def single():
print('Mode: Single')
img = Image.open('test_content/example_01.png').convert('RGB')
class_encoding = color_encoding = OrderedDict([
('unlabeled', (0, 0, 0)), ('road', (128, 64, 128)),
('sidewalk', (244, 35, 232)), ('building', (70, 70, 70)),
('wall', (102, 102, 156)), ('fence', (190, 153, 153)),
('pole', (153, 153, 153)), ('traffic_light', (250, 170, 30)),
('traffic_sign', (220, 220, 0)), ('vegetation', (107, 142, 35)),
('terrain', (152, 251, 152)), ('sky', (70, 130, 180)),
('person', (220, 20, 60)), ('rider', (255, 0, 0)),
('car', (0, 0, 142)), ('truck', (0, 0, 70)), ('bus', (0, 60, 100)),
('train', (0, 80, 100)), ('motorcycle', (0, 0, 230)),
('bicycle', (119, 11, 32))
])
num_classes = len(class_encoding)
model = ERFNet(num_classes)
model_path = os.path.join(args.save_dir, args.name)
print('Loading model at:', model_path)
checkpoint = torch.load(model_path)
# model = ENet(num_classes)
model = model.cuda()
model.load_state_dict(checkpoint['state_dict'])
img = img.resize((args.width, args.height), Image.BILINEAR)
start = time.time()
images = transforms.ToTensor()(img)
torch.reshape(images, (1, 3, args.width, args.height))
images = images.unsqueeze(0)
with torch.no_grad():
images = images.cuda()
predictions = model(images)
end = time.time()
print('model speed:', int(1 / (end - start)), "FPS")
_, predictions = torch.max(predictions.data, 1)
label_to_rgb = transforms.Compose(
[utils.LongTensorToRGBPIL(class_encoding),
transforms.ToTensor()])
color_predictions = utils.batch_transform(predictions.cpu(),
label_to_rgb)
end = time.time()
print('model+transform:', int(1 / (end - start)), "FPS")
utils.imshow_batch(images.data.cpu(), color_predictions)
def lane_detect(im_tensor):
# Image size
_, HEIGHT, WIDTH = im_tensor.shape
im_tensor = im_tensor.unsqueeze(0)
# Creating CNNs and loading pretrained models
segmentation_network = ERFNet(NUM_CLASSES_SEGMENTATION)
classification_network = LCNet(NUM_CLASSES_CLASSIFICATION, DESCRIPTOR_SIZE,
DESCRIPTOR_SIZE)
segmentation_network.load_state_dict(
torch.load(path + 'pretrained/erfnet_tusimple.pth',
map_location=map_location))
model_path = path + 'pretrained/classification_{}_{}class.pth'.format(
DESCRIPTOR_SIZE, NUM_CLASSES_CLASSIFICATION)
classification_network.load_state_dict(
torch.load(model_path, map_location=map_location))
segmentation_network = segmentation_network.eval()
classification_network = classification_network.eval()
if torch.cuda.is_available():
segmentation_network = segmentation_network.cuda()
classification_network = classification_network.cuda()
im_tensor = im_tensor.cuda()
out_segmentation = segmentation_network(im_tensor)
out_segmentation = out_segmentation.max(dim=1)[1]
out_segmentation_np = out_segmentation.cpu().numpy()[0]
descriptors, index_map = extract_descriptors(out_segmentation, im_tensor)
classes = classification_network(descriptors).max(1)[1]
lane_map = torch.zeros(HEIGHT, WIDTH, dtype=torch.int64)
if torch.cuda.is_available():
lane_map = lane_map.cuda()
for i, lane_index in index_map.items():
lane_map[out_segmentation_np == lane_index] = classes[i] + 1
return lane_map
def __init__(self, options, model=None):
if __name__ == "__main__":
print(" -> Executing script", os.path.basename(__file__))
self.opt = options
self.device = torch.device("cpu" if self.opt.no_cuda else "cuda")
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# LABELS
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
assert self.opt.train_set in {1, 2, 3, 12, 123}, "Invalid train_set!"
