def __init__(self, configer):
self.configer = configer
self.batch_time = AverageMeter()
self.data_time = AverageMeter()
self.train_schedule_loss = AverageMeter()
self.train_losses = AverageMeter()
self.train_loss_heatmap = AverageMeter()
self.train_loss_associate = AverageMeter()
self.val_losses = AverageMeter()
self.val_loss_heatmap = AverageMeter()
self.val_loss_associate = AverageMeter()
self.pose_visualizer = PoseVisualizer(configer)
self.pose_loss_manager = LossManager(configer)
self.pose_model_manager = ModelManager(configer)
self.pose_data_loader = DataLoader(configer)
self.heatmap_generator = HeatmapGenerator(configer)
self.paf_generator = PafGenerator(configer)
self.pose_net = None
self.train_loader = None
self.val_loader = None
self.optimizer = None
self.scheduler = None
self.runner_state = dict()
self._init_model()
def __init__(self, configer):
self.configer = configer
self.batch_time = AverageMeter()
self.data_time = AverageMeter()
self.train_losses = AverageMeter()
self.val_losses = AverageMeter()
self.cls_loss_manager = LossManager(configer)
self.cls_model_manager = ClsModelManager(configer)
self.cls_data_loader = DataLoader(configer)
self.cls_running_score = ClsRunningScore(configer)
self.cls_net = None
self.train_loader = None
self.val_loader = None
self.optimizer = None
self.scheduler = None
self.runner_state = dict()
self._init_model()
def __init__(self, configer):
self.configer = configer
self.batch_time = AverageMeter()
self.data_time = AverageMeter()
self.train_losses = AverageMeter()
self.val_losses = AverageMeter()
self.seg_running_score = SegRunningScore(configer)
self.seg_visualizer = SegVisualizer(configer)
self.seg_loss_manager = LossManager(configer)
self.module_runner = ModuleRunner(configer)
self.seg_model_manager = ModelManager(configer)
self.seg_data_loader = DataLoader(configer)
self.optim_scheduler = OptimScheduler(configer)
self.seg_net = None
self.train_loader = None
self.val_loader = None
self.optimizer = None
self.scheduler = None
self._init_model()
def __init__(self, configer):
self.configer = configer
self.batch_time = AverageMeter()
self.data_time = AverageMeter()
self.train_losses = AverageMeter()
self.val_losses = AverageMeter()
self.det_visualizer = DetVisualizer(configer)
self.det_loss_manager = LossManager(configer)
self.det_model_manager = DetModelManager(configer)
self.det_data_loader = DataLoader(configer)
self.yolo_detection_layer = YOLODetectionLayer(configer)
self.yolo_target_generator = YOLOTargetGenerator(configer)
self.det_running_score = DetRunningScore(configer)
self.det_net = None
self.train_loader = None
self.val_loader = None
self.optimizer = None
self.scheduler = None
self.runner_state = dict()
self._init_model()
def __init__(self, configer):
self.configer = configer
self.batch_time = AverageMeter()
self.data_time = AverageMeter()
self.train_losses = AverageMeter()
self.val_losses = AverageMeter()
self.det_visualizer = DetVisualizer(configer)
self.det_loss_manager = LossManager(configer)
self.det_model_manager = ModelManager(configer)
self.det_data_loader = DataLoader(configer)
self.fr_priorbox_layer = FRPriorBoxLayer(configer)
self.det_running_score = DetRunningScore(configer)
self.det_net = None
self.train_loader = None
self.val_loader = None
self.optimizer = None
self.scheduler = None
self.runner_state = dict()
self._init_model()
class OpenPose(object):
"""
The class for Pose Estimation. Include train, val, test & predict.
