def process(data_tuple, model, output_folder, training_args, overwrite):
fname, edg_source, edg_target, is_transition, labels, objects, clouds_data, xyz = data_tuple
spg_file = os.path.join(output_folder, fname[0])
logging.info("\nGenerating SPG file %s...", spg_file)
if os.path.exists(os.path.dirname(spg_file)) and not overwrite:
logging.info("Already exists, skipping")
return
elif not os.path.exists(os.path.dirname(spg_file)):
os.makedirs(os.path.dirname(spg_file))
if training_args.cuda:
is_transition = is_transition.to('cuda', non_blocking=True)
objects = objects.to('cuda', non_blocking=True)
clouds, clouds_global, nei = clouds_data
clouds_data = (clouds.to('cuda', non_blocking=True), clouds_global.to('cuda', non_blocking=True), nei)
ptnCloudEmbedder = get_embedder(training_args)
num_classes = get_num_classes(training_args)
embeddings = ptnCloudEmbedder.run_batch(model, *clouds_data, xyz)
diff = losses.compute_dist(embeddings, edg_source, edg_target, training_args.dist_type)
pred_components, pred_in_component = losses.compute_partition(
training_args, embeddings, edg_source, edg_target, diff, xyz)
graph_sp = graphs.compute_sp_graph(xyz, 100, pred_in_component, pred_components, labels, num_classes)
provider.write_spg(spg_file, graph_sp, pred_components, pred_in_component)
def evaluate(i_epoch):
""" Evaluated model on test set """
model.eval()
with torch.no_grad():
loader = torch.utils.data.DataLoader(test_dataset, batch_size=1, collate_fn=graph_collate, num_workers=args.nworkers)
if logging.getLogger().getEffectiveLevel() > logging.DEBUG:
loader = tqdm(loader, ncols=100)
loss_meter = tnt.meter.AverageValueMeter()
n_clusters_meter = tnt.meter.AverageValueMeter()
BR_meter = tnt.meter.AverageValueMeter()
BP_meter = tnt.meter.AverageValueMeter()
CM_classes = metrics.ConfusionMatrix(dbinfo['classes'])
# iterate over dataset in batches
for bidx, (fname, edg_source, edg_target, is_transition, labels, objects, clouds_data, xyz) in enumerate(loader):
if args.cuda:
is_transition = is_transition.to('cuda', non_blocking=True)
# labels = torch.from_numpy(labels).cuda()
objects = objects.to('cuda', non_blocking=True)
clouds, clouds_global, nei = clouds_data
clouds_data = (clouds.to('cuda', non_blocking=True), clouds_global.to('cuda', non_blocking=True), nei)
embeddings = ptnCloudEmbedder.run_batch(model, *clouds_data, xyz)
diff = compute_dist(embeddings, edg_source, edg_target, args.dist_type)
if len(is_transition) > 1:
weights_loss, pred_components, pred_in_component = compute_weight_loss(args, embeddings, objects, edg_source, edg_target,
is_transition, diff, True, xyz)
loss1, loss2 = compute_loss(args, diff, is_transition, weights_loss)
loss = (loss1 + loss2) / weights_loss.shape[0]
pred_transition = pred_in_component[edg_source] != pred_in_component[edg_target]
per_pred = perfect_prediction(pred_components, labels)
CM_classes.count_predicted_batch(labels[:, 1:], per_pred)
else:
loss = 0
if len(is_transition) > 1:
loss_meter.add(loss.item()) # /weights_loss.sum().item())
is_transition = is_transition.cpu().numpy()
n_clusters_meter.add(len(pred_components))
BR_meter.add((is_transition.sum()) * compute_boundary_recall(is_transition, relax_edge_binary(pred_transition, edg_source,
edg_target, xyz.shape[0],
args.BR_tolerance)),
n=is_transition.sum())
BP_meter.add((pred_transition.sum()) * compute_boundary_precision(relax_edge_binary(is_transition, edg_source,
edg_target, xyz.shape[0],
args.BR_tolerance), pred_transition),
n=pred_transition.sum())
CM = CM_classes.confusion_matrix
return loss_meter.value()[0], n_clusters_meter.value()[0], 100 * CM.trace() / CM.sum(), BR_meter.value()[0], BP_meter.value()[0]
def train(i_epoch):
""" Trains for one epoch """
#return 0
model.train()
loader = torch.utils.data.DataLoader(train_dataset, batch_size=args.batch_size, collate_fn=graph_collate, num_workers=args.nworkers, shuffle=True, drop_last=True)
if logging.getLogger().getEffectiveLevel() > logging.DEBUG: loader = tqdm(loader, ncols=100)
loss_meter = tnt.meter.AverageValueMeter()
n_clusters_meter = tnt.meter.AverageValueMeter()
t0 = time.time()
for bidx, (fname, edg_source, edg_target, is_transition, labels, objects, clouds_data, xyz) in enumerate(loader):
if args.cuda:
is_transition = is_transition.to('cuda',non_blocking=True)
#labels = torch.from_numpy(labels).cuda()
objects = objects.to('cuda',non_blocking=True)
clouds, clouds_global, nei = clouds_data
clouds_data = (clouds.to('cuda',non_blocking=True),clouds_global.to('cuda',non_blocking=True),nei)
t_loader = 1000*(time.time()-t0)