assert self.opt.task_to_val in {0, 1, 2, 3, 12, 123}, "Invalid task!"
keys_to_load = ['color', 'segmentation']
# Labels
labels = self._get_labels_cityscapes()
# Train IDs
self.train_ids = set([labels[i].trainId for i in range(len(labels))])
self.train_ids.remove(255)
self.train_ids = sorted(list(self.train_ids))
self.num_classes_model = len(self.train_ids)
# Task handling
if self.opt.task_to_val != 0:
labels_task = self._get_task_labels_cityscapes()
train_ids_task = set(
[labels_task[i].trainId for i in range(len(labels_task))])
train_ids_task.remove(255)
self.task_low = min(train_ids_task)
self.task_high = max(train_ids_task) + 1
labels = labels_task
self.train_ids = sorted(list(train_ids_task))
else:
self.task_low = 0
self.task_high = self.num_classes_model
self.opt.task_to_val = self.opt.train_set
# Number of classes for the SegmentationRunningScore
self.num_classes_score = self.task_high - self.task_low
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# DATASET DEFINITIONS
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# Data augmentation
test_data_transforms = [
mytransforms.CreateScaledImage(),
mytransforms.Resize((self.opt.height, self.opt.width),
image_types=['color']),
mytransforms.ConvertSegmentation(),
mytransforms.CreateColoraug(new_element=True,
scales=self.opt.scales),
mytransforms.RemoveOriginals(),
mytransforms.ToTensor(),
mytransforms.NormalizeZeroMean(),
]
# If hyperparameter search, only load the respective validation set. Else, load the full validation set.
if self.opt.hyperparameter:
trainvaltest_split = 'train'
folders_to_load = CitySet.get_city_set(-1)
else:
trainvaltest_split = 'validation'
folders_to_load = None
test_dataset = CityscapesDataset(dataset='cityscapes',
split=self.opt.dataset_split,
trainvaltest_split=trainvaltest_split,
video_mode='mono',
stereo_mode='mono',
scales=self.opt.scales,
labels_mode='fromid',
labels=labels,
keys_to_load=keys_to_load,
data_transforms=test_data_transforms,
video_frames=self.opt.video_frames,
folders_to_load=folders_to_load)
self.test_loader = DataLoader(dataset=test_dataset,
batch_size=self.opt.batch_size,
shuffle=False,
num_workers=self.opt.num_workers,
pin_memory=True,
drop_last=False)
print(
"++++++++++++++++++++++ INIT VALIDATION ++++++++++++++++++++++++")
print("Using dataset\n ", self.opt.dataset, "with split",
self.opt.dataset_split)
print("There are {:d} validation items\n ".format(len(test_dataset)))
print("Validating classes up to train set\n ", self.opt.train_set)
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# LOGGING OPTIONS
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# If no model is passed, standalone validation is to be carried out. The log_path needs to be set before
# self.load_model() is invoked.
if model is None:
self.opt.validate = False
self.opt.model_name = self.opt.load_model_name
path_getter = GetPath()
log_path = path_getter.get_checkpoint_path()
self.log_path = os.path.join(log_path, 'erfnet', self.opt.model_name)
# All outputs will be saved to save_path
self.save_path = self.log_path
# Create output path for standalone validation
if not self.opt.validate:
save_dir = 'eval_{}'.format(self.opt.dataset)
if self.opt.hyperparameter:
save_dir = save_dir + '_hyper'
save_dir = save_dir + '_task_to_val{}'.format(self.opt.task_to_val)
self.save_path = os.path.join(self.log_path, save_dir)
if not os.path.exists(self.save_path):
os.makedirs(self.save_path)
# Copy this file to save_path
shutil.copy2(__file__, self.save_path)
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# MODEL DEFINITION
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# Standalone validation
if not self.opt.validate:
# Create a conventional ERFNet
self.model = ERFNet(self.num_classes_model, self.opt)
self.load_model()
self.model.to(self.device)
# Validate while training
else:
self.model = model
self.model.eval()
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# LOGGING OPTIONS II
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# self.called is used to decide which file mode shall be used when writing metrics to disk.
