def train(train_loader, model, criterion, optimizer, epoch, logger):
average_meter = AverageMeter()
model.train() # switch to train mode
end = time.time()
batch_num = len(train_loader)
for i, (input, target) in enumerate(train_loader):
# itr_count += 1
input, target = input.cuda(), target.cuda()
# print('input size = ', input.size())
# print('target size = ', target.size())
torch.cuda.synchronize()
data_time = time.time() - end
# compute pred
end = time.time()
with torch.autograd.detect_anomaly():
pred_d, pred_ord = model(input) # @wx 注意输出
target_c = utils.get_labels_sid(
args, target) # using sid, discretize the groundtruth
loss = criterion(pred_ord, target_c)
optimizer.zero_grad()
loss.backward() # compute gradient and do SGD step
optimizer.step()
torch.cuda.synchronize()
gpu_time = time.time() - end
# measure accuracy and record loss
result = Result()
depth = utils.get_depth_sid(args, pred_d)
result.evaluate(depth.data, target.data)
average_meter.update(result, gpu_time, data_time, input.size(0))
end = time.time()
if (i + 1) % args.print_freq == 0:
print('=> output: {}'.format(output_directory))
print('Train Epoch: {0} [{1}/{2}]\t'
't_Data={data_time:.3f}({average.data_time:.3f}) '
't_GPU={gpu_time:.3f}({average.gpu_time:.3f})\n\t'
'Loss={Loss:.5f} '
'RMSE={result.rmse:.2f}({average.rmse:.2f}) '
'RML={result.absrel:.2f}({average.absrel:.2f}) '
'Log10={result.lg10:.3f}({average.lg10:.3f}) '
'Delta1={result.delta1:.3f}({average.delta1:.3f}) '
'Delta2={result.delta2:.3f}({average.delta2:.3f}) '
'Delta3={result.delta3:.3f}({average.delta3:.3f})'.format(
epoch,
i + 1,
len(train_loader),
data_time=data_time,
gpu_time=gpu_time,
Loss=loss.item(),
result=result,
average=average_meter.average()))
current_step = epoch * batch_num + i
logger.add_scalar('Train/RMSE', result.rmse, current_step)
logger.add_scalar('Train/rml', result.absrel, current_step)
logger.add_scalar('Train/Log10', result.lg10, current_step)
logger.add_scalar('Train/Delta1', result.delta1, current_step)
logger.add_scalar('Train/Delta2', result.delta2, current_step)
logger.add_scalar('Train/Delta3', result.delta3, current_step)
avg = average_meter.average()
def validate(val_loader, model, epoch, logger):
average_meter = AverageMeter()
model.eval() # switch to evaluate mode
end = time.time()
skip = len(val_loader) // 9 # save images every skip iters
img_list = []
for i, (input, target) in enumerate(val_loader):
input, target = input.cuda(), target.cuda()
torch.cuda.synchronize()
data_time = time.time() - end
# compute output
end = time.time()
with torch.no_grad():
pred, _ = model(input)
torch.cuda.synchronize()
gpu_time = time.time() - end
# measure accuracy and record loss
result = Result()
pred = utils.get_depth_sid(args, pred)
result.evaluate(pred.data, target.data)
average_meter.update(result, gpu_time, data_time, input.size(0))
end = time.time()
# save 8 images for visualization
rgb = input
if i == 0:
img_merge = utils.merge_into_row(rgb, target, pred)
elif (i < 8 * skip) and (i % skip == 0):
row = utils.merge_into_row(rgb, target, pred)
img_merge = utils.add_row(img_merge, row)
elif i == 8 * skip:
filename = output_directory + '/comparison_' + str(epoch) + '.png'
utils.save_image(img_merge, filename)
if (i + 1) % args.print_freq == 0:
print('Test: [{0}/{1}]\t'
't_GPU={gpu_time:.3f}({average.gpu_time:.3f})\n\t'
'RMSE={result.rmse:.2f}({average.rmse:.2f}) '
