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_visualizer = SegVisualizer(configer)
self.seg_loss_manager = SegLossManager(configer)
self.module_utilizer = ModuleUtilizer(configer)
self.seg_model_manager = SegModelManager(configer)
self.seg_data_loader = SegDataLoader(configer)
self.seg_net = None
self.train_loader = None
self.val_loader = None
self.optimizer = None
self.lr = None
self.iters = None
def init_model(self):
self.seg_net = self.seg_model_manager.seg_net()
self.iters = 0
self.seg_net, _ = self.module_utilizer.load_net(self.seg_net)
self.optimizer, self.lr = self.module_utilizer.update_optimizer(self.seg_net, self.iters)
if self.configer.get('dataset') == 'cityscape':
self.train_loader = self.seg_data_loader.get_trainloader(FSCityScapeLoader)
self.val_loader = self.seg_data_loader.get_valloader(FSCityScapeLoader)
else:
Log.error('Dataset: {} is not valid!'.format(self.configer.get('dataset')))
exit(1)
self.pixel_loss = self.seg_loss_manager.get_seg_loss('cross_entropy_loss')
def __train(self):
"""
Train function of every epoch during train phase.
"""
self.seg_net.train()
start_time = time.time()
# data_tuple: (inputs, heatmap, maskmap, tagmap, num_objects)
for i, data_tuple in enumerate(self.train_loader):
self.data_time.update(time.time() - start_time)
# Change the data type.
if len(data_tuple) < 2:
Log.error('Train Loader Error!')
exit(0)
inputs = Variable(data_tuple[0].cuda(async=True))
targets = Variable(data_tuple[1].cuda(async=True))
# Forward pass.
outputs = self.seg_net(inputs)
# Compute the loss of the train batch & backward.
loss_pixel = self.pixel_loss(outputs, targets)
loss = loss_pixel
self.train_losses.update(loss.data[0], 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.iters += 1
# Print the log info & reset the states.
if self.iters % self.configer.get('solver', 'display_iter') == 0:
Log.info('Train Iteration: {0}\t'
'Time {batch_time.sum:.3f}s / {1}iters, ({batch_time.avg:.3f})\t'
'Data load {data_time.sum:.3f}s / {1}iters, ({data_time.avg:3f})\n'
'Learning rate = {2}\n'
'Loss = {loss.val:.8f} (ave = {loss.avg:.8f})\n'.format(
self.iters, self.configer.get('solver', 'display_iter'),
self.lr, 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()
# Check to val the current model.
if self.val_loader is not None and \
self.iters % self.configer.get('solver', 'test_interval') == 0:
self.__val()
self.optimizer, self.lr = self.module_utilizer.update_optimizer(self.seg_net, self.iters)
def __val(self):
"""
Validation function during the train phase.
"""
self.seg_net.eval()
start_time = time.time()
for j, data_tuple in enumerate(self.val_loader):
# Change the data type.
inputs = Variable(data_tuple[0].cuda(async=True), volatile=True)
targets = Variable(data_tuple[1].cuda(async=True), volatile=True)
# Forward pass.
outputs = self.seg_net(inputs)
# Compute the loss of the val batch.
loss_pixel = self.pixel_loss(outputs, targets)
loss = loss_pixel
self.val_losses.update(loss.data[0], inputs.size(0))
# Update the vars of the val phase.
self.batch_time.update(time.time() - start_time)
start_time = time.time()
self.module_utilizer.save_net(self.seg_net, self.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.seg_net.train()
def train(self):
cudnn.benchmark = True
while self.iters < self.configer.get('solver', 'max_iter'):
self.__train()
if self.iters == self.configer.get('solver', 'max_iter'):
break
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_visualizer = SegVisualizer(configer)
self.seg_loss_manager = SegLossManager(configer)
self.module_utilizer = ModuleUtilizer(configer)
self.seg_model_manager = SegModelManager(configer)
self.seg_data_loader = SegDataLoader(configer)
self.seg_net = None
self.train_loader = None
self.val_loader = None
self.optimizer = None
self.lr = None
self.iters = None
def init_model(self):
self.seg_net = self.seg_model_manager.seg_net()
self.iters = 0
self.seg_net, _ = self.module_utilizer.load_net(self.seg_net)
self.optimizer, self.lr = self.module_utilizer.update_optimizer(
self.seg_net, self.iters)
if self.configer.get('dataset') == 'cityscape':
self.train_loader = self.seg_data_loader.get_trainloader(
FSCityScapeLoader)
self.val_loader = self.seg_data_loader.get_valloader(
FSCityScapeLoader)
else:
Log.error('Dataset: {} is not valid!'.format(
self.configer.get('dataset')))
exit(1)
self.pixel_loss = self.seg_loss_manager.get_seg_loss(
'cross_entropy_loss')
def __train(self):
"""
Train function of every epoch during train phase.