self.called = False
self.metric_model = SegmentationRunningScore(self.num_classes_score)
# Metrics are only saved if val_frequency > 0!
if self.opt.val_frequency != 0:
print("Saving metrics to\n ", self.save_path)
# Set up colour output. Coloured images are only output if standalone validation is carried out!
if not self.opt.validate and self.opt.save_pred_to_disk:
# Output path
self.img_path = os.path.join(
self.save_path, 'output_{}'.format(self.opt.weights_epoch))
if self.opt.pred_wout_blend:
self.img_path += '_wout_blend'
if not os.path.exists(self.img_path):
os.makedirs(self.img_path)
print("Saving prediction images to\n ", self.img_path)
print("Save frequency\n ", self.opt.pred_frequency)
# Get the colours from dataset.
colors = [
(label.trainId - self.task_low, label.color)
for label in labels
if label.trainId != 255 and label.trainId in self.train_ids
]
colors.append((255, (0, 0, 0))) # void class
self.id_color = dict(colors)
self.id_color_keys = [key for key in self.id_color.keys()]
self.id_color_vals = [val for val in self.id_color.values()]
# Ongoing index to name the outputs
self.img_idx = 0
# Set up probability output. Probabilities are only output if standalone validation is carried out!
if not self.opt.validate and self.opt.save_probs_to_disk:
# Output path
self.logit_path = os.path.join(
self.save_path,
'probabilities_{}'.format(self.opt.weights_epoch))
if not os.path.exists(self.logit_path):
os.makedirs(self.logit_path)
print("Saving probabilities to\n ", self.logit_path)
print("Save frequency\n ", self.opt.probs_frequency)
# Ongoing index to name the probability outputs
self.probs_idx = 0
print(
"+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++")
# Save all options to disk and print them to stdout
self._print_options()
self._save_opts(len(test_dataset))
def __init__(self, options):
self.opt = options
self.device = torch.device("cpu" if self.opt.no_cuda else "cuda")
# Assertions
assert os.path.isfile(self.opt.image), "Invalid image!"
self.opt.image.replace('/', os.sep)
self.opt.image.replace('\\', os.sep)
self.image_name = self.opt.image.split(os.sep)[-1]
if self.opt.model_stage == 1:
assert self.opt.task in {1}, "Invalid task!"
assert not self.opt.with_weights, "Weights for stage 1 not available"
elif self.opt.model_stage == 2:
assert self.opt.task in {1, 2, 12}, "Invalid task!"
elif self.opt.model_stage == 3:
assert self.opt.task in {1, 2, 3, 12, 123}, "Invalid task!"
# Model and task set-up
self.num_classes_model = {1: 5, 2: 11, 3: 19}[self.opt.model_stage]
self.task_low, self.task_high = {1: (0, 5), 2: (5, 11), 3: (11, 19), 12: (0, 11), 123: (0, 19)}[self.opt.task]
# Create a conventional ERFNet
self.model = ERFNet(self.num_classes_model, self.opt)
self._load_model()
self.model.to(self.device)
self.model.eval()
# Ground truth
self.metrics = False
if self.opt.ground_truth:
assert os.path.isfile(self.opt.ground_truth), "Invalid ground truth!"
self.metrics = True
self.num_classes_score = self.task_high - self.task_low
self.metric_model = SegmentationRunningScore(self.num_classes_score)
# Output directory
if self.opt.output_path:
if not os.path.isdir(self.opt.output_path):
os.makedirs(self.opt.output_path)
else:
self.opt.output_path = os.path.join(self.opt.image.split(os.sep)[:-1])
image_extension_idx = self.image_name.rfind('.')
