['train_dir']
dataset = config_file['dataset']
cache_io = config_file['cache_io']
app_io = config_file['app']
symm_io = config_file['symm_io']
shuffle_io = config_file['shuffle_io']
n_classes = config_file['num_classes']
apply_da = config_file['data_augment']
num_feats = config_file['features_dim']
batch_io = args.batch_size
epochs = args.epochs
bdir = os.path.basename(train_dir)
prefix = 'agnn_sg_model_' + dataset + '_' + bdir + '_' + str(
args.n_layers) + '_' + args.readout
if args.readout == 'spp':
extra = '_' + str(args.n_grid)
prefix += extra
print('saving to prefix: ', prefix)
# create train dataset
trainset = ShockGraphDataset(train_dir,
dataset,
app=app_io,
cache=cache_io,
symmetric=symm_io,
data_augment=apply_da,
grid=args.n_grid)
# Use PyTorch's DataLoader and the collate function
# defined before.
data_loader = DataLoader(trainset,
batch_size=batch_io,
shuffle=shuffle_io,
collate_fn=partial(collate, device_name=device))
print('A AGNN Graph Classifier is being trained')
model = Classifier(num_feats, n_classes, args.n_layers, args.init_beta,
args.learn_beta, args.readout, F.relu, args.dropout,
args.n_grid, device)
loss_func = nn.CrossEntropyLoss()
# define the optimizer
optimizer = torch.optim.Adam(model.parameters(),
lr=args.lr,
weight_decay=args.weight_decay)
model = model.to(device)
model.train()
print(model)
epoch_losses = []
for epoch in tqdm(range(epochs)):
epoch_loss = 0
for iter, (bg, label) in enumerate(data_loader):
prediction = model(bg)
loss = loss_func(prediction, label)
optimizer.zero_grad()
loss.backward()
optimizer.step()
epoch_loss += loss.detach().item()
epoch_loss /= (iter + 1)
epoch_losses.append(epoch_loss)
print('Epoch {}, loss {:.6f}'.format(epoch, epoch_loss))
if (epoch + 1) % 25 == 0:
path = prefix + '_epoch_' + str(epoch + 1).zfill(3) + '.pth'
torch.save(
{
'epoch': epoch,
'model_state_dict': model.state_dict(),
'optimizer_state_dict': optimizer.state_dict(),
'loss': epoch_loss
}, path)
def main(args):
if args.gpu < 0:
device = torch.device("cpu")
else:
device = torch.device("cuda:" + str(args.gpu))
# create dataset
config_file = json.load(open(args.cfg))
train_dir = config_file['train_dir']
test_dir = config_file['test_dir']
dataset = config_file['dataset']
cache_io = config_file['cache_io']
napp = config_file['node_app']
eapp = config_file['edge_app']
symm_io = config_file['symm_io']
shuffle_io = config_file['shuffle_io']
n_classes = config_file['num_classes']
apply_da = config_file['data_augment']
rad_scale = config_file['rad_scale']
angle_scale = config_file['angle_scale']
length_scale = config_file['length_scale']
curve_scale = config_file['curve_scale']
poly_scale = config_file['poly_scale']
batch_io = args.batch_size
epochs = args.epochs
bdir = os.path.basename(train_dir)
bdir = 'se_tcg_train_fc'
input_dim = 58
if napp:
input_dim = input_dim + 21
if eapp:
input_dim = input_dim + 9
norm_factors = {
'rad_scale': rad_scale,
'angle_scale': angle_scale,
'length_scale': length_scale,
'curve_scale': curve_scale,
'poly_scale': poly_scale
}
prefix = 'data-' + str(bdir) + ':' + str(dataset) + '_m-tag_ni-' + str(
input_dim) + '_nh-' + str(args.n_hidden) + '_lay-' + str(
args.n_layers) + '_hops-' + str(args.hops) + '_napp-' + str(
napp) + '_eapp-' + str(eapp) + '_do-' + str(
args.dropout) + '_ro-' + str(args.readout)
if args.readout == 'spp':
extra = '_ng-' + str(args.n_grid)
prefix += extra
extra = '_b-' + str(batch_io)
prefix += extra
print('saving to prefix: ', prefix)
# create train and test dataset
trainset = ShockGraphDataset(train_dir,
dataset,
norm_factors,
node_app=napp,
edge_app=eapp,
cache=True,
symmetric=symm_io,
data_augment=False,
grid=args.n_grid)
testset = ShockGraphDataset(test_dir,
dataset,
norm_factors,
node_app=napp,
edge_app=eapp,
cache=True,
symmetric=symm_io,
data_augment=False,
grid=args.n_grid)