"""
def __init__(self, configer):
self.configer = configer
self.batch_time = AverageMeter()
self.data_time = AverageMeter()
self.train_schedule_loss = AverageMeter()
self.train_losses = AverageMeter()
self.train_loss_heatmap = AverageMeter()
self.train_loss_associate = AverageMeter()
self.val_losses = AverageMeter()
self.val_loss_heatmap = AverageMeter()
self.val_loss_associate = AverageMeter()
self.pose_visualizer = PoseVisualizer(configer)
self.pose_loss_manager = LossManager(configer)
self.pose_model_manager = ModelManager(configer)
self.pose_data_loader = DataLoader(configer)
self.heatmap_generator = HeatmapGenerator(configer)
self.paf_generator = PafGenerator(configer)
self.pose_net = None
self.train_loader = None
self.val_loader = None
self.optimizer = None
self.scheduler = None
self.runner_state = dict()
self._init_model()
def _init_model(self):
self.pose_net = self.pose_model_manager.multi_pose_detector()
self.pose_net = RunnerHelper.load_net(self, self.pose_net)
self.optimizer, self.scheduler = Trainer.init(self,
self._get_parameters())
self.train_loader = self.pose_data_loader.get_trainloader()
self.val_loader = self.pose_data_loader.get_valloader()
self.weights = self.configer.get('network', 'loss_weights')
self.mse_loss = self.pose_loss_manager.get_pose_loss()
def _get_parameters(self):
lr_1 = []
lr_2 = []
params_dict = dict(self.pose_net.named_parameters())
for key, value in params_dict.items():
if 'backbone' not in key:
lr_2.append(value)
else:
lr_1.append(value)
params = [
{
'params': lr_1,
'lr': self.configer.get('lr', 'base_lr'),
'weight_decay': 0.0
},
{
'params': lr_2,
'lr': self.configer.get('lr', 'base_lr'),
'weight_decay': 0.0
},
]
return params
def train(self):
"""
Train function of every epoch during train phase.
"""
self.pose_net.train()
start_time = time.time()
# Adjust the learning rate after every epoch.
self.runner_state['epoch'] += 1
self.scheduler.step(self.train_schedule_loss.avg,
epoch=self.configer.get('epoch'))
self.train_schedule_loss.reset()
# data_tuple: (inputs, heatmap, maskmap, vecmap)
for i, data_dict in enumerate(self.train_loader):
inputs = data_dict['img']
maskmap = data_dict['maskmap']
heatmap = data_dict['heatmap']
vecmap = data_dict['vecmap']
self.data_time.update(time.time() - start_time)
# Change the data type.
inputs, heatmap, maskmap, vecmap = RunnerHelper.to_device(
self, inputs, heatmap, maskmap, vecmap)
# Forward pass.
paf_out, heatmap_out = self.pose_net(inputs)
# Compute the loss of the train batch & backward.
loss_heatmap = self.mse_loss(heatmap_out,
heatmap,
mask=maskmap,
weights=self.weights)
loss_associate = self.mse_loss(paf_out,
vecmap,
mask=maskmap,
weights=self.weights)
loss = 2.0 * loss_heatmap + loss_associate
self.train_losses.update(loss.item(), inputs.size(0))
self.train_schedule_loss.update(loss.item(), inputs.size(0))
self.train_loss_heatmap.update(loss_heatmap.item(), inputs.size(0))
self.train_loss_associate.update(loss_associate.item(),
inputs.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('Loss Heatmap:{}, Loss Asso: {}'.format(
self.train_loss_heatmap.avg,
self.train_loss_associate.avg))
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()
self.train_loss_heatmap.reset()
self.train_loss_associate.reset()
if self.configer.get('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):
"""
Validation function during the train phase.
"""
self.pose_net.eval()
start_time = time.time()
with torch.no_grad():
for i, data_dict in enumerate(self.val_loader):
inputs = data_dict['img']
maskmap = data_dict['maskmap']
heatmap = data_dict['heatmap']
vecmap = data_dict['vecmap']
# Change the data type.
inputs, heatmap, maskmap, vecmap = RunnerHelper.to_device(
self, inputs, heatmap, maskmap, vecmap)
# Forward pass.
paf_out, heatmap_out = self.pose_net(inputs)
# Compute the loss of the val batch.
loss_heatmap = self.mse_loss(heatmap_out[-1], heatmap, maskmap)
loss_associate = self.mse_loss(paf_out[-1], vecmap, maskmap)
loss = 2.0 * loss_heatmap + loss_associate
self.val_losses.update(loss.item(), inputs.size(0))
self.val_loss_heatmap.update(loss_heatmap.item(),
inputs.size(0))
self.val_loss_associate.update(loss_associate.item(),
inputs.size(0))