segmentation_name = self.image_name[:image_extension_idx] + \
"_seg_stage_{}_task_{}".format(self.opt.model_stage, self.opt.task) + \
self.image_name[image_extension_idx:]
self.output_image = os.path.join(self.opt.output_path, segmentation_name)
ground_truth_name = self.image_name[:image_extension_idx] + \
"_gt_stage_{}_task_{}".format(self.opt.model_stage, self.opt.task) + \
self.image_name[image_extension_idx:]
self.output_gt = os.path.join(self.opt.output_path, ground_truth_name)
# stdout output
print("++++++++++++++++++++++ INIT DEMO ++++++++++++++++++++++++")
print("Image:\t {}".format(self.opt.image))
print("GT:\t {}".format(self.opt.ground_truth))
print("Output:\t {}".format(self.opt.output_path))
print("Stage:\t {}".format(self.opt.model_stage))
print("Weights: {}".format(self.opt.with_weights))
print("Task:\t {}".format(self.opt.task))
print("!!! MIND THAT THE MODELS WERE TRAINED USING AN IMAGE RESOLUTION OF 1024x512px !!!")
# Class colours
labels = labels_cityscape_seg_train3_eval.getlabels()
colors = [(label.trainId - self.task_low, label.color) for label in labels if
label.trainId != 255 and label.trainId in range(0, 19)]
colors.append((255, (0, 0, 0))) # void class
self.id_color = dict(colors)
self.id_color_keys = [key for key in self.id_color.keys()]
self.id_color_vals = [val for val in self.id_color.values()]
def __init__(self, options):
print(" -> Executing script", os.path.basename(__file__))
self.opt = options
self.device = torch.device("cpu" if self.opt.no_cuda else "cuda")
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# LABELS AND CITIES
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
assert self.opt.train_set in {123, 1}, "Invalid train_set!"
keys_to_load = ['color', 'segmentation']
# Labels
if self.opt.train_set == 1:
labels = labels_cityscape_seg_train1.getlabels()
else:
labels = labels_cityscape_seg_train3_eval.getlabels()
# Train IDs
self.train_ids = set([labels[i].trainId for i in range(len(labels))])
self.train_ids.remove(255)
self.num_classes = len(self.train_ids)
# Apply city filter
folders_to_train = CitySet.get_city_set(0)
if self.opt.city:
folders_to_train = CitySet.get_city_set(self.opt.train_set)
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# DATASET DEFINITIONS
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# Data augmentation
train_data_transforms = [
mytransforms.RandomHorizontalFlip(),
mytransforms.CreateScaledImage(),
mytransforms.Resize((self.opt.height, self.opt.width),
image_types=keys_to_load),
mytransforms.RandomRescale(1.5),
mytransforms.RandomCrop(
(self.opt.crop_height, self.opt.crop_width)),
mytransforms.ConvertSegmentation(),
mytransforms.CreateColoraug(new_element=True,
scales=self.opt.scales),
mytransforms.ColorJitter(brightness=0.2,
contrast=0.2,
saturation=0.2,
hue=0.1,
gamma=0.0),
mytransforms.RemoveOriginals(),
mytransforms.ToTensor(),
mytransforms.NormalizeZeroMean(),
]
train_dataset = CityscapesDataset(
dataset="cityscapes",
trainvaltest_split='train',
video_mode='mono',
stereo_mode='mono',
scales=self.opt.scales,
labels_mode='fromid',
labels=labels,
keys_to_load=keys_to_load,
data_transforms=train_data_transforms,
video_frames=self.opt.video_frames,
folders_to_load=folders_to_train,
)
self.train_loader = DataLoader(dataset=train_dataset,
batch_size=self.opt.batch_size,
shuffle=True,
num_workers=self.opt.num_workers,
pin_memory=True,
drop_last=True)
val_data_transforms = [
mytransforms.CreateScaledImage(),