# Use PyTorch's DataLoader and the collate function
# defined before.
data_loader_train = DataLoader(trainset,
batch_size=1,
shuffle=False,
collate_fn=partial(collate,
device_name=device))
data_loader_test = DataLoader(testset,
batch_size=1,
shuffle=False,
collate_fn=partial(collate,
device_name=device))
model_files = glob.glob(prefix + '*pth')
model_files.sort()
spp = args.n_grid * args.n_grid
for state_path in model_files:
print('Using weights: ', state_path)
model = Classifier(input_dim, args.n_hidden, n_classes, args.n_layers,
args.ctype, args.hops, args.readout, F.relu,
args.dropout, args.n_grid, args.K, device)
layer = nn.Module()
for name, module in model.named_children():
if name == 'readout_fcn':
layer = module
model.load_state_dict(torch.load(state_path)['model_state_dict'])
model.to(device)
model.eval()
# get train embeddings and labels
train_embeddings = torch.zeros(
(len(data_loader_train) * spp, args.n_hidden))
train_labels = torch.zeros(len(data_loader_train) * spp,
dtype=torch.int32)
start = 0
stop = spp
for iter, (bg, label) in enumerate(data_loader_train):
train_embeddings[start:stop, :] = im2vec(bg, layer, model,
args.n_hidden)
train_labels[start:stop] = label
start = stop
stop = start + spp
# get test embeddings and labels
test_embeddings = torch.zeros(
(len(data_loader_test) * spp, args.n_hidden))
test_labels = torch.zeros(len(data_loader_test), dtype=torch.int32)
start = 0
stop = spp
for iter, (bg, label) in enumerate(data_loader_test):
test_embeddings[start:stop, :] = im2vec(bg, layer, model,
args.n_hidden)
test_labels[iter] = label
start = stop
stop = start + spp
D = cosine_distance(test_embeddings, train_embeddings)
predicted = predict(D, train_labels, n_classes, spp)
groundtruth = test_labels
confusion_matrix = np.zeros((n_classes, n_classes))
for ind in range(groundtruth.shape[0]):
if groundtruth[ind] == predicted[ind]:
confusion_matrix[groundtruth[ind], groundtruth[ind]] += 1
else:
confusion_matrix[groundtruth[ind], predicted[ind]] += 1
confusion_matrix = (confusion_matrix /
np.sum(confusion_matrix, 1)[:, None]) * 100
#print(confusion_matrix)
mAP = np.diagonal(confusion_matrix)
print(mAP)
print("mAP: ", np.mean(mAP))
print(
'Accuracy of argmax predictedions on the test set: {:4f}%'.format(
(groundtruth == predicted).sum().item() / len(groundtruth) *
100))
del model
def main(args):
if args.gpu < 0:
device = torch.device("cpu")
else:
device = torch.device("cuda:" + str(args.gpu))
# create dataset
config_file = json.load(open(args.cfg))
test_dir = config_file['test_dir']
train_dir = config_file['train_dir']
dataset = config_file['dataset']
cache_io = config_file['cache_io']
app_io = config_file['app']
symm_io = config_file['symm_io']
shuffle_io = config_file['shuffle_io']
n_classes = config_file['num_classes']
apply_da = config_file['data_augment']
num_feats = config_file['features_dim']
batch_io = args.batch_size
epochs = args.epochs
bdir = os.path.basename(train_dir)
prefix = 'gin_sg_model_' + dataset + '_' + bdir + '_' + str(
args.n_layers) + '_' + str(
args.n_hidden
) + '_' + args.neighbor_pooling_type + '_' + args.graph_pooling_type
# create train dataset
testset = ShockGraphDataset(test_dir,
dataset,
app=app_io,
cache=cache_io,
symmetric=symm_io,
data_augment=apply_da)