# Update the vars of the val phase.
self.batch_time.update(time.time() - start_time)
start_time = time.time()
self.runner_state['val_loss'] = self.val_losses.avg
RunnerHelper.save_net(self,
self.pose_net,
val_loss=self.val_losses.avg)
Log.info('Loss Heatmap:{}, Loss Asso: {}'.format(
self.val_loss_heatmap.avg, self.val_loss_associate.avg))
# 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))
self.batch_time.reset()
self.val_losses.reset()
self.val_loss_heatmap.reset()
self.val_loss_associate.reset()
self.pose_net.train()
class Trainer(object):
"""
The class for Pose Estimation. Include train, val, val & predict.
"""
def __init__(self, configer):
self.configer = configer
self.batch_time = AverageMeter()
self.data_time = AverageMeter()
self.train_losses = AverageMeter()
self.val_losses = AverageMeter()
self.seg_running_score = SegRunningScore(configer)
self.seg_visualizer = SegVisualizer(configer)
self.seg_loss_manager = LossManager(configer)
self.module_runner = ModuleRunner(configer)
self.seg_model_manager = ModelManager(configer)
self.seg_data_loader = DataLoader(configer)
self.optim_scheduler = OptimScheduler(configer)
self.seg_net = None
self.train_loader = None
self.val_loader = None
self.optimizer = None
self.scheduler = None
self._init_model()
def _init_model(self):
self.seg_net = self.seg_model_manager.semantic_segmentor()
self.seg_net = self.module_runner.load_net(self.seg_net)
Log.info('Params Group Method: {}'.format(
self.configer.get('optim', 'group_method')))
if self.configer.get('optim', 'group_method') == 'decay':
params_group = self.group_weight(self.seg_net)
else:
assert self.configer.get('optim', 'group_method') is None
params_group = self._get_parameters()
self.optimizer, self.scheduler = self.optim_scheduler.init_optimizer(
params_group)
self.train_loader = self.seg_data_loader.get_trainloader()
self.val_loader = self.seg_data_loader.get_valloader()
self.pixel_loss = self.seg_loss_manager.get_seg_loss()
@staticmethod
def group_weight(module):
group_decay = []
group_no_decay = []
for m in module.modules():
if isinstance(m, nn.Linear):
group_decay.append(m.weight)
if m.bias is not None:
group_no_decay.append(m.bias)
elif isinstance(m, nn.modules.conv._ConvNd):
group_decay.append(m.weight)
if m.bias is not None:
group_no_decay.append(m.bias)
else:
if hasattr(m, 'weight'):
group_no_decay.append(m.weight)
if hasattr(m, 'bias'):
group_no_decay.append(m.bias)
assert len(list(
module.parameters())) == len(group_decay) + len(group_no_decay)
groups = [
dict(params=group_decay),
dict(params=group_no_decay, weight_decay=.0)
]
return groups
def _get_parameters(self):
bb_lr = []
nbb_lr = []
params_dict = dict(self.seg_net.named_parameters())
for key, value in params_dict.items():
if 'backbone' not in key:
nbb_lr.append(value)
else:
bb_lr.append(value)
params = [{
'params': bb_lr,
'lr': self.configer.get('lr', 'base_lr')
}, {
'params':
nbb_lr,
'lr':
self.configer.get('lr', 'base_lr') *
self.configer.get('lr', 'nbb_mult')
}]
return params
def __train(self):
"""
Train function of every epoch during train phase.
