def _speech_to_text(self, raw_data, token, lang="ja-JP", samplerate=16000):
log.debug("Start.")
# Bing Speech API呼び出し
url = self.config["wav2textURL"] + "?" + urllib.parse.urlencode(
{"language": lang})
headers = {
"Content-type":
"audio/wav; codec=audio/pcm; samplerate={0}".format(samplerate),
#"Transfer-Encoding": "chunked",
"Authorization":
"Bearer " + token
}
log.info("Request -------------\n url=" + url + "\n headers=" +
str(headers))
response = requests.post(url, data=raw_data, headers=headers)
if not response.ok:
raise response.raise_for_status()
# 文字化け対策のためutf-8で処理する
response.encoding = "utf-8"
log.info("Response ------------\n " + response.text)
json = response.json()
if ("Success" != json["RecognitionStatus"]):
log.warn(json["RecognitionStatus"] + "が発生しました。")
return ""
result = response.json()["DisplayText"]
print("End.")
return result
def train(args):
experiment_dir = mkdir('./experiment/')
checkpoints_dir = mkdir('./experiment/semseg/%s/'%(args.model_name))
train_data, train_label, test_data, test_label = _load()
dataset = S3DISDataLoader(train_data, train_label, data_augmentation = args.augment)
dataloader = DataLoader(dataset, batch_size=args.batch_size,shuffle=True, num_workers=args.workers)
test_dataset = S3DISDataLoader(test_data, test_label)
testdataloader = DataLoader(test_dataset, batch_size=args.batch_size,shuffle=True, num_workers=args.workers)
num_classes = 13
if args.model_name == 'pointnet':
model = PointNetSeg(num_classes, feature_transform=True, input_dims = 9)
else:
model = PointNet2SemSeg(num_classes, feature_dims = 6)
torch.backends.cudnn.benchmark = True
model = torch.nn.DataParallel(model).cuda()
log.debug('Using gpu:',args.gpu)
if args.pretrain is not None:
log.debug('Use pretrain model...')
model.load_state_dict(torch.load(args.pretrain))
init_epoch = int(args.pretrain[:-4].split('-')[-1])
log.debug('start epoch from', init_epoch)
else:
log.debug('Training from scratch')
init_epoch = 0
if args.optimizer == 'SGD':
optimizer = torch.optim.SGD(model.parameters(), lr=0.01, momentum=0.9)
elif args.optimizer == 'Adam':
optimizer = torch.optim.Adam(
model.parameters(),
lr=args.learning_rate,
betas=(0.9, 0.999),
eps=1e-08,
weight_decay=args.decay_rate)
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=20, gamma=0.5)
LEARNING_RATE_CLIP = 1e-5
history = {'loss':[]}
best_acc = 0
best_meaniou = 0
for epoch in range(init_epoch,args.epoch):
scheduler.step()
lr = max(optimizer.param_groups[0]['lr'],LEARNING_RATE_CLIP)
log.info(job='semseg',model=args.model_name,gpu=args.gpu,epoch='%d/%s' % (epoch, args.epoch),lr=lr)
for param_group in optimizer.param_groups:
param_group['lr'] = lr
for points, target in tqdm(dataloader, total=len(dataloader), smoothing=0.9, dynamic_ncols=True):
points, target = points.float(), target.long()
