def Validation(cf, sess, sb):
val_time = time.time()
val_writer = sb.tensorBoard.save(
cf.exp_folder + cf.log_path + 'validation/', sess)
valid_image_path = os.path.join(cf.valid_dataset_path,
cf.valid_folder_names[0])
valid_gt_path = os.path.join(cf.valid_dataset_path,
cf.valid_folder_names[1])
valid_set = Data_loader(cf, valid_image_path, cf.valid_samples,
cf.size_image_valid, valid_gt_path)
valid_set.Load_dataset(cf.valid_batch_size)
valid_stats = Statistics(cf.valid_batch_size, sb)
tf.summary.scalar("Mean_IoU/validation",
valid_stats.mean_IoU,
collections=['validation'])
tf.summary.scalar("Mean_Acc/validation",
valid_stats.accuracy_class,
collections=['validation'])
valid_loss_batch = np.zeros(valid_set.num_batches, dtype=np.float32)
sess.run(valid_stats.running_vars_initializer)
prog_bar = ProgressBar(valid_set.num_batches)
for i in range(valid_set.num_batches):
batch_x, batch_y = valid_set.Next_batch(cf.valid_batch_size)
feed_dict = {
sb.model.simb_image: batch_x,
sb.model.simb_gt: batch_y,
sb.model.simb_is_training: False
}
simbol_list = [
sb.loss_fun, sb.model.annotation_pred, valid_stats.update_IoU,
valid_stats.update_acc_class
]
sess_return = sess.run(simbol_list, feed_dict)
valid_loss_batch[i] = sess_return[0]
pred = sess_return[1]
conf_mat = sess_return[3]
prog_bar.update()
conf_mat = conf_mat / valid_set.num_batches
img_conf_mat = confm_metrics2image(conf_mat, cf.labels)
img_conf_mat = tf.expand_dims(img_conf_mat, 0)
tf.summary.image("conf_mat/validation",
img_conf_mat,
max_outputs=2,
collections=['validation'])
summary_op_val = sb.tensorBoard.set_up('validation')
mIoU_valid, mAcc_valid, sammary_val = sess.run(
[valid_stats.mean_IoU, valid_stats.accuracy_class, summary_op_val])
val_time = time.time() - val_time
print("\t Loss: %g, mIoU: %g, mAcc: %g, Time: %ds" % (np.mean(
np.asarray(valid_loss_batch)), mIoU_valid, mAcc_valid, val_time))
val_writer.add_summary(sammary_val)
def start(self,
valid_set,
valid_loader,
mode='Validation',
epoch=None,
global_bar=None,
save_folder=None):
confm_list = np.zeros((self.cf.num_classes, self.cf.num_classes))
self.val_loss = AverageMeter()
# Initialize epoch progress bar
val_num_batches = math.ceil(valid_set.num_images /
float(self.cf.valid_batch_size))
prev_msg = '\n' + mode + ' estimated time...\n'
bar = ProgressBar(val_num_batches, lenBar=20)
bar.set_prev_msg(prev_msg)
bar.update(show=False)
# Validate model
if self.cf.problem_type == 'detection':
self.validation_loop(epoch, valid_loader, valid_set, bar,
global_bar, save_folder)
else:
self.validation_loop(epoch, valid_loader, valid_set, bar,
global_bar, confm_list)
# Compute stats
self.compute_stats(np.asarray(self.stats.val.conf_m),
self.val_loss)
# Save stats
self.save_stats(epoch)
if mode == 'Epoch Validation':
self.logger_stats.write_stat(
self.stats.train, epoch,
os.path.join(self.cf.train_json_path,
'valid_epoch_' + str(epoch) + '.json'))
elif mode == 'Validation':
self.logger_stats.write_stat(self.stats.val, epoch,
self.cf.val_json_file)
elif mode == 'Test':
self.logger_stats.write_stat(self.stats.val, epoch,
self.cf.test_json_file)
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 Predict(cf, sess, sb):
predict_time = time.time()
test_image_path = os.path.join(cf.test_dataset_path,
cf.test_folder_names[0])
test_set = Data_loader(cf, test_image_path, cf.test_samples,
cf.resize_image_test)
test_set.Load_dataset(cf.test_batch_size)
prog_bar = ProgressBar(test_set.num_batches)
for i in range(test_set.num_batches):
batch_x, batch_names = test_set.Next_batch_pred(cf.test_batch_size)
feed_dict = {