"""
self.seg_net.train()
start_time = time.time()
# data_tuple: (inputs, heatmap, maskmap, tagmap, num_objects)
for i, data_tuple in enumerate(self.train_loader):
self.data_time.update(time.time() - start_time)
# Change the data type.
if len(data_tuple) < 2:
Log.error('Train Loader Error!')
exit(0)
inputs = Variable(data_tuple[0].cuda(async=True))
targets = Variable(data_tuple[1].cuda(async=True))
# Forward pass.
outputs = self.seg_net(inputs)
# Compute the loss of the train batch & backward.
loss_pixel = self.pixel_loss(outputs, targets)
loss = loss_pixel
self.train_losses.update(loss.data[0], 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.iters += 1
# Print the log info & reset the states.
if self.iters % self.configer.get('solver', 'display_iter') == 0:
Log.info(
'Train Iteration: {0}\t'
'Time {batch_time.sum:.3f}s / {1}iters, ({batch_time.avg:.3f})\t'
'Data load {data_time.sum:.3f}s / {1}iters, ({data_time.avg:3f})\n'
'Learning rate = {2}\n'
'Loss = {loss.val:.8f} (ave = {loss.avg:.8f})\n'.format(
self.iters,
self.configer.get('solver', 'display_iter'),
self.lr,
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()
# Check to val the current model.
if self.val_loader is not None and \
self.iters % self.configer.get('solver', 'test_interval') == 0:
self.__val()
self.optimizer, self.lr = self.module_utilizer.update_optimizer(
self.seg_net, self.iters)
def __val(self):
"""
Validation function during the train phase.
"""
self.seg_net.eval()
start_time = time.time()
for j, data_tuple in enumerate(self.val_loader):
# Change the data type.
inputs = Variable(data_tuple[0].cuda(async=True), volatile=True)
targets = Variable(data_tuple[1].cuda(async=True), volatile=True)
# Forward pass.
outputs = self.seg_net(inputs)
# Compute the loss of the val batch.
loss_pixel = self.pixel_loss(outputs, targets)
loss = loss_pixel
self.val_losses.update(loss.data[0], inputs.size(0))
# Update the vars of the val phase.
self.batch_time.update(time.time() - start_time)
start_time = time.time()
self.module_utilizer.save_net(self.seg_net, self.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.seg_net.train()
def train(self):
cudnn.benchmark = True
while self.iters < self.configer.get('solver', 'max_iter'):
self.__train()
if self.iters == self.configer.get('solver', 'max_iter'):
break
class FCNSegmentorTest(object):
def __init__(self, configer):
self.configer = configer
self.seg_vis = SegVisualizer(configer)
self.seg_model_manager = SegModelManager(configer)
self.module_utilizer = ModuleUtilizer(configer)
self.seg_net = None
def init_model(self):
self.seg_net = self.seg_model_manager.seg_net()
self.seg_net, _ = self.module_utilizer.load_net(self.seg_net)
self.seg_net.eval()
def forward(self, image_path):
image = Image.open(image_path).convert('RGB')
image = RandomResize(size=self.configer.get('data', 'input_size'),
is_base=False)(image)
image = ToTensor()(image)
image = Normalize(mean=[128.0, 128.0, 128.0],
std=[256.0, 256.0, 256.0])(image)
inputs = Variable(image.unsqueeze(0).cuda(), volatile=True)
results = self.seg_net.forward(inputs)
return results.data.cpu().numpy().argmax(axis=1)[0].squeeze()
def __test_img(self, image_path, save_path):
if self.configer.get('dataset') == 'cityscape':
self.__test_cityscape_img(image_path, save_path)
elif self.configer.get('dataset') == 'laneline':
self.__test_laneline_img(image_path, save_path)
else:
Log.error('Dataset: {} is not valid.'.format(
self.configer.get('dataset')))
exit(1)
def __test_cityscape_img(self, img_path, save_path):
color_list = [(128, 64, 128), (244, 35, 232), (70, 70, 70),
(102, 102, 156), (190, 153, 153), (153, 153, 153),
(250, 170, 30), (220, 220, 0), (107, 142, 35),