mytransforms.Resize((self.opt.height, self.opt.width),
image_types=keys_to_load),
mytransforms.ConvertSegmentation(),
mytransforms.CreateColoraug(new_element=True,
scales=self.opt.scales),
mytransforms.RemoveOriginals(),
mytransforms.ToTensor(),
mytransforms.NormalizeZeroMean(),
]
val_dataset = CityscapesDataset(
dataset=self.opt.dataset,
trainvaltest_split="train",
video_mode='mono',
stereo_mode='mono',
scales=self.opt.scales,
labels_mode='fromid',
labels=labels,
keys_to_load=keys_to_load,
data_transforms=val_data_transforms,
video_frames=self.opt.video_frames,
folders_to_load=CitySet.get_city_set(-1))
self.val_loader = DataLoader(dataset=val_dataset,
batch_size=self.opt.batch_size,
shuffle=False,
num_workers=self.opt.num_workers,
pin_memory=True,
drop_last=True)
self.val_iter = iter(self.val_loader)
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# LOGGING OPTIONS
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
print(
"++++++++++++++++++++++ INIT TRAINING ++++++++++++++++++++++++++")
print("Using dataset:\n ", self.opt.dataset, "with split",
self.opt.dataset_split)
print(
"There are {:d} training items and {:d} validation items\n".format(
len(train_dataset), len(val_dataset)))
path_getter = GetPath()
log_path = path_getter.get_checkpoint_path()
self.log_path = os.path.join(log_path, 'erfnet', self.opt.model_name)
self.writers = {}
for mode in ["train", "validation"]:
self.writers[mode] = SummaryWriter(
os.path.join(self.log_path, mode))
# Copy this file to log dir
shutil.copy2(__file__, self.log_path)
print("Training model named:\n ", self.opt.model_name)
print("Models and tensorboard events files are saved to:\n ",
self.log_path)
print("Training is using:\n ", self.device)
print("Training takes place on train set:\n ", self.opt.train_set)
print(
"+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++")
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# MODEL DEFINITION
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# Instantiate model
self.model = ERFNet(self.num_classes, self.opt)
self.model.to(self.device)
self.parameters_to_train = self.model.parameters()
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# OPTIMIZER SET-UP
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
self.model_optimizer = optim.Adam(params=self.parameters_to_train,
lr=self.opt.learning_rate,
weight_decay=self.opt.weight_decay)
lambda1 = lambda epoch: pow((1 -
((epoch - 1) / self.opt.num_epochs)), 0.9)
self.model_lr_scheduler = optim.lr_scheduler.LambdaLR(
self.model_optimizer, lr_lambda=lambda1)
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# LOSSES
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
self.crossentropy = CrossEntropyLoss(ignore_background=True,
device=self.device)
self.crossentropy.to(self.device)
self.metric_model = SegmentationRunningScore(self.num_classes)
# Save all options to disk and print them to stdout
self.save_opts(len(train_dataset), len(val_dataset))
self._print_options()
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# EVALUATOR DEFINITION
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
if self.opt.validate:
self.evaluator = Evaluator(self.opt, self.model)
def train(train_loader, val_loader, circ_S):
print("\nTraining...\n")
model = ERFNet(1).to(device).double()
#criterion = nn.MSELoss()
criterion = ReconsLoss(circ_S)
optimizer = optim.Adam(model.parameters(),
lr=args.learning_rate,
weight_decay=args.weight_decay)