points = points.transpose(2, 1)
points, target = points.cuda(), target.cuda()
optimizer.zero_grad()
model = model.train()
if args.model_name == 'pointnet':
pred, trans_feat = model(points)
else:
pred = model(points)
pred = pred.contiguous().view(-1, num_classes)
target = target.view(-1, 1)[:, 0]
loss = F.nll_loss(pred, target)
if args.model_name == 'pointnet':
loss += feature_transform_reguliarzer(trans_feat) * 0.001
history['loss'].append(loss.cpu().data.numpy())
loss.backward()
optimizer.step()
log.debug('clear cuda cache')
torch.cuda.empty_cache()
test_metrics, cat_mean_iou = test_semseg(
model.eval(),
testdataloader,
label_id_to_name,
args.model_name,
num_classes,
)
mean_iou = np.mean(cat_mean_iou)
save_model = False
if test_metrics['accuracy'] > best_acc:
best_acc = test_metrics['accuracy']
if mean_iou > best_meaniou:
best_meaniou = mean_iou
save_model = True
if save_model:
fn_pth = 'semseg-%s-%.5f-%04d.pth' % (args.model_name, best_meaniou, epoch)
log.info('Save model...',fn = fn_pth)
torch.save(model.state_dict(), os.path.join(checkpoints_dir, fn_pth))
log.warn(cat_mean_iou)
else:
log.info('No need to save model')
log.warn(cat_mean_iou)
log.warn('Curr',accuracy=test_metrics['accuracy'], meanIOU=mean_iou)
log.warn('Best',accuracy=best_acc, meanIOU=best_meaniou)
def train(args):
experiment_dir = mkdir('experiment/')
checkpoints_dir = mkdir('experiment/%s/'%(args.model_name))
kitti_utils = Semantic_KITTI_Utils(ROOT, subset = args.subset)
class_names = kitti_utils.class_names
num_classes = kitti_utils.num_classes
if args.subset == 'inview':
train_npts = 2000
test_npts = 2500
if args.subset == 'all':
train_npts = 50000
test_npts = 100000
log.info(subset=args.subset, train_npts=train_npts, test_npts=test_npts)
dataset = SemKITTI_Loader(ROOT, train_npts, train = True, subset = args.subset)
dataloader = DataLoader(dataset, batch_size=args.batch_size, shuffle=True,
num_workers=args.workers, pin_memory=True)
test_dataset = SemKITTI_Loader(ROOT, test_npts, train = False, subset = args.subset)
testdataloader = DataLoader(test_dataset, batch_size=int(args.batch_size/2), shuffle=False,
num_workers=args.workers, pin_memory=True)
if args.model_name == 'pointnet':
model = PointNetSeg(num_classes, input_dims = 4, feature_transform = True)
else:
model = PointNet2SemSeg(num_classes, feature_dims = 1)
if args.optimizer == 'SGD':
optimizer = torch.optim.SGD(model.parameters(), lr=0.01, momentum=0.9)
elif args.optimizer == 'Adam':
optimizer = torch.optim.Adam(
model.parameters(),
lr=args.learning_rate,
betas=(0.9, 0.999),
eps=1e-08,
weight_decay=1e-4)
torch.backends.cudnn.benchmark = True
model = torch.nn.DataParallel(model)
#use more than 1 gpu
model.cuda()
log.info('Using gpu:',args.gpu)
if args.pretrain is not None:
log.info('Use pretrain model...')
