def val(self):
"""
Validation function during the train phase.
"""
self.cls_net.eval()
start_time = time.time()
with torch.no_grad():
for j, data_dict in enumerate(self.val_loader):
# Forward pass.
data_dict = RunnerHelper.to_device(self, data_dict)
out = self.cls_net(data_dict)
loss_dict = self.loss(out)
out_dict, label_dict, _ = RunnerHelper.gather(self, out)
self.running_score.update(out_dict, label_dict)
self.val_losses.update({key: loss.item() for key, loss in loss_dict.items()}, data_dict['img'].size(0))
# Update the vars of the val phase.
self.batch_time.update(time.time() - start_time)
start_time = time.time()
RunnerHelper.save_net(self, self.cls_net)
# Print the log info & reset the states.
Log.info('Test Time {batch_time.sum:.3f}s'.format(batch_time=self.batch_time))
Log.info('TestLoss = {}'.format(self.val_losses.info()))
Log.info('Top1 ACC = {}'.format(RunnerHelper.dist_avg(self, self.running_score.get_top1_acc())))
Log.info('Top3 ACC = {}'.format(RunnerHelper.dist_avg(self, self.running_score.get_top3_acc())))
Log.info('Top5 ACC = {}'.format(RunnerHelper.dist_avg(self, self.running_score.get_top5_acc())))
self.batch_time.reset()
self.batch_time.reset()
self.val_losses.reset()
self.running_score.reset()
self.cls_net.train()
def test(self, test_dir, out_dir):
for _, data_dict in enumerate(
self.test_loader.get_testloader(test_dir=test_dir)):
data_dict['testing'] = True
data_dict = RunnerHelper.to_device(self, data_dict)
out_dict = self.det_net(data_dict)
meta_list = DCHelper.tolist(data_dict['meta'])
test_indices_and_rois, test_roi_locs, test_roi_scores, test_rois_num = out_dict[
'test_group']
batch_detections = self.decode(test_roi_locs, test_roi_scores,
test_indices_and_rois,
test_rois_num, self.configer,
meta_list)
for i in range(len(meta_list)):
ori_img_bgr = ImageHelper.read_image(meta_list[i]['img_path'],
tool='cv2',
mode='BGR')
json_dict = self.__get_info_tree(batch_detections[i])
image_canvas = self.det_parser.draw_bboxes(
ori_img_bgr.copy(),
json_dict,
conf_threshold=self.configer.get('res', 'vis_conf_thre'))
ImageHelper.save(image_canvas,
save_path=os.path.join(
out_dir, 'vis/{}.png'.format(
meta_list[i]['filename'])))
Log.info('Json Path: {}'.format(
os.path.join(
out_dir,
'json/{}.json'.format(meta_list[i]['filename']))))
JsonHelper.save_file(json_dict,
save_path=os.path.join(
out_dir, 'json/{}.json'.format(
meta_list[i]['filename'])))
def train(self):
"""
Train function of every epoch during train phase.
"""
self.cls_net.train()
start_time = time.time()
# Adjust the learning rate after every epoch.
self.runner_state['epoch'] += 1
for i, data_dict in enumerate(self.train_loader):
Trainer.update(self, warm_list=(0, 1),
warm_lr_list=(self.solver_dict['lr']['base_lr']*self.configer.get('solver.lr.bb_lr_scale'),
self.solver_dict['lr']['base_lr']),
solver_dict=self.solver_dict)
self.data_time.update(time.time() - start_time)
data_dict = RunnerHelper.to_device(self, data_dict)
# Forward pass.
out = self.cls_net(data_dict)
loss_dict = self.loss(out)
# Compute the loss of the train batch & backward.
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()
if self.configer.get('network', 'clip_grad', default=False):
RunnerHelper.clip_grad(self.cls_net, 10.)