"""
self.seg_net.train()
start_time = time.time()
for i, data_dict in enumerate(self.train_loader):
if self.configer.get('lr', 'metric') == 'iters':
self.scheduler.step(self.configer.get('iters'))
else:
self.scheduler.step(self.configer.get('epoch'))
if self.configer.get('lr', 'is_warm'):
self.module_runner.warm_lr(self.configer.get('iters'),
self.scheduler,
self.optimizer,
backbone_list=[
0,
])
inputs = data_dict['img']
targets = data_dict['labelmap']
self.data_time.update(time.time() - start_time)
# Change the data type.
# inputs, targets = self.module_runner.to_device(inputs, targets)
# Forward pass.
outputs = self.seg_net(inputs)
# outputs = self.module_utilizer.gather(outputs)
# Compute the loss of the train batch & backward.
loss = self.pixel_loss(outputs,
targets,
gathered=self.configer.get(
'network', 'gathered'))
if self.configer.exists('train', 'loader') and self.configer.get(
'train', 'loader') == 'rs':
batch_size = self.configer.get(
'train', 'batch_size') * self.configer.get(
'train', 'batch_per_gpu')
self.train_losses.update(loss.item(), batch_size)
else:
self.train_losses.update(loss.item(), inputs.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.configer.plus_one('iters')
# Print the log info & reset the states.
if self.configer.get('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.configer.get('epoch'),
self.configer.get('iters'),
self.configer.get('solver', 'display_iter'),
self.module_runner.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('iters') == self.configer.get(
'solver', 'max_iters'):
break
# Check to val the current model.
if self.configer.get('iters') % self.configer.get(
'solver', 'test_interval') == 0:
self.__val()
self.configer.plus_one('epoch')
def __val(self, data_loader=None):
"""
Validation function during the train phase.
"""
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):
inputs = data_dict['img']
targets = data_dict['labelmap']
with torch.no_grad():
# Change the data type.
inputs, targets = self.module_runner.to_device(inputs, targets)
# Forward pass.
outputs = self.seg_net(inputs)
# Compute the loss of the val batch.
loss = self.pixel_loss(outputs,
targets,
gathered=self.configer.get(
'network', 'gathered'))
outputs = self.module_runner.gather(outputs)
self.val_losses.update(loss.item(), inputs.size(0))
self._update_running_score(outputs[-1], data_dict['meta'])
# self.seg_running_score.update(pred.max(1)[1].cpu().numpy(), targets.cpu().numpy())
# Update the vars of the val phase.
self.batch_time.update(time.time() - start_time)
start_time = time.time()
self.configer.update(['performance'],
self.seg_running_score.get_mean_iou())
self.configer.update(['val_loss'], self.val_losses.avg)
self.module_runner.save_net(self.seg_net, save_mode='performance')
self.module_runner.save_net(self.seg_net, save_mode='val_loss')
# 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('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 _update_running_score(self, pred, metas):
pred = pred.permute(0, 2, 3, 1)
for i in range(pred.size(0)):
ori_img_size = metas[i]['ori_img_size']
border_size = metas[i]['border_size']
ori_target = metas[i]['ori_target']
total_logits = cv2.resize(
pred[i, :border_size[1], :border_size[0]].cpu().numpy(),
tuple(ori_img_size),
interpolation=cv2.INTER_CUBIC)
labelmap = np.argmax(total_logits, axis=-1)
self.seg_running_score.update(labelmap[None], ori_target[None])
def train(self):
# cudnn.benchmark = True
if self.configer.get('network',
'resume') is not None and self.configer.get(
'network', 'resume_val'):
self.__val()
while self.configer.get('iters') < self.configer.get(
'solver', 'max_iters'):
self.__train()
self.__val(data_loader=self.seg_data_loader.get_valloader(
dataset='val'))
self.__val(data_loader=self.seg_data_loader.get_valloader(
dataset='train'))
class YOLOv3(object):
"""
The class for YOLO v3. Include train, val, test & predict.
