def train(self):
"""
Train function of every epoch during train phase.
"""
self.det_net.train()
start_time = time.time()
# Adjust the learning rate after every epoch.
self.runner_state['epoch'] += 1
# data_tuple: (inputs, heatmap, maskmap, vecmap)
for i, data_dict in enumerate(self.train_loader):
Trainer.update(self,
warm_list=(0, ),
warm_lr_list=(self.configer.get('solver',
'lr')['base_lr'], ),
solver_dict=self.configer.get('solver'))
self.data_time.update(time.time() - start_time)
# Forward pass.
out_dict = self.det_net(data_dict)
# Compute the loss of the train batch & backward.
loss = out_dict['loss'].mean()
self.train_losses.update(loss.item(),
len(DCHelper.tolist(data_dict['meta'])))
self.optimizer.zero_grad()
loss.backward()
self.optimizer.step()
# Update the vars of the train phase.
self.batch_time.update(time.time() - start_time)
start_time = time.time()
self.runner_state['iters'] += 1
# Print the log info & reset the states.
if self.runner_state['iters'] % self.configer.get(
'solver', 'display_iter') == 0:
Log.info(
'Train Epoch: {0}\tTrain Iteration: {1}\t'
'Time {batch_time.sum:.3f}s / {2}iters, ({batch_time.avg:.3f})\t'
'Data load {data_time.sum:.3f}s / {2}iters, ({data_time.avg:3f})\n'
'Learning rate = {3}\tLoss = {loss.val:.8f} (ave = {loss.avg:.8f})\n'
.format(self.runner_state['epoch'],
self.runner_state['iters'],
self.configer.get('solver', 'display_iter'),
RunnerHelper.get_lr(self.optimizer),
batch_time=self.batch_time,
data_time=self.data_time,
loss=self.train_losses))
self.batch_time.reset()
self.data_time.reset()
self.train_losses.reset()
if self.configer.get('solver', 'lr')['metric'] == 'iters' \
and self.runner_state['iters'] == self.configer.get('solver', 'max_iters'):
break
# Check to val the current model.
if self.runner_state['iters'] % self.configer.get(
'solver', 'test_interval') == 0:
self.val()
def train(self):
"""
Train function of every epoch during train phase.
"""
self.seg_net.train()
start_time = time.time()
# Adjust the learning rate after every epoch.
for i, data_dict in enumerate(self.train_loader):
Trainer.update(self, warm_list=(0,), solver_dict=self.configer.get('solver'))
self.data_time.update(time.time() - start_time)
# Forward pass.
data_dict = RunnerHelper.to_device(self, data_dict)
out = self.seg_net(data_dict)
# Compute the loss of the train batch & backward.
loss_dict = self.loss(out)
loss = loss_dict['loss']
self.train_losses.update({key: loss.item() for key, loss in loss_dict.items()}, data_dict['img'].size(0))
self.optimizer.zero_grad()
loss.backward()
self.optimizer.step()
# Update the vars of the train phase.
self.batch_time.update(time.time() - start_time)
start_time = time.time()
self.runner_state['iters'] += 1
# Print the log info & reset the states.
if self.runner_state['iters'] % self.configer.get('solver', 'display_iter') == 0:
Log.info('Train Epoch: {0}\tTrain Iteration: {1}\t'
'Time {batch_time.sum:.3f}s / {2}iters, ({batch_time.avg:.3f})\t'
'Data load {data_time.sum:.3f}s / {2}iters, ({data_time.avg:3f})\n'
'Learning rate = {4}\tLoss = {3}\n'.format(
self.runner_state['epoch'], self.runner_state['iters'],
self.configer.get('solver', 'display_iter'), self.train_losses.info(),
RunnerHelper.get_lr(self.optimizer), batch_time=self.batch_time, data_time=self.data_time))
self.batch_time.reset()
self.data_time.reset()
self.train_losses.reset()
if self.runner_state['iters'] % self.configer.get('solver.save_iters') == 0 \
and self.configer.get('local_rank') == 0:
RunnerHelper.save_net(self, self.seg_net)
if self.configer.get('solver', 'lr')['metric'] == 'iters' \
and self.runner_state['iters'] == self.configer.get('solver', 'max_iters'):
break
# Check to val the current model.
if self.runner_state['iters'] % self.configer.get('solver', 'test_interval') == 0 \
and not self.configer.get('network.distributed'):
self.val()
self.runner_state['epoch'] += 1
def _init_model(self):
self.gan_net = self.model_manager.gan_model()
self.gan_net = RunnerHelper.load_net(self, self.gan_net)
self.optimizer_G, self.scheduler_G = Trainer.init(
self._get_parameters()[0], self.configer.get('solver'))
self.optimizer_D, self.scheduler_D = Trainer.init(
self._get_parameters()[1], self.configer.get('solver'))
self.train_loader = self.seg_data_loader.get_trainloader()
self.val_loader = self.seg_data_loader.get_valloader()
def _init_model(self):
self.det_net = self.det_model_manager.object_detector()
self.det_net = RunnerHelper.load_net(self, self.det_net)
self.optimizer, self.scheduler = Trainer.init(
self._get_parameters(), self.configer.get('solver'))
self.train_loader = self.det_data_loader.get_trainloader()
self.val_loader = self.det_data_loader.get_valloader()
def _init_model(self):
# torch.multiprocessing.set_sharing_strategy('file_system')
self.det_net = self.det_model_manager.object_detector()
self.det_net = RunnerHelper.load_net(self, self.det_net)
self.optimizer, self.scheduler = Trainer.init(
self._get_parameters(), self.configer.get('solver'))
self.train_loader = self.det_data_loader.get_trainloader()
self.val_loader = self.det_data_loader.get_valloader()
self.det_loss = self.det_model_manager.get_det_loss()
def __init__(self, configer):
self.configer = configer
self.runner_state = dict()
self.batch_time = AverageMeter()
self.data_time = AverageMeter()
self.train_losses = DictAverageMeter()
self.val_losses = DictAverageMeter()
self.cls_model_manager = ModelManager(configer)
self.cls_data_loader = DataLoader(configer)
self.running_score = ClsRunningScore(configer)
self.cls_net = self.cls_model_manager.get_cls_model()
self.solver_dict = self.configer.get('solver')
self.cls_net = RunnerHelper.load_net(self, self.cls_net)
self.optimizer, self.scheduler = Trainer.init(self._get_parameters(),
self.solver_dict)
self.train_loader = self.cls_data_loader.get_trainloader()
self.val_loader = self.cls_data_loader.get_valloader()
self.loss = self.cls_model_manager.get_cls_loss()