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.solver_dict['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.solver_dict['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.solver_dict['lr']['metric'] == 'iters' and self.runner_state['iters'] == self.solver_dict['max_iters']:
break
if self.runner_state['iters'] % self.solver_dict['save_iters'] == 0 and self.configer.get('local_rank') == 0:
RunnerHelper.save_net(self, self.cls_net)
# Check to val the current model.
if self.runner_state['iters'] % self.solver_dict['test_interval'] == 0:
self.val()
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
for i, data_dict in enumerate(self.train_loader):
Trainer.update(self, 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.det_net(data_dict)
loss_dict = self.det_loss(out)
loss = loss_dict['loss'].mean()
self.train_losses.update(loss.item(),
len(DCHelper.tolist(data_dict['meta'])))
self.optimizer.zero_grad()
loss.backward()
RunnerHelper.clip_grad(self.det_net, 10.)
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 val(self, data_loader=None):
"""
Validation function during the train phase.
"""
if self.configer.get('local_rank') != 0:
return
self.seg_net.eval()
start_time = time.time()
data_loader = self.val_loader if data_loader is None else data_loader
for j, data_dict in enumerate(data_loader):
data_dict = RunnerHelper.to_device(self, data_dict)
with torch.no_grad():
# Forward pass.
out = self.seg_net(data_dict)
loss_dict = self.loss(out)
# Compute the loss of the val batch.
out_dict, _ = RunnerHelper.gather(self, out)
self.val_losses.update(
{key: loss.item()
for key, loss in loss_dict.items()}, data_dict['img'].size(0))
self._update_running_score(out_dict['out'],
DCHelper.tolist(data_dict['meta']))
# Update the vars of the val phase.
self.batch_time.update(time.time() - start_time)
start_time = time.time()
self.runner_state['performance'] = self.seg_running_score.get_mean_iou(
)
self.runner_state['val_loss'] = self.val_losses.avg['loss']
RunnerHelper.save_net(
self,
self.seg_net,
performance=self.seg_running_score.get_mean_iou(),
val_loss=self.val_losses.avg['loss'])
# Print the log info & reset the states.
Log.info('Test Time {batch_time.sum:.3f}s, ({batch_time.avg:.3f})\t'
'Loss = {0}\n'.format(self.val_losses.info(),
batch_time=self.batch_time))
Log.info('Mean IOU: {}\n'.format(
self.seg_running_score.get_mean_iou()))
Log.info('Pixel ACC: {}\n'.format(
self.seg_running_score.get_pixel_acc()))
self.batch_time.reset()
self.val_losses.reset()
self.seg_running_score.reset()
self.seg_net.train()
def val(self):
"""
Validation function during the train phase.
"""
self.det_net.eval()
start_time = time.time()
with torch.no_grad():
for j, data_dict in enumerate(self.val_loader):
# Forward pass.
data_dict = RunnerHelper.to_device(self, data_dict)
out = self.det_net(data_dict)
loss_dict = self.det_loss(out)
# Compute the loss of the train batch & backward.
loss = loss_dict['loss'].mean()
out_dict, _ = RunnerHelper.gather(self, out)
self.val_losses.update(loss.item(),
len(DCHelper.tolist(data_dict['meta'])))
test_indices_and_rois, test_roi_locs, test_roi_scores, test_rois_num = out_dict[
'test_group']
batch_detections = FastRCNNTest.decode(
test_roi_locs, test_roi_scores, test_indices_and_rois,
test_rois_num, self.configer,
DCHelper.tolist(data_dict['meta']))
batch_pred_bboxes = self.__get_object_list(batch_detections)
self.det_running_score.update(batch_pred_bboxes, [
item['ori_bboxes']
for item in DCHelper.tolist(data_dict['meta'])
], [
item['ori_labels']
for item in DCHelper.tolist(data_dict['meta'])
])
# Update the vars of the val phase.
self.batch_time.update(time.time() - start_time)
start_time = time.time()
RunnerHelper.save_net(self,
self.det_net,
iters=self.runner_state['iters'])
# Print the log info & reset the states.
Log.info(
'Test Time {batch_time.sum:.3f}s, ({batch_time.avg:.3f})\t'
'Loss {loss.avg:.8f}\n'.format(batch_time=self.batch_time,
loss=self.val_losses))
Log.info('Val mAP: {}\n'.format(self.det_running_score.get_mAP()))
self.det_running_score.reset()
self.batch_time.reset()
self.val_losses.reset()
self.det_net.train()
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,
backbone_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()
#out.detach().cpu()
torch.cuda.empty_cache()
# 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