'RML={result.absrel:.2f}({average.absrel:.2f}) '
'Log10={result.lg10:.3f}({average.lg10:.3f}) '
'Delta1={result.delta1:.3f}({average.delta1:.3f}) '
'Delta2={result.delta2:.3f}({average.delta2:.3f}) '
'Delta3={result.delta3:.3f}({average.delta3:.3f})'.format(
i + 1,
len(val_loader),
gpu_time=gpu_time,
result=result,
average=average_meter.average()))
avg = average_meter.average()
print('\n*\n'
'RMSE={average.rmse:.3f}\n'
'Rel={average.absrel:.3f}\n'
'Log10={average.lg10:.3f}\n'
'Delta1={average.delta1:.3f}\n'
'Delta2={average.delta2:.3f}\n'
'Delta3={average.delta3:.3f}\n'
't_GPU={time:.3f}\n'.format(average=avg, time=avg.gpu_time))
logger.add_scalar('Test/rmse', avg.rmse, epoch)
logger.add_scalar('Test/Rel', avg.absrel, epoch)
logger.add_scalar('Test/log10', avg.lg10, epoch)
logger.add_scalar('Test/Delta1', avg.delta1, epoch)
logger.add_scalar('Test/Delta2', avg.delta2, epoch)
logger.add_scalar('Test/Delta3', avg.delta3, epoch)
return avg, img_merge
def train(train_loader, model, criterion, optimizer, epoch, logger, device,
opts, iteration):
average_meter = AverageMeter()
model.train() # switch to train mode
end = time.time()
batch_num = len(train_loader)
for i, (input, target) in enumerate(train_loader):
if i < iteration:
continue
input = input.to(device)
target = target.to(device)
if torch.cuda.is_available():
torch.cuda.synchronize()
data_time = time.time() - end
# compute pred
end = time.time()
with torch.autograd.detect_anomaly():
pred_d, pred_ord = model(input)
target_c = utils.get_labels_sid(
opts, target, device) # using sid, discretize the groundtruth
loss = criterion(pred_ord, target_c)
optimizer.zero_grad()
loss.backward() # compute gradient and do SGD step
optimizer.step()
if torch.cuda.is_available():
torch.cuda.synchronize()
gpu_time = time.time() - end
# measure accuracy and record loss
result = Result()
depth = utils.get_depth_sid(opts, pred_d, device)
result.evaluate(depth.data, target.data)
average_meter.update(result, gpu_time, data_time, input.size(0))
end = time.time()
if (i + 1) % opts.save_freq == 0:
utils.save_checkpoint(
{
'args': opts,
'epoch': epoch,
'model': model,
'best_result': best_result,
'optimizer': optimizer,
'iteration': i + 1
}, False, epoch, output_directory)
if (i + 1) % opts.print_freq == 0:
print('Train Epoch: {0} [{1}/{2}]\t'
't_Data={data_time:.3f}({average.data_time:.3f}) '
't_GPU={gpu_time:.3f}({average.gpu_time:.3f})\n\t'
'Loss={Loss:.5f} '
'RMSE={result.rmse:.2f}({average.rmse:.2f}) '
'RML={result.absrel:.2f}({average.absrel:.2f}) '
'Log10={result.lg10:.3f}({average.lg10:.3f}) '
'Delta1={result.delta1:.3f}({average.delta1:.3f}) '
'Delta2={result.delta2:.3f}({average.delta2:.3f}) '
'Delta3={result.delta3:.3f}({average.delta3:.3f})'.format(
epoch,
i + 1,
len(train_loader),
data_time=data_time,
gpu_time=gpu_time,
Loss=loss.item(),
result=result,
average=average_meter.average()))
current_step = epoch * batch_num + i
logger.add_scalar('Train/RMSE', result.rmse, current_step)
logger.add_scalar('Train/rml', result.absrel, current_step)
logger.add_scalar('Train/Log10', result.lg10, current_step)
logger.add_scalar('Train/Delta1', result.delta1, current_step)
logger.add_scalar('Train/Delta2', result.delta2, current_step)
logger.add_scalar('Train/Delta3', result.delta3, current_step)
print("GPU:", torch.cuda.memory_allocated())
if torch.cuda.is_available():
torch.cuda.empty_cache()
avg = average_meter.average()