model.load_state_dict(torch.load(args.pretrain))
init_epoch = int(args.pretrain[:-4].split('-')[-1])
log.info('Restart training', epoch=init_epoch)
else:
log.msg('Training from scratch')
init_epoch = 0
best_acc = 0
best_miou = 0
#->5.12 add
# to show details of epoch training
loss_list = []
miou_list = []
acc_list = []
epoch_time = []
lr_list = []
#-<5.12 add
for epoch in range(init_epoch,args.epoch):
model.train()
lr = calc_decay(args.learning_rate, epoch)
log.info(model=args.model_name, gpu=args.gpu, epoch=epoch, lr=lr)
for param_group in optimizer.param_groups:
param_group['lr'] = lr
for points, target in tqdm(dataloader, total=len(dataloader), smoothing=0.9, dynamic_ncols=True):
points = points.float().transpose(2, 1).cuda()
target = target.long().cuda()
if args.model_name == 'pointnet':
logits, trans_feat = model(points)
else:
logits = model(points)
#logits = logits.contiguous().view(-1, num_classes)
#target = target.view(-1, 1)[:, 0]
#loss = F.nll_loss(logits, target)
logits = logits.transpose(2, 1)
loss = nn.CrossEntropyLoss()(logits, target)
if args.model_name == 'pointnet':
loss += feature_transform_reguliarzer(trans_feat) * 0.001
# loss_list.append(loss.item())
optimizer.zero_grad()
loss.backward()
optimizer.step()
torch.cuda.empty_cache()
acc, miou = test_kitti_semseg(model.eval(), testdataloader,
args.model_name,num_classes,class_names)
# miou_list.append(np.asscalar(miou))
# acc_list.append(np.asscalar(acc))
save_model = False
if acc > best_acc:
best_acc = acc
if miou > best_miou:
best_miou = miou
save_model = True
#->5.12 add
loss_list.append(loss.item())
miou_list.append(np.asscalar(miou))
acc_list.append(np.asscalar(acc))
epoch_time.append(epoch)
lr_list.append(lr)
#->5.12 add
if save_model:
fn_pth = '%s-%.5f-%04d.pth' % (args.model_name, best_miou, epoch)
log.info('Save model...',fn = fn_pth)
torch.save(model.state_dict(), os.path.join(checkpoints_dir, fn_pth))
else:
log.info('No need to save model')
# 3.31 add |>
# show(args)
# 3.31 add |<
log.warn('Curr',accuracy=acc, mIOU=miou)
log.warn('Best',accuracy=best_acc, mIOU=best_miou)
# 5.15 add
label_size = {"size":40}
fig = plt.figure()
plt.plot(epoch_time,loss_list,label = "loss")
plt.plot(epoch_time,miou_list,label = "mIOU")
plt.plot(epoch_time,acc_list,label = "accuracy")
# plt.plot(epoch_time,lr_list,label = "learning rate")
plt.xlabel("epoch time", fontsize=40)
plt.ylabel("value", fontsize=40)
plt.title("training trendency", fontsize=60)
plt.tick_params(labelsize=40)
plt.legend(prop = label_size)
plt.show()
def train(args):
experiment_dir = mkdir('experiment/')
checkpoints_dir = mkdir('experiment/%s/' % (args.model_name))
kitti_utils = Semantic_KITTI_Utils(KITTI_ROOT, subset=args.subset)
class_names = kitti_utils.class_names
num_classes = kitti_utils.num_classes
if args.subset == 'inview':
train_npts = 8000
test_npts = 24000
if args.subset == 'all':
train_npts = 50000
test_npts = 100000
log.info(subset=args.subset, train_npts=train_npts, test_npts=test_npts)
dataset = SemKITTI_Loader(KITTI_ROOT,
train_npts,
train=True,
subset=args.subset)
dataloader = DataLoader(dataset,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.workers,
pin_memory=True)
test_dataset = SemKITTI_Loader(KITTI_ROOT,
test_npts,
train=False,
subset=args.subset)
testdataloader = DataLoader(test_dataset,
batch_size=int(args.batch_size / 2),
shuffle=False,
num_workers=args.workers,
pin_memory=True)
if args.model_name == 'pointnet':
model = PointNetSeg(num_classes, input_dims=4, feature_transform=True)
else:
model = PointNet2SemSeg(num_classes, feature_dims=1)
if args.optimizer == 'SGD':
optimizer = torch.optim.SGD(model.parameters(), lr=0.01, momentum=0.9)
elif args.optimizer == 'Adam':
optimizer = torch.optim.Adam(model.parameters(),
lr=args.learning_rate,
betas=(0.9, 0.999),
eps=1e-08,
weight_decay=1e-4)
torch.backends.cudnn.benchmark = True
model = torch.nn.DataParallel(model)
model.cuda()
log.info('Using gpu:', args.gpu)
if args.pretrain is not None:
log.info('Use pretrain model...')