sb.model.simb_image: batch_x,
sb.model.simb_is_training: False
}
simbol_list = [sb.model.annotation_pred]
sess_return = sess.run(simbol_list, feed_dict)
pred = sess_return[0]
save_prediction(cf.predict_output, pred, batch_names)
prog_bar.update()
predict_time = time.time() - predict_time
print("\t Time: %ds" % (predict_time))
def start(self,
train_loader,
train_set,
valid_set=None,
valid_loader=None):
self.train_num_batches = math.ceil(train_set.num_images /
float(self.cf.train_batch_size))
self.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'
self.global_bar = ProgressBar(
(self.cf.epochs + 1 - self.curr_epoch) *
(self.train_num_batches + self.val_num_batches),
lenBar=20)
self.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)
epoch_bar = ProgressBar(self.train_num_batches, lenBar=20)
epoch_bar.update(show=False)
# Initialize stats
self.stats.epoch = epoch
self.train_loss = AverageMeter()
self.confm_list = np.zeros(
(self.cf.num_classes, self.cf.num_classes))
# Train epoch
self.training_loop(epoch, train_loader, epoch_bar)
# Save stats
self.stats.train.conf_m = self.confm_list
self.compute_stats(np.asarray(self.confm_list),
self.train_loss)
self.save_stats_epoch(epoch)
self.logger_stats.write_stat(
self.stats.train, epoch,
os.path.join(self.cf.train_json_path,
'train_epoch_' + str(epoch) + '.json'))
# Validate epoch
self.validate_epoch(valid_set, valid_loader, early_Stopping,
epoch, self.global_bar)
# Update scheduler
if self.model.scheduler is not None:
self.model.scheduler.step(self.stats.val.loss)
# Saving model if score improvement
new_best = self.model.save(self.stats)
if new_best:
self.logger_stats.write_best_stats(self.stats, epoch,
self.cf.best_json_file)
# Update display values
self.update_messages(epoch, epoch_time, new_best)
if self.stop:
return
# Save model without training
if self.cf.epochs == 0:
self.model.save_model()
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)
def Train(cf, sess, sb):
#Path definitions
train_image_path = os.path.join(cf.train_dataset_path,
cf.train_folder_names[0])
train_gt_path = os.path.join(cf.train_dataset_path,
cf.train_folder_names[1])
valid_image_path = os.path.join(cf.valid_dataset_path,
cf.valid_folder_names[0])
valid_gt_path = os.path.join(cf.valid_dataset_path,
cf.valid_folder_names[1])
trainable_var = tf.trainable_variables()
# Training dataset set up
train_set = Data_loader(cf, train_image_path, cf.train_samples,
cf.size_image_train, train_gt_path)
train_set.Load_dataset(cf.train_batch_size)
# Validation dataset set up
valid_set = Data_loader(cf, valid_image_path, cf.valid_samples_epoch,
cf.size_image_valid, valid_gt_path)
valid_set.Load_dataset(cf.valid_batch_size)
# Simbol creation for metrics and statistics
train_stats = Statistics(cf.train_batch_size, sb)
valid_stats = Statistics(cf.valid_batch_size, sb)
# More summary information to add
#tf.summary.scalar("Mean_loss", train_mLoss)
#img_conf_mat = tf.placeholder(tf.uint8, shape=[None, 480, 640, 3], name="conf_mat")
tf.summary.scalar("Mean_IoU/train",
train_stats.mean_IoU,
collections=['train'])
tf.summary.scalar("Mean_Acc/train",
train_stats.accuracy_class,
collections=['train'])
tf.summary.scalar("Mean_IoU/train_valid",
valid_stats.mean_IoU,
collections=['train_valid'])
tf.summary.scalar("Mean_Acc/train_valid",
valid_stats.accuracy_class,
collections=['train_valid'])
train_writer = sb.tensorBoard.save(cf.exp_folder + cf.log_path + 'train/',
sess)
val_writer = sb.tensorBoard.save(
cf.exp_folder + cf.log_path + 'train_valid/', sess)
# Early stopping
if cf.early_stopping:
e_stop = Early_Stopping(cf.patience)