(152, 251, 152), (70, 130, 180), (220, 20, 60),
(255, 0, 0), (0, 0, 142), (0, 0, 70), (0, 60, 100),
(0, 80, 100), (0, 0, 230), (119, 11, 32)]
result = self.forward(img_path)
width = self.configer.get(
'data', 'input_size')[0] // self.configer.get('network', 'stride')
height = self.configer.get(
'data', 'input_size')[1] // self.configer.get('network', 'stride')
color_dst = np.zeros((height, width, 3), dtype=np.uint8)
for i in range(self.configer.get('data', 'num_classes')):
color_dst[result == i] = color_list[i]
color_img = np.array(color_dst, dtype=np.uint8)
color_img = Image.fromarray(color_img, 'RGB')
color_img.save(save_path)
def __test_laneline_img(self, img_path, save_path):
pass
def test(self):
base_dir = os.path.join(self.configer.get('project_dir'),
'val/results/seg',
self.configer.get('dataset'), 'test')
if not os.path.exists(base_dir):
os.makedirs(base_dir)
test_img = self.configer.get('test_img')
test_dir = self.configer.get('test_dir')
if test_img is None and test_dir is None:
Log.error('test_img & test_dir not exists.')
exit(1)
if test_img is not None and test_dir is not None:
Log.error('Either test_img or test_dir.')
exit(1)
if test_img is not None:
filename = test_img.rstrip().split('/')[-1]
save_path = os.path.join(base_dir, filename)
self.__test_img(test_img, save_path)
else:
for filename in self.__list_dir(test_dir):
image_path = os.path.join(test_dir, filename)
save_path = os.path.join(base_dir, filename)
self.__test_img(image_path, save_path)
def __create_cityscape_submission(self, test_dir=None, base_dir=None):
label_list = [
7, 8, 11, 12, 13, 17, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 31,
32, 33
]
for filename in self.__list_dir(test_dir):
image_path = os.path.join(test_dir, filename)
save_path = os.path.join(base_dir, filename)
result = self.forward(image_path)
width = self.configer.get('data',
'input_size')[0] // self.configer.get(
'network', 'stride')
height = self.configer.get('data',
'input_size')[1] // self.configer.get(
'network', 'stride')
label_dst = np.ones((height, width), dtype=np.uint8) * 255
for i in range(self.configer.get('data', 'num_classes')):
label_dst[result == i] = label_list[i]
label_img = np.array(label_dst, dtype=np.uint8)
label_img = Image.fromarray(label_img, 'P')
label_img.save(save_path)
def create_submission(self, test_dir=None):
base_dir = os.path.join(self.configer.get('project_dir'),
'val/results/seg',
self.configer.get('dataset'), 'submission')
if not os.path.exists(base_dir):
os.makedirs(base_dir)
if self.configer.get('dataset') == 'cityscape':
self.__create_cityscape_submission(test_dir, base_dir)
else:
Log.error('Dataset: {} is not valid.'.format(
self.configer.get('dataset')))
exit(1)
def __list_dir(self, dir_name):
filename_list = list()
for item in os.listdir(dir_name):
if os.path.isdir(item):
for filename in os.listdir(os.path.join(dir_name, item)):
filename_list.append('{}/{}'.format(item, filename))
else:
filename_list.append(item)
return filename_list
class FCNSegmentorTest(object):
def __init__(self, configer):
self.configer = configer
self.seg_vis = SegVisualizer(configer)
self.seg_model_manager = SegModelManager(configer)
self.module_utilizer = ModuleUtilizer(configer)
self.seg_net = None
def init_model(self):
self.seg_net = self.seg_model_manager.seg_net()
self.seg_net, _ = self.module_utilizer.load_net(self.seg_net)
self.seg_net.eval()
def forward(self, image_path):
image = Image.open(image_path).convert('RGB')
image = RandomResize(size=self.configer.get('data', 'input_size'), is_base=False)(image)
image = ToTensor()(image)
image = Normalize(mean=[128.0, 128.0, 128.0], std=[256.0, 256.0, 256.0])(image)