model.load_state_dict(torch.load(args.pretrain))
init_epoch = int(args.pretrain[:-4].split('-')[-1])
log.info('Restart training', epoch=init_epoch)
else:
log.msg('Training from scratch')
init_epoch = 0
best_acc = 0
best_miou = 0
for epoch in range(init_epoch, args.epoch):
model.train()
lr = calc_decay(args.learning_rate, epoch)
log.info(subset=args.subset,
model=args.model_name,
gpu=args.gpu,
epoch=epoch,
lr=lr)
for param_group in optimizer.param_groups:
param_group['lr'] = lr
for points, target in tqdm(dataloader,
total=len(dataloader),
smoothing=0.9,
dynamic_ncols=True):
points = points.float().transpose(2, 1).cuda()
target = target.long().cuda()
if args.model_name == 'pointnet':
logits, trans_feat = model(points)
else:
logits = model(points)
#logits = logits.contiguous().view(-1, num_classes)
#target = target.view(-1, 1)[:, 0]
#loss = F.nll_loss(logits, target)
logits = logits.transpose(2, 1)
loss = nn.CrossEntropyLoss()(logits, target)
if args.model_name == 'pointnet':
loss += feature_transform_reguliarzer(trans_feat) * 0.001
optimizer.zero_grad()
loss.backward()
optimizer.step()
torch.cuda.empty_cache()
acc, miou = test_kitti_semseg(model.eval(), testdataloader,
args.model_name, num_classes,
class_names)
save_model = False
if acc > best_acc:
best_acc = acc
if miou > best_miou:
best_miou = miou
save_model = True
if save_model:
fn_pth = '%s-%s-%.5f-%04d.pth' % (args.model_name, args.subset,
best_miou, epoch)
log.info('Save model...', fn=fn_pth)
torch.save(model.state_dict(),
os.path.join(checkpoints_dir, fn_pth))
else:
log.info('No need to save model')
log.warn('Curr', accuracy=acc, mIOU=miou)
log.warn('Best', accuracy=best_acc, mIOU=best_miou)
def train(args):
experiment_dir = mkdir('./experiment/')
checkpoints_dir = mkdir('./experiment/partseg/%s/' % (args.model_name))
cache = _load(root)
norm = True if args.model_name == 'pointnet' else False
npoints = 2048
train_ds = PartNormalDataset(root,
cache,
npoints=npoints,
split='trainval',
data_augmentation=args.augment)
dataloader = DataLoader(train_ds,
batch_size=args.batch_size,
shuffle=True,
num_workers=int(args.workers))
test_ds = PartNormalDataset(root, cache, npoints=npoints, split='test')
testdataloader = DataLoader(test_ds,
batch_size=args.batch_size,
shuffle=False,
num_workers=int(args.workers))
num_classes = 16
num_part = 50
log.info(len_training=len(train_ds), len_testing=len(test_ds))
log.info(num_classes=num_classes, num_part=num_part)
if args.model_name == 'pointnet':
model = PointNetDenseCls(cat_num=num_classes, part_num=num_part)
else:
model = PointNet2PartSegMsg_one_hot(num_part)
torch.backends.cudnn.benchmark = True
model = torch.nn.DataParallel(model).cuda()
log.debug('Using gpu:', args.gpu)
if args.pretrain is not None and args.pretrain != 'None':
log.debug('Use pretrain model...')
