def validation_loop(self, epoch, valid_loader, valid_set, confm_list):
for vi, data in tqdm(enumerate(valid_loader), desc="Validation", total=len(valid_loader),
file=sys.stdout):
# Read data
inputs, gts = data
n_images, w, h, c = inputs.size()
inputs = Variable(inputs).cuda()
gts = Variable(gts).cuda()
# Predict model
with torch.no_grad():
outputs = self.model.net(inputs)
predictions = outputs.data.max(1)[1].cpu().numpy()
# Compute batch stats
self.val_loss.update(float(self.model.loss(outputs, gts).cpu().item() / n_images), n_images)
confm = compute_confusion_matrix(predictions, gts.cpu().data.numpy(), self.cf.num_classes,
self.cf.void_class)
confm_list = confm_list + confm
# Save epoch stats
self.stats.val.conf_m = confm_list
if not self.cf.normalize_loss:
self.stats.val.loss = self.val_loss.avg
else:
self.stats.val.loss = self.val_loss.avg
# Save predictions and generate overlaping
self.update_tensorboard(inputs.cpu(), gts.cpu(),
predictions, epoch, range(vi * self.cf.valid_batch_size,
vi * self.cf.valid_batch_size +
np.shape(predictions)[0]),
valid_set.num_images)
def training_loop(self, epoch, train_loader):
# Train epoch
for i, data in tqdm(enumerate(train_loader), desc="Epoch {}/{}".format(epoch, self.cf.epochs),
total=len(train_loader), file=sys.stdout):
# Read Data
inputs, labels = data
n, c, w, h = inputs.size()
inputs = Variable(inputs).cuda()
self.inputs = inputs
self.labels = Variable(labels).cuda()
# Predict model
self.model.optimizer.zero_grad()
self.outputs = self.model.net(inputs)
predictions = self.outputs.data.max(1)[1].cpu().numpy()
# Compute gradients
self.compute_gradients()
# Compute batch stats
self.train_loss.update(float(self.loss.cpu().item()), n)
confm = compute_confusion_matrix(predictions, self.labels.cpu().data.numpy(), self.cf.num_classes,
self.cf.void_class)
self.confm_list = self.confm_list + confm
if self.cf.normalize_loss:
self.stats.train.loss = self.train_loss.avg
else:
self.stats.train.loss = self.train_loss.avg
if not self.cf.debug:
# Save stats
self.save_stats_batch((epoch - 1) * self.train_num_batches + i)
def validation_loop(self, epoch, valid_loader, valid_set, bar,
global_bar, confm_list):
for vi, data in enumerate(valid_loader):
# Read data
inputs, gts = data
n_images, w, h, c = inputs.size()
inputs = Variable(inputs).cuda()
gts = Variable(gts).cuda()
# Predict model
with torch.no_grad():
outputs = self.model.net(inputs)
predictions = outputs.data.max(1)[1].cpu().numpy()
print(type(data))
print(inputs.shape)
print(outputs.shape)
print(gts.shape)
print(type(self.model.loss(outputs, gts).cpu()))
print(self.model.loss(outputs, gts).item())
# Compute batch stats
#self.val_loss.update(float(self.model.loss(outputs, gts).cpu().data[0] / n_images), n_images)
self.val_loss.update(
float(self.model.loss(outputs, gts).item() / n_images),
n_images)
confm = compute_confusion_matrix(predictions,
gts.cpu().data.numpy(),
self.cf.num_classes,
self.cf.void_class)
confm_list = list(map(operator.add, confm_list, confm))
# Save epoch stats
self.stats.val.conf_m = confm_list
if not self.cf.normalize_loss:
self.stats.val.loss = self.val_loss.avg
else:
self.stats.val.loss = self.val_loss.avg
# Save predictions and generate overlaping
self.update_tensorboard(
inputs.cpu(), gts.cpu(), predictions, epoch,
range(
vi * self.cf.valid_batch_size,
vi * self.cf.valid_batch_size +
np.shape(predictions)[0]), valid_set.num_images)
# Update messages
if not self.cf.silent:
self.update_msg(bar, global_bar)
def training_loop(self, epoch, train_loader, epoch_bar):
# Train epoch
for i, data in enumerate(train_loader):
# Read Data
inputs, labels = data
N, w, h, c = inputs.size()
inputs = Variable(inputs).cuda()
self.inputs = inputs
self.labels = Variable(labels).cuda()
# Predict model
self.model.optimizer.zero_grad()
self.outputs = self.model.net(inputs)
predictions = self.outputs.data.max(1)[1].cpu().numpy()
# Compute gradients
self.compute_gradients()
# Compute batch stats
self.train_loss.update(float(self.loss.cpu().item()), N)
confm = compute_confusion_matrix(
predictions,
self.labels.cpu().data.numpy(), self.cf.num_classes,
self.cf.void_class)
self.confm_list = map(operator.add, self.confm_list, confm)