# Learning rate decay scheduler
lr_updater = lr_scheduler.StepLR(optimizer, args.lr_decay_epochs,
args.lr_decay)
# Optionally resume from a checkpoint
if args.resume:
model, optimizer, start_epoch, best_loss, best_snr = utils.load_checkpoint(
model, optimizer, args.save_dir, args.name)
print("Resuming from model: Start epoch = {0} "
"| Best mean loss = {1:.4f} Best mean snr = {1:.4f}".format(
start_epoch, best_snr))
else:
start_epoch = 0
best_loss = 0
best_snr = 0
if args.visdom:
vis = visdom.Visdom()
loss_win = vis.line(X=np.column_stack(
(np.array(start_epoch), np.array(start_epoch))),
Y=np.column_stack(
(np.array(best_loss), np.array(best_loss))),
opts=dict(legend=['train', 'test'],
xlabel='epoch',
ylabel='loss',
title='Loss'))
snr_win = vis.line(X=np.column_stack(
(np.array(start_epoch), np.array(start_epoch))),
Y=np.column_stack((np.array(0.), np.array(0.))),
opts=dict(legend=['train', 'test'],
xlabel='epoch',
ylabel='snr',
title='SNR'))
# Start Training
print()
train = Train(model, train_loader, optimizer, criterion, device)
val = Test(model, val_loader, criterion, device)
for epoch in range(start_epoch, args.epochs):
print(">>>> [Epoch: {0:d}] Training".format(epoch))
epoch_loss, epoch_snr = train.run_epoch(lr_updater, args.print_step)
lr_updater.step()
print(
">>>> [Epoch: {0:d}] Avg. loss: {1:.4f} Avg. snr: {2:.4f} Lr: {3:f}"
.format(epoch, epoch_loss, epoch_snr,
lr_updater.get_lr()[0]))
if (epoch + 1) % 1 == 0 or epoch + 1 == args.epochs:
print(">>>> [Epoch: {0:d}] Validation".format(epoch))
loss, snr = val.run_epoch(args.print_step)
print(">>>> [Epoch: {0:d}] Avg. loss: {1:.4f} Avg. snr: {2:.4f}".
format(epoch, loss, snr))
# Save the model if it's the best thus far
if snr > best_snr:
print("\nBest model thus far. Saving...\n")
best_snr = snr
utils.save_checkpoint(model, optimizer, epoch + 1, best_loss,
best_snr, args)
if args.visdom:
vis.line(X=np.column_stack((np.array(epoch), np.array(epoch))),
Y=np.column_stack((np.array(epoch_loss), np.array(loss))),
win=loss_win,
update='append')
vis.line(X=np.column_stack((np.array(epoch), np.array(epoch))),
Y=np.column_stack((np.array(epoch_snr), np.array(snr))),
win=snr_win,
update='append')
return model
# Fail fast if the dataset directory doesn't exist
assert os.path.isdir(
args.dataset_dir), "The directory \"{0}\" doesn't exist.".format(
args.dataset_dir)
# Fail fast if the saving directory doesn't exist
assert os.path.isdir(
args.save_dir), "The directory \"{0}\" doesn't exist.".format(
args.save_dir)
train_loader, val_loader, test_loader = load_dataset(dataset)
circ_S, _ = hadamard_s(args.matrix_size)
if args.mode.lower() in {'train', 'full'}:
model = train(train_loader, val_loader, circ_S)
if args.mode.lower() in {'test', 'full'}:
if args.mode.lower() == 'test':
# Intialize a new ERFNet model
model = ERFNet(1).to(device).double()
# Initialize a optimizer just so we can retrieve the model from the
# checkpoint
optimizer = optim.Adam(model.parameters())
# Load the previoulsy saved model state to the ERFNet model
model = utils.load_checkpoint(model, optimizer, args.save_dir,
args.name)[0]
test(model, test_loader, circ_S)
# im = Image.open('images/test.jpg')
im = Image.open('/aimldl-dat/samples/lanenet/4.jpg')
print(im)
# ipynb visualization
# get_ipython().run_line_magic('matplotlib', 'inline')
imgplot = imshow(np.asarray(im))
show()
im = im.resize((WIDTH, HEIGHT))
im_tensor = ToTensor()(im)
im_tensor = im_tensor.unsqueeze(0)