# Use PyTorch's DataLoader and the collate function
# defined before.
data_loader = DataLoader(testset,
batch_size=batch_io,
shuffle=shuffle_io,
collate_fn=partial(collate, device_name=device))
model_files = glob.glob(prefix + '*pth')
model_files.sort()
for state_path in model_files:
print('Using weights: ', state_path)
model = Classifier(args.n_layers, args.num_mlp_layers, num_feats,
args.n_hidden, n_classes, args.dropout,
args.learn_eps, args.graph_pooling_type,
args.neighbor_pooling_type, device)
model.load_state_dict(torch.load(state_path)['model_state_dict'])
model.to(device)
model.eval()
groundtruth, predicted, scores = classify_data(model, data_loader)
confusion_matrix = np.zeros((n_classes, n_classes))
for ind in range(0, groundtruth.shape[0]):
if groundtruth[ind] == predicted[ind]:
confusion_matrix[groundtruth[ind], groundtruth[ind]] += 1
else:
confusion_matrix[groundtruth[ind], predicted[ind]] += 1
confusion_matrix = (confusion_matrix /
np.sum(confusion_matrix, 1)[:, None]) * 100
print(confusion_matrix)
mAP = np.diagonal(confusion_matrix)
print(mAP)
print("mAP: ", np.mean(mAP))
print(
'Accuracy of argmax predictedions on the test set: {:4f}%'.format(
(groundtruth == predicted).sum().item() / len(groundtruth) *
100))
del model
def main(args):
if args.gpu<0:
device = torch.device("cpu")
else:
device = torch.device("cuda:" + str(args.gpu))
# create dataset
config_file=json.load(open(args.cfg))
train_dir=config_file['train_dir']
test_dir=config_file['test_dir']
dataset=config_file['dataset']
cache_io=config_file['cache_io']
app_io=config_file['app']
symm_io=config_file['symm_io']
shuffle_io=config_file['shuffle_io']
n_classes=config_file['num_classes']
apply_da=config_file['data_augment']
num_feats = config_file['features_dim']
batch_io=1
epochs=args.epochs
bdir=os.path.basename(train_dir)
prefix=args.ctype+'_sg_model_'+dataset+'_'+bdir+'_'+str(args.n_layers)+'_'+str(args.n_hidden)+'_'+str(args.hops)+'_'+args.readout
# create train dataset
testset=ShockGraphDataset(test_dir,dataset,app=app_io,cache=True,symmetric=symm_io,data_augment=False)