optimizer.zero_grad()
t0 = time.time()
embeddings = ptnCloudEmbedder.run_batch(model, *clouds_data, xyz)
diff = compute_dist(embeddings, edg_source, edg_target, args.dist_type)
weights_loss, pred_comp, in_comp = compute_weight_loss(args, embeddings, objects, edg_source, edg_target, is_transition, diff, True, xyz)
loss1, loss2 = compute_loss(args, diff, is_transition, weights_loss)
factor = 1000 #scaling for better usage of float precision
loss = (loss1 + loss2) / weights_loss.shape[0]*factor
loss.backward()
if args.grad_clip>0:
for p in model.parameters():
p.grad.data.clamp_(-args.grad_clip*factor, args.grad_clip*factor)
optimizer.step()
t_trainer = 1000*(time.time()-t0)
loss_meter.add(loss.item()/factor)#/weights_loss.mean().item())
n_clusters_meter.add(embeddings.shape[0] / len(pred_comp))
logging.debug('Batch loss %f, Loader time %f ms, Trainer time %f ms.', loss.item() / factor, t_loader, t_trainer)
t0 = time.time()
#return 0,0,0
return loss_meter.value()[0], n_clusters_meter.value()[0]
def evaluate_final():
""" Evaluated model on test set """
print("Final evaluation")
model.eval()
loss_meter = tnt.meter.AverageValueMeter()
n_clusters_meter = tnt.meter.AverageValueMeter()
confusion_matrix_classes = metrics.ConfusionMatrix(dbinfo['classes'])
confusion_matrix_BR = metrics.ConfusionMatrix(2)
confusion_matrix_BP = metrics.ConfusionMatrix(2)
with torch.no_grad():
loader = torch.utils.data.DataLoader(test_dataset,
batch_size=1,
collate_fn=graph_collate,
num_workers=args.nworkers)
if logging.getLogger().getEffectiveLevel() > logging.DEBUG:
loader = tqdm(loader, ncols=100)
# iterate over dataset in batches
for bidx, (fname, edg_source, edg_target, is_transition, labels,
objects, clouds_data, xyz) in enumerate(loader):
if args.cuda:
is_transition = is_transition.to('cuda', non_blocking=True)
# labels = torch.from_numpy(labels).cuda()
objects = objects.to('cuda', non_blocking=True)
clouds, clouds_global, nei = clouds_data
clouds_data = (clouds.to('cuda', non_blocking=True),
clouds_global.to('cuda',
non_blocking=True), nei)
if args.dataset == 'sema3d':
embeddings = ptnCloudEmbedder.run_batch_cpu(
model, *clouds_data, xyz)
else:
embeddings = ptnCloudEmbedder.run_batch(
model, *clouds_data, xyz)
diff = compute_dist(embeddings, edg_source, edg_target,
args.dist_type)
pred_components, pred_in_component = compute_partition(
args, embeddings, edg_source, edg_target, diff, xyz)
if len(is_transition) > 1:
pred_transition = pred_in_component[
edg_source] != pred_in_component[edg_target]
is_transition = is_transition.cpu().numpy()
n_clusters_meter.add(len(pred_components))
per_pred = perfect_prediction(pred_components, labels)
confusion_matrix_classes.count_predicted_batch(
labels[:, 1:], per_pred)
confusion_matrix_BR.count_predicted_batch_hard(
is_transition,
relax_edge_binary(pred_transition, edg_source,
edg_target, xyz.shape[0],
args.BR_tolerance).astype('uint8'))
confusion_matrix_BP.count_predicted_batch_hard(
relax_edge_binary(is_transition, edg_source,
edg_target, xyz.shape[0],
args.BR_tolerance),
pred_transition.astype('uint8'))
if args.spg_out:
graph_sp = compute_sp_graph(xyz, 100, pred_in_component,
pred_components, labels,
dbinfo["classes"])
spg_file = os.path.join(folder_hierarchy.spg_folder,
fname[0])
if not os.path.exists(os.path.dirname(spg_file)):
os.makedirs(os.path.dirname(spg_file))
try:
os.remove(spg_file)
except OSError:
pass
write_spg(spg_file, graph_sp, pred_components,
pred_in_component)
# Debugging purpose - write the embedding file and an exemple of scalar files
# if bidx % 0 == 0:
# embedding2ply(os.path.join(folder_hierarchy.emb_folder , fname[0][:-3] + '_emb.ply'), xyz, embeddings.detach().cpu().numpy())
# scalar2ply(os.path.join(folder_hierarchy.scalars , fname[0][:-3] + '_elevation.ply') , xyz, clouds_data[1][:,1].cpu())
# edg_class = is_transition + 2*pred_transition
# edge_class2ply2(os.path.join(folder_hierarchy.emb_folder , fname[0][:-3] + '_transition.ply'), edg_class, xyz, edg_source, edg_target)
if len(is_transition) > 1:
res_name = folder_hierarchy.outputdir + '/res.h5'
res_file = h5py.File(res_name, 'w')
res_file.create_dataset(
'confusion_matrix_classes',
data=confusion_matrix_classes.confusion_matrix,
dtype='uint64')
res_file.create_dataset(
'confusion_matrix_BR',
data=confusion_matrix_BR.confusion_matrix,
dtype='uint64')
res_file.create_dataset(
'confusion_matrix_BP',
data=confusion_matrix_BP.confusion_matrix,
dtype='uint64')
res_file.create_dataset('n_clusters',
data=n_clusters_meter.value()[0],
dtype='uint64')
res_file.close()
return