model.load_state_dict(torch.load(args.pretrain))
init_epoch = int(args.pretrain[:-4].split('-')[-1])
log.debug('start epoch from', init_epoch)
else:
log.debug('Training from scratch')
init_epoch = 0
if args.optimizer == 'SGD':
optimizer = torch.optim.SGD(model.parameters(), lr=0.01, momentum=0.9)
elif args.optimizer == 'Adam':
optimizer = torch.optim.Adam(model.parameters(),
lr=args.learning_rate,
betas=(0.9, 0.999),
eps=1e-08,
weight_decay=args.decay_rate)
scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
step_size=20,
gamma=0.5)
history = {'loss': []}
best_acc = 0
best_class_avg_iou = 0
best_inctance_avg_iou = 0
LEARNING_RATE_CLIP = 1e-5
# criterion = PointNetLoss()
def feature_transform_reguliarzer(trans):
d = trans.size()[1]
I = torch.eye(d)[None, :, :]
if trans.is_cuda:
I = I.cuda()
loss = torch.mean(
torch.norm(torch.bmm(trans,
trans.transpose(2, 1) - I), dim=(1, 2)))
return loss
def PointNet_Loss(labels_pred, label, seg_pred, seg, trans_feat):
mat_diff_loss_scale = 0.001
weight = 1
seg_loss = F.nll_loss(seg_pred, seg)
mat_diff_loss = feature_transform_reguliarzer(trans_feat)
label_loss = F.nll_loss(labels_pred, label)
loss = weight * seg_loss + (
1 - weight) * label_loss + mat_diff_loss * mat_diff_loss_scale
return loss, seg_loss, label_loss
for epoch in range(init_epoch, args.epoch):
scheduler.step()
lr = max(optimizer.param_groups[0]['lr'], LEARNING_RATE_CLIP)
log.info(job='partseg',
model=args.model_name,
gpu=args.gpu,
epoch='%d/%s' % (epoch, args.epoch),
lr=lr)
for param_group in optimizer.param_groups:
param_group['lr'] = lr
for i, data in tqdm(enumerate(dataloader, 0),
total=len(dataloader),
smoothing=0.9):
points, label, target, norm_plt = data
points, label, target = points.float(), label.long(), target.long()
points = points.transpose(2, 1)
norm_plt = norm_plt.transpose(2, 1)
points, label, target, norm_plt = points.cuda(), label.squeeze(
).cuda(), target.cuda(), norm_plt.cuda()
optimizer.zero_grad()
model = model.train()
if args.model_name == 'pointnet':
labels_pred, seg_pred, trans_feat = model(
points, to_categorical(label, 16))
seg_pred = seg_pred.contiguous().view(-1, num_part)
target = target.view(-1, 1)[:, 0]
# loss, seg_loss, label_loss = criterion(labels_pred, label, seg_pred, target, trans_feat)
loss, seg_loss, label_loss = PointNet_Loss(
labels_pred, label, seg_pred, target, trans_feat)
else:
seg_pred = model(points, norm_plt, to_categorical(label, 16))
seg_pred = seg_pred.contiguous().view(-1, num_part)
target = target.view(-1, 1)[:, 0]
loss = F.nll_loss(seg_pred, target)
history['loss'].append(loss.cpu().data.numpy())
loss.backward()
optimizer.step()
log.debug('clear cuda cache')
torch.cuda.empty_cache()
test_metrics, test_hist_acc, cat_mean_iou = test_partseg(
model.eval(),
testdataloader,
label_id_to_name,
args.model_name,
num_part,
)
save_model = False
if test_metrics['accuracy'] > best_acc:
best_acc = test_metrics['accuracy']
if test_metrics['class_avg_iou'] > best_class_avg_iou:
best_class_avg_iou = test_metrics['class_avg_iou']
if test_metrics['inctance_avg_iou'] > best_inctance_avg_iou:
best_inctance_avg_iou = test_metrics['inctance_avg_iou']
save_model = True
if save_model:
fn_pth = 'partseg-%s-%.5f-%04d.pth' % (
args.model_name, best_inctance_avg_iou, epoch)
log.info('Save model...', fn=fn_pth)
torch.save(model.state_dict(),
os.path.join(checkpoints_dir, fn_pth))
log.info(cat_mean_iou)
else:
log.info('No need to save model')
log.warn('Curr',
accuracy=test_metrics['accuracy'],
class_avg_mIOU=test_metrics['class_avg_iou'],
inctance_avg_mIOU=test_metrics['inctance_avg_iou'])
log.warn('Best',
accuracy=best_acc,
class_avg_mIOU=best_class_avg_iou,
inctance_avg_mIOU=best_inctance_avg_iou)