# Use PyTorch's DataLoader and the collate function
# defined before.
data_loader = DataLoader(testset, batch_size=batch_io, shuffle=False,
collate_fn=partial(collate,device_name=device))
if args.ctype == 'tagconv':
print('A TAGConv Graph Classifier is being trained')
else:
print('A SGConv Graph Classifier is being trained')
model = Classifier(num_feats,
args.n_hidden,
n_classes,
args.n_layers,
args.ctype,
args.hops,
args.readout,
F.relu,
args.dropout,
device)
model.load_state_dict(torch.load(args.model)['model_state_dict'])
layer=nn.Module()
for name,module in model.named_children():
if name == 'readout_fcn':
layer=module
model.to(device)
model.eval()
embeddings=np.zeros((len(data_loader),args.n_hidden))
for iter, (bg, label) in enumerate(data_loader):
embeddings[iter,:] = im2vec(bg,layer,model,args.n_hidden)
np.savetxt('test_embeddings.txt',embeddings,delimiter=' ')
fid=open('testset.txt','w')
for i in testset.files:
fid.writelines(i+'\n')
fid.close()
def eval(config_file, state_path, device, flip):
test_dir = config_file['test_dir']
dataset = config_file['dataset']
cache_io = True
symm_io = config_file['symm_io']
shuffle_io = False
num_classes = config_file['num_classes']
input_dim = config_file['features_dim']
hidden_dim = config_file['hidden_dim']
hidden_layers = config_file['hidden_layers']
aggregate = config_file['aggregate']
combine = config_file['combine']
batch_io = config_file['batch']
dropout = config_file['dropout']
model = Classifier(input_dim, hidden_dim, num_classes, hidden_layers,
combine, nn.functional.relu, dropout, device)
model.load_state_dict(torch.load(state_path)['model_state_dict'])
model.to(device)
model.eval()
testset = ShockGraphDataset(test_dir,
dataset,
cache=cache_io,
symmetric=symm_io,
data_augment=False)
if flip:
testset_flip = ShockGraphDataset(test_dir,
dataset,
cache=cache_io,
symmetric=symm_io,
data_augment=False,
flip_pp=True)
groundtruth, predicted, scores, testfiles = classify_data(
model, testset, batch_io, device)
if flip:
_, predicted_flip, scores_flip, _ = classify_data(
model, testset_flip, batch_io, device)
confusion_matrix = np.zeros((num_classes, num_classes))
combined_predicted = np.copy(predicted)
if flip:
for i in range(groundtruth.shape[0]):
if scores_flip[i] > scores[i]:
print("flipping: ", scores_flip[i], scores[i],
combined_predicted[i], predicted_flip[i])
combined_predicted[i] = predicted_flip[i]
for ind in range(0, groundtruth.shape[0]):
if groundtruth[ind] == combined_predicted[ind]:
confusion_matrix[groundtruth[ind], groundtruth[ind]] += 1
else:
confusion_matrix[groundtruth[ind], combined_predicted[ind]] += 1
confusion_matrix = (confusion_matrix /
np.sum(confusion_matrix, 1)[:, None]) * 100
print(confusion_matrix)
mAP = np.diagonal(confusion_matrix)
print(mAP)
print("mAP: ", np.mean(mAP))
print(groundtruth)
print(predicted)
print(combined_predicted)
print('Accuracy of argmax combined_predictedions on the test set: {:4f}%'.
format((groundtruth == combined_predicted).sum().item() /
len(groundtruth) * 100))
fid = open('output.txt', 'w')
for ind in range(0, len(testfiles)):
line = [
testfiles[ind] + ' ',
str(groundtruth[ind]) + ' ',
str(predicted[ind]) + ' ',
str(scores[ind]) + '\n'
]
fid.writelines(line)
fid.close()
def main(args):
if args.gpu<0:
device = torch.device("cpu")
else:
device = torch.device("cuda:" + str(args.gpu))
# create dataset
config_file=json.load(open(args.cfg))
train_dir=config_file['train_dir']
dataset=config_file['dataset']
cache_io=config_file['cache_io']
napp=config_file['node_app']
eapp=config_file['edge_app']
symm_io=config_file['symm_io']
shuffle_io=config_file['shuffle_io']
n_classes=config_file['num_classes']
apply_da=config_file['data_augment']
rad_scale=config_file['rad_scale']
angle_scale=config_file['angle_scale']
length_scale=config_file['length_scale']
curve_scale=config_file['curve_scale']
poly_scale=config_file['poly_scale']
batch_io=args.batch_size
epochs=args.epochs
input_dim=58
if napp:
input_dim=input_dim+21
if eapp:
input_dim=input_dim+9
norm_factors={'rad_scale':rad_scale,'angle_scale':angle_scale,'length_scale':length_scale,'curve_scale':curve_scale,'poly_scale':poly_scale}
prefix='data-'+str(dataset)+'_m-triplet_ni-'+str(input_dim)+'_nh-'+str(args.n_hidden)+'_lay-'+str(args.n_layers)+'_hops-'+str(args.hops)+'_napp-'+str(napp)+'_eapp-'+str(eapp)+'_do-'+str(args.dropout)+'_ro-'+str(args.readout)+'_m-'+str(args.margin)
if args.readout == 'spp':
extra='_ng-'+str(args.n_grid)
prefix+=extra
extra='_b-'+str(batch_io)
prefix+=extra
print('saving to prefix: ', prefix)
# create train dataset
trainset=ShockGraphDataset(train_dir,dataset,norm_factors,node_app=napp,edge_app=eapp,cache=cache_io,symmetric=symm_io,data_augment=apply_da,grid=args.n_grid)