"""
def __init__(self, configer):
self.configer = configer
self.batch_time = AverageMeter()
self.data_time = AverageMeter()
self.train_losses = AverageMeter()
self.val_losses = AverageMeter()
self.det_visualizer = DetVisualizer(configer)
self.det_loss_manager = LossManager(configer)
self.det_model_manager = DetModelManager(configer)
self.det_data_loader = DataLoader(configer)
self.yolo_detection_layer = YOLODetectionLayer(configer)
self.yolo_target_generator = YOLOTargetGenerator(configer)
self.det_running_score = DetRunningScore(configer)
self.det_net = None
self.train_loader = None
self.val_loader = None
self.optimizer = None
self.scheduler = None
self.runner_state = dict()
self._init_model()
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,
self._get_parameters())
self.train_loader = self.det_data_loader.get_trainloader()
self.val_loader = self.det_data_loader.get_valloader()
self.det_loss = self.det_loss_manager.get_det_loss()
def _get_parameters(self):
lr_1 = []
lr_10 = []
params_dict = dict(self.det_net.named_parameters())
for key, value in params_dict.items():
if 'backbone' not in key:
lr_10.append(value)
else:
lr_1.append(value)
params = [{
'params': lr_1,
'lr': self.configer.get('lr', 'base_lr')
}, {
'params': lr_10,
'lr': self.configer.get('lr', 'base_lr') * 10.
}]
return params
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, backbone_list=(0, ))
inputs = data_dict['img']
batch_gt_bboxes = data_dict['bboxes']
batch_gt_labels = data_dict['labels']
input_size = [inputs.size(3), inputs.size(2)]
self.data_time.update(time.time() - start_time)
# Change the data type.
inputs = RunnerHelper.to_device(self, inputs)
# Forward pass.
feat_list, predictions, _ = self.det_net(inputs)
targets, objmask, noobjmask = self.yolo_target_generator(
feat_list, batch_gt_bboxes, batch_gt_labels, input_size)
targets, objmask, noobjmask = RunnerHelper.to_device(
self, targets, objmask, noobjmask)
# Compute the loss of the train batch & backward.
loss = self.det_loss(predictions, targets, objmask, noobjmask)
self.train_losses.update(loss.item(), inputs.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.configer.get('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('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):
"""
Validation function during the train phase.
"""
self.det_net.eval()
start_time = time.time()
with torch.no_grad():
for i, data_dict in enumerate(self.val_loader):
inputs = data_dict['img']
batch_gt_bboxes = data_dict['bboxes']
batch_gt_labels = data_dict['labels']
input_size = [inputs.size(3), inputs.size(2)]
# Forward pass.
inputs = RunnerHelper.to_device(self, inputs)
feat_list, predictions, detections = self.det_net(inputs)
targets, objmask, noobjmask = self.yolo_target_generator(
feat_list, batch_gt_bboxes, batch_gt_labels, input_size)
targets, objmask, noobjmask = RunnerHelper.to_device(
self, targets, objmask, noobjmask)
# Compute the loss of the val batch.
loss = self.det_loss(predictions, targets, objmask, noobjmask)
self.val_losses.update(loss.item(), inputs.size(0))
batch_detections = YOLOv3Test.decode(detections, self.configer,
input_size)
batch_pred_bboxes = self.__get_object_list(
batch_detections, input_size)
self.det_running_score.update(batch_pred_bboxes,
batch_gt_bboxes, batch_gt_labels)
# 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: {}'.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 __get_object_list(self, batch_detections, input_size):
batch_pred_bboxes = list()
for idx, detections in enumerate(batch_detections):
object_list = list()
if detections is not None:
for x1, y1, x2, y2, conf, cls_conf, cls_pred in detections:
xmin = x1.cpu().item()
ymin = y1.cpu().item()
xmax = x2.cpu().item()
ymax = y2.cpu().item()
cf = conf.cpu().item()
cls_pred = cls_pred.cpu().item()
object_list.append([
xmin, ymin, xmax, ymax,
int(cls_pred),
float('%.2f' % cf)
])
batch_pred_bboxes.append(object_list)
return batch_pred_bboxes
class FCNSegmentor(object):
"""
The class for Pose Estimation. Include train, val, val & predict.