inputs = Variable(image.unsqueeze(0).cuda(), volatile=True)
results = self.seg_net.forward(inputs)
return results.data.cpu().numpy().argmax(axis=1)[0].squeeze()
def __test_img(self, image_path, save_path):
if self.configer.get('dataset') == 'cityscape':
self.__test_cityscape_img(image_path, save_path)
elif self.configer.get('dataset') == 'laneline':
self.__test_laneline_img(image_path, save_path)
else:
Log.error('Dataset: {} is not valid.'.format(self.configer.get('dataset')))
exit(1)
def __test_cityscape_img(self, img_path, save_path):
color_list = [(128, 64, 128), (244, 35, 232), (70, 70, 70), (102, 102, 156), (190, 153, 153),
(153, 153, 153), (250, 170, 30), (220, 220, 0), (107, 142, 35), (152, 251, 152),
(70, 130, 180), (220, 20, 60), (255, 0, 0), (0, 0, 142), (0, 0, 70), (0, 60, 100),
(0, 80, 100), (0, 0, 230), (119, 11, 32)]
result = self.forward(img_path)
width = self.configer.get('data', 'input_size')[0] // self.configer.get('network', 'stride')
height = self.configer.get('data', 'input_size')[1] // self.configer.get('network', 'stride')
color_dst = np.zeros((height, width, 3), dtype=np.uint8)
for i in range(self.configer.get('data', 'num_classes')):
color_dst[result == i] = color_list[i]
color_img = np.array(color_dst, dtype=np.uint8)
color_img = Image.fromarray(color_img, 'RGB')
color_img.save(save_path)
def __test_laneline_img(self, img_path, save_path):
pass
def test(self):
base_dir = os.path.join(self.configer.get('project_dir'),
'val/results/seg', self.configer.get('dataset'), 'test')
if not os.path.exists(base_dir):
os.makedirs(base_dir)
test_img = self.configer.get('test_img')
test_dir = self.configer.get('test_dir')
if test_img is None and test_dir is None:
Log.error('test_img & test_dir not exists.')
exit(1)
if test_img is not None and test_dir is not None:
Log.error('Either test_img or test_dir.')
exit(1)
if test_img is not None:
filename = test_img.rstrip().split('/')[-1]
save_path = os.path.join(base_dir, filename)
self.__test_img(test_img, save_path)
else:
for filename in self.__list_dir(test_dir):
image_path = os.path.join(test_dir, filename)
save_path = os.path.join(base_dir, filename)
self.__test_img(image_path, save_path)
def __create_cityscape_submission(self, test_dir=None, base_dir=None):
label_list = [7, 8, 11, 12, 13, 17, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 31, 32, 33]
for filename in self.__list_dir(test_dir):
image_path = os.path.join(test_dir, filename)
save_path = os.path.join(base_dir, filename)
result = self.forward(image_path)
width = self.configer.get('data', 'input_size')[0] // self.configer.get('network', 'stride')
height = self.configer.get('data', 'input_size')[1] // self.configer.get('network', 'stride')
label_dst = np.ones((height, width), dtype=np.uint8) * 255
for i in range(self.configer.get('data', 'num_classes')):
label_dst[result == i] = label_list[i]
label_img = np.array(label_dst, dtype=np.uint8)
label_img = Image.fromarray(label_img, 'P')
label_img.save(save_path)
def create_submission(self, test_dir=None):
base_dir = os.path.join(self.configer.get('project_dir'),
'val/results/seg', self.configer.get('dataset'), 'submission')
if not os.path.exists(base_dir):
os.makedirs(base_dir)
if self.configer.get('dataset') == 'cityscape':
self.__create_cityscape_submission(test_dir, base_dir)
else:
Log.error('Dataset: {} is not valid.'.format(self.configer.get('dataset')))
exit(1)
def __list_dir(self, dir_name):
filename_list = list()
for item in os.listdir(dir_name):
if os.path.isdir(item):
for filename in os.listdir(os.path.join(dir_name, item)):
filename_list.append('{}/{}'.format(item, filename))
else:
filename_list.append(item)
return filename_list