# Use PyTorch's DataLoader and the collate function
# defined before.
data_loader = DataLoader(trainset, batch_size=batch_io, shuffle=False,
collate_fn=partial(collate,device_name=device))
print('A TAGConv Triplet Graph Classifier is being trained')
model = Classifier(input_dim,
args.n_hidden,
args.n_layers,
args.hops,
args.readout,
F.relu,
args.dropout,
args.n_grid,
args.K,
device)
model.load_state_dict(torch.load(args.model)['model_state_dict'])
layer=nn.Module()
for name,module in model.named_children():
if name == 'readout_fcn':
layer=module
model.to(device)
model.eval()
embeddings=np.zeros((len(data_loader),args.n_hidden))
for iter, (bg, label) in enumerate(data_loader):
embeddings[iter,:] = im2vec(bg,layer,model,args.n_hidden)
np.savetxt('test_embeddings.txt',embeddings,delimiter=' ')
fid=open('testset.txt','w')
for i in trainset.files:
fid.writelines(i+'\n')
fid.close()
def main(args):
if args.gpu<0:
device = torch.device("cpu")
else:
device = torch.device("cuda:" + str(args.gpu))
# create dataset
config_file=json.load(open(args.cfg))
train_dir=config_file['train_dir']
test_dir=config_file['test_dir']
dataset=config_file['dataset']
cache_io=config_file['cache_io']
app_io=config_file['app']
symm_io=config_file['symm_io']
shuffle_io=config_file['shuffle_io']
n_classes=config_file['num_classes']
apply_da=config_file['data_augment']
num_feats = config_file['features_dim']
batch_io=args.batch_size
epochs=args.epochs
bdir=os.path.basename(train_dir)
prefix=args.ctype+'_sg_model_'+dataset+'_'+bdir+'_'+str(args.n_layers)+'_'+str(args.n_hidden)+'_'+str(args.hops)+'_'+args.readout
if args.readout == 'spp':
extra='_'+str(args.n_grid)
prefix+=extra
# create train dataset
testset=ShockGraphDataset(test_dir,dataset,app=app_io,cache=True,symmetric=symm_io,
data_augment=False,grid=args.n_grid)
# Use PyTorch's DataLoader and the collate function
# defined before.
data_loader = DataLoader(testset, batch_size=batch_io, shuffle=False,
collate_fn=partial(collate,device_name=device))
if args.flip:
testset_flip=ShockGraphDataset(test_dir,dataset,app=app_io,cache=True,
symmetric=symm_io,data_augment=False,grid=args.n_grid,flip_pp=True)