if self.cf.normalize_loss:
self.stats.train.loss = self.train_loss.avg
else:
self.stats.train.loss = self.train_loss.avg
if not self.cf.debug:
# Save stats
self.save_stats_batch((epoch - 1) *
self.train_num_batches + i)
# Update epoch messages
if not self.cf.silent:
self.update_epoch_messages(epoch_bar, self.global_bar,
self.train_num_batches,
epoch, i)
def start(self, criterion, valid_set, valid_loader, epoch=None, global_bar=None):
confm_list = np.zeros((self.cf.num_classes,self.cf.num_classes))
val_loss = AverageMeter()
# Initialize epoch progress bar
val_num_batches = math.ceil(valid_set.num_images / float(self.cf.valid_batch_size))
prev_msg = '\nValidation estimated time...\n'
bar = ProgressBar(val_num_batches, lenBar=20)
bar.set_prev_msg(prev_msg)
bar.update(show=False)
# Validate model
for vi, data in enumerate(valid_loader):
# Read data
inputs, gts = data
n_images,w,h,c = inputs.size()
inputs = Variable(inputs, volatile=True).cuda()
gts = Variable(gts, volatile=True).cuda()
# Predict model
outputs = self.model.net(inputs)
predictions = outputs.data.max(1)[1].cpu().numpy()
# Compute batch stats
val_loss.update(criterion(outputs, gts).data[0] / n_images, n_images)
confm = compute_confusion_matrix(predictions,gts.cpu().data.numpy(),self.cf.num_classes,self.cf.void_class)
confm_list = map(operator.add, confm_list, confm)
# Save epoch stats
self.stats.val.conf_m = confm_list
self.stats.val.loss = val_loss.avg / (w * h * c)
# Update messages
self.update_msg(bar, global_bar)
# Compute stats
self.compute_stats(np.asarray(self.stats.val.conf_m), val_loss)
# Save stats
self.save_stats(epoch)
def start(self, criterion, optimizer, train_loader, train_set, valid_set=None, valid_loader=None, scheduler=None):
train_num_batches = math.ceil(train_set.num_images / float(self.cf.train_batch_size))
val_num_batches = 0 if valid_set is None else math.ceil(valid_set.num_images / float(self.cf.valid_batch_size))
# Define early stopping control
if self.cf.early_stopping:
early_Stopping = Early_Stopping(self.cf)
else:
early_Stopping = None
prev_msg = '\nTotal estimated training time...\n'
global_bar = ProgressBar((self.cf.epochs+1-self.curr_epoch)*(train_num_batches+val_num_batches), lenBar=20)
global_bar.set_prev_msg(prev_msg)
# Train process
for epoch in range(self.curr_epoch, self.cf.epochs + 1):
# Shuffle train data
train_set.update_indexes()
# Initialize logger
epoch_time = time.time()
self.logger_stats.write('\t ------ Epoch: ' + str(epoch) + ' ------ \n')
# Initialize epoch progress bar
self.msg.accum_str = '\n\nEpoch %d/%d estimated time...\n' % (epoch, self.cf.epochs + 1 - self.curr_epoch)
epoch_bar = ProgressBar(train_num_batches, lenBar=20)
epoch_bar.update(show=False)
# Initialize stats
train_loss = AverageMeter()
confm_list = np.zeros((self.cf.num_classes, self.cf.num_classes))
# Train epoch
for i, data in enumerate(train_loader):
# Read Data
inputs, labels = data
N,w,h,c = inputs.size()
inputs = Variable(inputs).cuda()
labels = Variable(labels).cuda()
# Predict model
optimizer.zero_grad()
outputs = self.model.net(inputs)
predictions = outputs.data.max(1)[1].cpu().numpy()
# Compute gradients
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
# Compute batch stats
train_loss.update(loss.data[0], N)
confm = compute_confusion_matrix(predictions, labels.cpu().data.numpy(), self.cf.num_classes,
self.cf.void_class)
confm_list = map(operator.add, confm_list, confm)
self.stats.train.loss = train_loss.avg / (w*h*c)
# Save stats
self.save_stats_batch((epoch - 1) * train_num_batches + i)
# Update epoch messages
self.update_epoch_messages(epoch_bar, global_bar, train_num_batches,epoch, i)
# Save stats
self.stats.train.conf_m = confm_list
self.compute_stats(np.asarray(confm_list),train_loss)
self.save_stats_epoch(epoch)
# Validate epoch
self.validate_epoch(valid_set, valid_loader, criterion, early_Stopping, epoch, global_bar)
# Update scheduler
if scheduler is not None:
scheduler.step(self.stats.val.loss)
# Saving model if needed
self.model.net.save(self.stats)
# Update display values
self.update_messages(epoch, epoch_time)
if self.stop:
return
# Save model without training
if self.cf.epochs == 0:
self.model.save_model(self.model.net)