# We also need to load the weights of the CNNs. We simply load it using pytorch methods.
# Creating CNNs and loading pretrained models
segmentation_network = ERFNet(NUM_CLASSES_SEGMENTATION)
classification_network = LCNet(NUM_CLASSES_CLASSIFICATION, DESCRIPTOR_SIZE,
DESCRIPTOR_SIZE)
segmentation_network.load_state_dict(
torch.load('pretrained/erfnet_tusimple.pth', map_location=map_location))
model_path = 'pretrained/classification_{}_{}class.pth'.format(
DESCRIPTOR_SIZE, NUM_CLASSES_CLASSIFICATION)
classification_network.load_state_dict(
torch.load(model_path, map_location=map_location))
segmentation_network = segmentation_network.eval()
classification_network = classification_network.eval()
if torch.cuda.is_available():
segmentation_network = segmentation_network.cuda()
def video():
print('testing from video')
cameraWidth = 1920
cameraHeight = 1080
cameraMatrix = np.matrix([[1.3878727764994030e+03, 0, cameraWidth / 2],
[0, 1.7987055172413220e+03, cameraHeight / 2],
[0, 0, 1]])
distCoeffs = np.matrix([
-5.8881725390917083e-01, 5.8472404395779809e-01,
-2.8299599929891900e-01, 0
])
vidcap = cv2.VideoCapture('test_content/massachusetts.mp4')
success = True
i = 0
while success:
success, img = vidcap.read()
if i % 1000 == 0:
print("frame: ", i)
if args.rmdistort:
P = cv2.fisheye.estimateNewCameraMatrixForUndistortRectify(
cameraMatrix, distCoeffs, (cameraWidth, cameraHeight),
None)
map1, map2 = cv2.fisheye.initUndistortRectifyMap(
cameraMatrix, distCoeffs, np.eye(3), P, (1920, 1080),
cv2.CV_16SC2)
img = cv2.remap(img, map1, map2, cv2.INTER_LINEAR)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img = Image.fromarray(img)
# img = img.convert('RGB')
# cv2.imshow('',img)
# cv2.waitKey(0)
# img2 = Image.open(filename).convert('RGB')
class_encoding = color_encoding = OrderedDict([
('unlabeled', (0, 0, 0)), ('road', (128, 64, 128)),
('sidewalk', (244, 35, 232)), ('building', (70, 70, 70)),
('wall', (102, 102, 156)), ('fence', (190, 153, 153)),
('pole', (153, 153, 153)), ('traffic_light', (250, 170, 30)),
('traffic_sign', (220, 220, 0)),
('vegetation', (107, 142, 35)), ('terrain', (152, 251, 152)),
('sky', (70, 130, 180)), ('person', (220, 20, 60)),
('rider', (255, 0, 0)), ('car', (0, 0, 142)),
('truck', (0, 0, 70)), ('bus', (0, 60, 100)),
('train', (0, 80, 100)), ('motorcycle', (0, 0, 230)),
('bicycle', (119, 11, 32))
])
num_classes = len(class_encoding)
model_path = os.path.join(args.save_dir, args.name)
checkpoint = torch.load(model_path)
model = ERFNet(num_classes)
model = model.cuda()
model.load_state_dict(checkpoint['state_dict'])
img = img.resize((args.width, args.height), Image.BILINEAR)
start = time.time()
images = transforms.ToTensor()(img)
torch.reshape(images, (1, 3, args.width, args.height))
images = images.unsqueeze(0)
with torch.no_grad():
images = images.cuda()
predictions = model(images)
end = time.time()
print('model speed:', int(1 / (end - start)), "FPS")
_, predictions = torch.max(predictions.data, 1)
label_to_rgb = transforms.Compose([
utils.LongTensorToRGBPIL(class_encoding),
transforms.ToTensor()
])
color_predictions = utils.batch_transform(
predictions.cpu(), label_to_rgb)
end = time.time()
print('model+transform:', int(1 / (end - start)), "FPS")
utils.imshow_batch(images.data.cpu(), color_predictions)
i += 1
def train(train_loader, val_loader, class_weights, class_encoding):
print("Training...")