# Use PyTorch's DataLoader and the collate function
# defined before.
data_loader_flip = DataLoader(testset_flip, batch_size=batch_io, shuffle=False,
collate_fn=partial(collate,device_name=device))
if args.ctype == 'tagconv':
print('A TAGConv Graph Classifier is being trained')
else:
print('A SGConv Graph Classifier is being trained')
model_files=glob.glob(prefix+'*pth')
model_files.sort()
for state_path in model_files:
print('Using weights: ',state_path)
model = Classifier(num_feats,
args.n_hidden,
n_classes,
args.n_layers,
args.ctype,
args.hops,
args.readout,
F.relu,
args.dropout,
args.n_grid,
device)
model.load_state_dict(torch.load(state_path)['model_state_dict'])
model.to(device)
model.eval()
groundtruth,predicted,scores=classify_data(model,data_loader,n_classes)
if args.flip:
_,predicted_flip,scores_flip=classify_data(model,data_loader_flip,n_classes)
combined_predicted=np.copy(predicted)
if args.flip:
for i in range(groundtruth.shape[0]):
if np.max(scores_flip[i,:]) > np.max(scores[i,:]):
print("flipping: ",np.max(scores_flip[i,:]),np.max(scores[i,:]),predicted[i],predicted_flip[i])
combined_predicted[i]=predicted_flip[i]
confusion_matrix=np.zeros((n_classes,n_classes))
for ind in range(0,groundtruth.shape[0]):
if groundtruth[ind]==combined_predicted[ind]:
confusion_matrix[groundtruth[ind],groundtruth[ind]]+=1
else:
confusion_matrix[groundtruth[ind],combined_predicted[ind]]+=1
confusion_matrix=(confusion_matrix/np.sum(confusion_matrix,1)[:,None])*100
#print(confusion_matrix)
mAP=np.diagonal(confusion_matrix)
print(mAP)
print("mAP: ",np.mean(mAP))
print('Accuracy of argmax combined_predictedions on the test set: {:4f}%'.format(
(groundtruth == combined_predicted).sum().item() / len(groundtruth) * 100))
testfiles=testset.files
fid=open('output.txt','w')
for ind in range(0,len(testfiles)):
line=[testfiles[ind]+' ',str(groundtruth[ind])+' ',str(combined_predicted[ind])+' ']
for idx in range(scores.shape[1]):
val=scores[ind,idx]
if idx==scores.shape[1]-1:
line.append(str(val)+'\n')
else:
line.append(str(val)+' ')
fid.writelines(line)
fid.close()
del model
def train(config_file, device):
train_dir = config_file['train_dir']
dataset = config_file['dataset']
cache_io = config_file['cache_io']
symm_io = config_file['symm_io']
shuffle_io = config_file['shuffle_io']
num_classes = config_file['num_classes']
input_dim = config_file['features_dim']
hidden_dim = config_file['hidden_dim']
hidden_layers = config_file['hidden_layers']
aggregate = config_file['aggregate']
combine = config_file['combine']
epochs = config_file['epochs']
batch_io = config_file['batch']
apply_da = config_file['data_augment']
dropout = config_file['dropout']
bdir = os.path.basename(train_dir)
prefix = 'gcn_sg_model_' + dataset + '_' + bdir + '_' + aggregate + '_' + combine + '_' + str(
hidden_dim) + '_' + str(hidden_layers)
print("Training with batch size of: ", batch_io, " over ", epochs,
" Epochs with da: ", apply_da)
print("Writing out to : ", prefix)
trainset = ShockGraphDataset(train_dir,
dataset,
cache=cache_io,
symmetric=symm_io,
data_augment=apply_da)
# Use PyTorch's DataLoader and the collate function
# defined before.
data_loader = DataLoader(trainset,
batch_size=batch_io,
shuffle=shuffle_io,
collate_fn=partial(collate, device_name=device))
# Create model
model = Classifier(input_dim, hidden_dim, num_classes, hidden_layers,
combine, nn.functional.relu, dropout, device)
loss_func = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001, weight_decay=5e-4)
model.to(device)
model.train()
print(model)
epoch_losses = []
for epoch in tqdm(range(epochs)):
epoch_loss = 0
for iter, (bg, label) in enumerate(data_loader):
prediction = model(bg)
loss = loss_func(prediction, label)
optimizer.zero_grad()
loss.backward()
optimizer.step()
epoch_loss += loss.detach().item()
epoch_loss /= (iter + 1)
epoch_losses.append(epoch_loss)
print('Epoch {}, loss {:.6f}'.format(epoch, epoch_loss))
if (epoch + 1) % 50 == 0:
path = prefix + '_epoch_' + str(epoch + 1).zfill(3) + '.pth'
torch.save(
{
'epoch': epoch,
'model_state_dict': model.state_dict(),
'optimizer_state_dict': optimizer.state_dict(),
'loss': epoch_loss
}, path)