"""
def __init__(self, configer):
self.configer = configer
self.batch_time = AverageMeter()
self.data_time = AverageMeter()
self.train_losses = AverageMeter()
self.val_losses = AverageMeter()
self.seg_running_score = SegRunningScore(configer)
self.seg_visualizer = SegVisualizer(configer)
self.seg_loss_manager = LossManager(configer)
self.seg_model_manager = SegModelManager(configer)
self.seg_data_loader = DataLoader(configer)
self.seg_net = None
self.train_loader = None
self.val_loader = None
self.optimizer = None
self.scheduler = None
self.runner_state = dict()
self._init_model()
def _init_model(self):
self.seg_net = self.seg_model_manager.semantic_segmentor()
self.seg_net = RunnerHelper.load_net(self, self.seg_net)
self.optimizer, self.scheduler = Trainer.init(self,
self._get_parameters())
self.train_loader = self.seg_data_loader.get_trainloader()
self.val_loader = self.seg_data_loader.get_valloader()
self.pixel_loss = self.seg_loss_manager.get_seg_loss()
def _get_parameters(self):
lr_1 = []
lr_10 = []
params_dict = dict(self.seg_net.named_parameters())
for key, value in params_dict.items():
if 'backbone' not in key:
lr_10.append(value)
else:
lr_1.append(value)
params = [{
'params': lr_1,
'lr': self.configer.get('lr', 'base_lr')
}, {
'params': lr_10,
'lr': self.configer.get('lr', 'base_lr') * 1.0
}]
return params
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, ))
inputs = data_dict['img']
targets = data_dict['labelmap']
self.data_time.update(time.time() - start_time)
# Change the data type.
inputs, targets = RunnerHelper.to_device(self, inputs, targets)
# Forward pass.
outputs = self.seg_net(inputs)
# outputs = self.module_utilizer.gather(outputs)
# Compute the loss of the train batch & backward.
loss = self.pixel_loss(outputs,
targets,
gathered=self.configer.get(
'network', 'gathered'))
self.train_losses.update(loss.item(), inputs.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.configer.get('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('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()
self.runner_state['epoch'] += 1
def val(self, data_loader=None):
"""
Validation function during the train phase.
"""
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):
inputs = data_dict['img']
targets = data_dict['labelmap']
with torch.no_grad():
# Change the data type.
inputs, targets = RunnerHelper.to_device(self, inputs, targets)
# Forward pass.
outputs = self.seg_net(inputs)
# Compute the loss of the val batch.
loss = self.pixel_loss(outputs,
targets,
gathered=self.configer.get(
'network', 'gathered'))
outputs = RunnerHelper.gather(self, outputs)
self.val_losses.update(loss.item(), inputs.size(0))
self._update_running_score(outputs[-1], 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
RunnerHelper.save_net(
self,
self.seg_net,
performance=self.seg_running_score.get_mean_iou(),
val_loss=self.val_losses.avg)
# 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('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 _update_running_score(self, pred, metas):
pred = pred.permute(0, 2, 3, 1)
for i in range(pred.size(0)):
ori_img_size = metas[i]['ori_img_size']
border_size = metas[i]['border_size']
ori_target = metas[i]['ori_target']
total_logits = cv2.resize(
pred[i, :border_size[1], :border_size[0]].cpu().numpy(),
tuple(ori_img_size),
interpolation=cv2.INTER_CUBIC)
labelmap = np.argmax(total_logits, axis=-1)
self.seg_running_score.update(labelmap[None], ori_target[None])
class FCClassifier(object):
"""
The class for the training phase of Image classification.
"""
def __init__(self, configer):
self.configer = configer
self.batch_time = AverageMeter()
self.data_time = AverageMeter()
self.train_losses = AverageMeter()
self.val_losses = AverageMeter()
self.cls_loss_manager = LossManager(configer)
self.cls_model_manager = ClsModelManager(configer)
self.cls_data_loader = DataLoader(configer)
self.cls_running_score = ClsRunningScore(configer)
self.cls_net = None
self.train_loader = None
self.val_loader = None
self.optimizer = None
self.scheduler = None
self.runner_state = dict()
self._init_model()
def _init_model(self):
self.cls_net = self.cls_model_manager.image_classifier()
self.cls_net = RunnerHelper.load_net(self, self.cls_net)
self.optimizer, self.scheduler = Trainer.init(self,
self._get_parameters())
self.train_loader = self.cls_data_loader.get_trainloader()
self.val_loader = self.cls_data_loader.get_valloader()
self.ce_loss = self.cls_loss_manager.get_cls_loss()
def _get_parameters(self):
return self.cls_net.parameters()
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)
inputs = data_dict['img']
labels = data_dict['label']
self.data_time.update(time.time() - start_time)
