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 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, ), backbone_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) loss = out_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 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 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) batch_gt_bboxes = data_dict['bboxes'] batch_gt_labels = data_dict['labels'] metas = data_dict['meta'] data_dict['bboxes'] = DCHelper.todc( batch_gt_bboxes, gpu_list=self.configer.get('gpu'), cpu_only=True) data_dict['labels'] = DCHelper.todc( batch_gt_labels, gpu_list=self.configer.get('gpu'), cpu_only=True) data_dict['meta'] = DCHelper.todc( metas, gpu_list=self.configer.get('gpu'), cpu_only=True) self.data_time.update(time.time() - start_time) # Forward pass. loss = self.det_net(data_dict) loss = loss.mean() self.train_losses.update(loss.item(), data_dict['img'].size(0)) 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('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.pose_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, backbone_list=(0, ), solver_dict=self.configer.get('solver')) self.data_time.update(time.time() - start_time) # Forward pass. out_dict = self.pose_net(data_dict) # Compute the loss of the train batch & backward. loss_dict = self.mse_loss(out_dict, data_dict, gathered=self.configer.get( 'network', 'gathered')) loss = loss_dict['loss'] 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('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('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()