num_classes = len(class_encoding)
model = ERFNet(num_classes)
criterion = nn.CrossEntropyLoss(weight=class_weights)
optimizer = optim.Adam(model.parameters(),
lr=args.learning_rate,
weight_decay=args.weight_decay)
# Learning rate decay scheduler
lr_updater = lr_scheduler.StepLR(optimizer, args.lr_decay_epochs,
args.lr_decay)
# Evaluation metric
if args.ignore_unlabeled:
ignore_index = list(class_encoding).index('unlabeled')
else:
ignore_index = None
metric = IoU(num_classes, ignore_index=ignore_index)
if use_cuda:
model = model.cuda()
criterion = criterion.cuda()
# Optionally resume from a checkpoint
if args.resume:
model, optimizer, start_epoch, best_miou, val_miou, train_miou, val_loss, train_loss = utils.load_checkpoint(
model, optimizer, args.save_dir, args.name, True)
print(
"Resuming from model: Start epoch = {0} | Best mean IoU = {1:.4f}".
format(start_epoch, best_miou))
else:
start_epoch = 0
best_miou = 0
val_miou = []
train_miou = []
val_loss = []
train_loss = []
# Start Training
train = Train(model, train_loader, optimizer, criterion, metric, use_cuda)
val = Test(model, val_loader, criterion, metric, use_cuda)
for epoch in range(start_epoch, args.epochs):
print(">> [Epoch: {0:d}] Training".format(epoch))
lr_updater.step()
epoch_loss, (iou, miou) = train.run_epoch(args.print_step)
print(
">> [Epoch: {0:d}] Avg. loss: {1:.4f} | Mean IoU: {2:.4f}".format(
epoch, epoch_loss, miou))
train_loss.append(epoch_loss)
train_miou.append(miou)
#preform a validation test
if (epoch + 1) % 10 == 0 or epoch + 1 == args.epochs:
print(">>>> [Epoch: {0:d}] Validation".format(epoch))
loss, (iou, miou) = val.run_epoch(args.print_step)
print(">>>> [Epoch: {0:d}] Avg. loss: {1:.4f} | Mean IoU: {2:.4f}".
format(epoch, loss, miou))
val_loss.append(loss)
val_miou.append(miou)
# Print per class IoU on last epoch or if best iou
if epoch + 1 == args.epochs or miou > best_miou:
for key, class_iou in zip(class_encoding.keys(), iou):
print("{0}: {1:.4f}".format(key, class_iou))
# Save the model if it's the best thus far
if miou > best_miou:
print("Best model thus far. Saving...")
best_miou = miou
utils.save_checkpoint(model, optimizer, epoch + 1, best_miou,
val_miou, train_miou, val_loss,
train_loss, args)
return model, train_loss, train_miou, val_loss, val_miou
loaders, w_class, class_encoding = load_dataset(dataset)
train_loader, val_loader, test_loader = loaders
if args.mode.lower() in {'train'}:
model, tl, tmiou, vl, vmiou = train(train_loader, val_loader,
w_class, class_encoding)
plt.plot(tl, label="train loss")
plt.plot(tmiou, label="train miou")
plt.plot(vl, label="val loss")
plt.plot(vmiou, label="val miou")
plt.legend()
plt.xlabel("Epoch")
plt.ylabel("loss/accuracy")
plt.grid(True)
plt.xticks()
plt.savefig('./plots/train.png')
elif args.mode.lower() == 'test':
num_classes = len(class_encoding)
#model = ENet(num_classes)
model = ERFNet(num_classes)
if use_cuda:
model = model.cuda()
optimizer = optim.Adam(model.parameters())
model = utils.load_checkpoint(model, optimizer, args.save_dir,
args.name)[0]
test(model, test_loader, w_class, class_encoding)
else:
raise RuntimeError(
"\"{0}\" is not a valid choice for execution mode.".format(
args.mode))