# Change the data type.
inputs, labels = RunnerHelper.to_device(self, inputs, labels)
# Forward pass.
outputs = self.cls_net(inputs)
# Compute the loss of the train batch & backward.
loss = self.ce_loss(outputs, labels)
self.train_losses.update(loss.item(), inputs.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 = {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('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):
"""
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):
inputs = data_dict['img']
labels = data_dict['label']
# Change the data type.
inputs, labels = RunnerHelper.to_device(self, inputs, labels)
# Forward pass.
outputs = self.cls_net(inputs)
outputs = RunnerHelper.gather(self, outputs)
# Compute the loss of the val batch.
loss = self.ce_loss(outputs, labels)
self.cls_running_score.update(outputs, labels)
self.val_losses.update(loss.item(), inputs.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,
performance=self.cls_running_score.get_top1_acc())
self.runner_state[
'performance'] = self.cls_running_score.get_top1_acc()
# 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 = {loss.avg:.8f}'.format(loss=self.val_losses))
Log.info('Top1 ACC = {}'.format(
self.cls_running_score.get_top1_acc()))
Log.info('Top5 ACC = {}'.format(
self.cls_running_score.get_top5_acc()))
self.batch_time.reset()
self.val_losses.reset()
self.cls_running_score.reset()
self.cls_net.train()
class ConvPoseMachine(object):
"""
The class for Pose Estimation. Include train, val, val & predict.
"""
def __init__(self, configer):
self.configer = configer
self.batch_time = AverageMeter()
self.data_time = AverageMeter()
self.train_losses = AverageMeter()
self.val_losses = AverageMeter()
self.pose_visualizer = PoseVisualizer(configer)
self.pose_loss_manager = LossManager(configer)
self.pose_model_manager = ModelManager(configer)
self.pose_data_loader = DataLoader(configer)
self.heatmap_generator = HeatmapGenerator(configer)
self.pose_net = None
self.train_loader = None
self.val_loader = None
self.optimizer = None
self.scheduler = None
self.runner_state = dict()
self._init_model()
def _init_model(self):
self.pose_net = self.pose_model_manager.single_pose_detector()
self.pose_net = RunnerHelper.load_net(self, self.pose_net)
self.optimizer, self.scheduler = Trainer.init(self, self._get_parameters())
self.train_loader = self.pose_data_loader.get_trainloader()
self.val_loader = self.pose_data_loader.get_valloader()
self.mse_loss = self.pose_loss_manager.get_pose_loss()
def _get_parameters(self):
return self.pose_net.parameters()
def train(self):
"""
Train function of every epoch during train phase.
"""
self.pose_net.train()
start_time = time.time()
# Adjust the learning rate after every epoch.
self.runner_state['epoch'] += 1
# data_tuple: (inputs, heatmap, maskmap, tagmap, num_objects)
for i, data_dict in enumerate(self.train_loader):
Trainer.update(self)
inputs = data_dict['img']
heatmap = data_dict['heatmap']
self.data_time.update(time.time() - start_time)
# Change the data type.
inputs, heatmap = RunnerHelper.to_device(self, inputs, heatmap)
# self.pose_visualizer.vis_peaks(heatmap[0], inputs[0], name='cpm')
# Forward pass.
outputs = self.pose_net(inputs)
# Compute the loss of the train batch & backward.
loss = self.mse_loss(outputs, heatmap)
self.train_losses.update(loss.item(), inputs.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 = {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('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):
"""
Validation function during the train phase.
"""
self.pose_net.eval()
start_time = time.time()
with torch.no_grad():
for j, data_dict in enumerate(self.val_loader):
inputs = data_dict['img']
heatmap = data_dict['heatmap']
# Change the data type.
inputs, heatmap = RunnerHelper.to_device(self, inputs, heatmap)
# Forward pass.
outputs = self.pose_net(inputs)
# Compute the loss of the val batch.
loss = self.mse_loss(outputs[-1], heatmap)
self.val_losses.update(loss.item(), inputs.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.pose_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))
self.batch_time.reset()
self.val_losses.reset()
self.pose_net.train()