# Training
feed_dict = []
stop = False
epoch = 1
# Epoch loop
while epoch < cf.epochs + 1 and not stop:
epoch_time = time.time()
if cf.shuffle:
train_set.Shuffle()
valid_set.Shuffle()
loss_per_batch = np.zeros(train_set.num_batches, dtype=np.float32)
conf_mat = np.zeros((cf.num_classes, cf.num_classes), dtype=np.float32)
# initialize/reset the running variables
sess.run(train_stats.running_vars_initializer)
#Progress bar
prog_bar = ProgressBar(train_set.num_batches)
#Dataset batch loop
for i in range(train_set.num_batches):
batch_x, batch_y = train_set.Next_batch(cf.train_batch_size,
crop=True)
feed_dict = {
sb.model.simb_image: batch_x,
sb.model.simb_gt: batch_y,
sb.model.simb_is_training: True
}
simbol_list = [
sb.train_op, sb.loss_fun, sb.model.annotation_pred,
train_stats.update_IoU, train_stats.update_acc_class,
train_stats.conf_matrix_batch
]
sess_return = sess.run(simbol_list, feed_dict)
loss_per_batch[i] = sess_return[1]
#pred = sess_return[2]
conf_mat += sess_return[5]
prog_bar.update()
# Epoch train summary info
conf_mat = conf_mat / train_set.num_batches
img_conf_mat = confm_metrics2image(conf_mat, cf.labels)
img_conf_mat = tf.expand_dims(img_conf_mat, 0)
tf.summary.image("conf_mat/train",
img_conf_mat,
max_outputs=2,
collections=['train'])
train_mLoss = np.mean(np.asarray(loss_per_batch))
summary_op_train = sb.tensorBoard.set_up('train')
mIoU_train, mAcc_train, summary_train = sess.run([
train_stats.mean_IoU, train_stats.accuracy_class, summary_op_train
], feed_dict)
train_set.Reset_Offset()
# Validation in train
if cf.valid_samples_epoch > 0:
conf_mat = np.zeros((cf.num_classes, cf.num_classes),
dtype=np.float32)
valid_loss_batch = np.zeros(valid_set.num_batches,
dtype=np.float32)
sess.run(valid_stats.running_vars_initializer)
for i in range(valid_set.num_batches):
batch_x, batch_y = valid_set.Next_batch(cf.valid_batch_size)
feed_dict = {
sb.model.simb_image: batch_x,
sb.model.simb_gt: batch_y,
sb.model.simb_is_training: False
}
simbol_list = [
sb.loss_fun, sb.model.annotation_pred,
valid_stats.update_IoU, valid_stats.update_acc_class,
valid_stats.conf_matrix_batch
]
sess_return = sess.run(simbol_list, feed_dict)
valid_loss_batch[i] = sess_return[0]
pred = sess_return[1]
conf_mat += sess_return[4]
conf_mat = conf_mat / train_set.num_batches
img_conf_mat = confm_metrics2image(conf_mat, cf.labels)
img_conf_mat = tf.expand_dims(img_conf_mat, 0)
tf.summary.image("conf_mat/train_valid",
img_conf_mat,
max_outputs=2,
collections=['train_valid'])
summary_op_val = sb.tensorBoard.set_up('train_valid')
mIoU_valid, mAcc_valid, sammary_val = sess.run([
valid_stats.mean_IoU, valid_stats.accuracy_class,
summary_op_val
])
valid_mLoss = np.mean(np.asarray(valid_loss_batch))
valid_set.Reset_Offset()
# Screen display
train_writer.add_summary(summary_train, epoch)
val_writer.add_summary(sammary_val, epoch)
epoch_time = time.time() - epoch_time
print("Epoch: %d, Time: %ds \n\t Train_loss: %g, mIoU: %g, mAcc: %g" %
(epoch, epoch_time, train_mLoss, mIoU_train, mAcc_train))
if cf.valid_samples_epoch > 0:
print("\t Valid_loss: %g, mIoU: %g, mAcc: %g" %
(valid_mLoss, mIoU_valid, mAcc_valid))
sb.model.modelIO.Save(cf, sess, train_mLoss, mIoU_train,
mAcc_train, valid_mLoss, mIoU_valid,
mAcc_valid)
if cf.early_stopping:
stop = e_stop.Check(cf.save_condition, train_mLoss, mIoU_train,
mAcc_train, valid_mLoss, mIoU_valid,
mAcc_valid)
else:
sb.model.modelIO.Save(cf, sess, train_mLoss, mIoU_train,
mAcc_train)
if cf.early_stopping:
stop = e_stop.Check(cf.save_condition, train_mLoss, mIoU_train,
mAcc_train)
epoch += 1