sub_folders.sort()
for folder in sub_folders:
# Get color image filenames
test_filenames = utils.get_file_names_in_sequence(
sequence_root=folder)
if len(test_filenames) == 0:
print("Sequence {} does not have relevant files".format(
str(folder)))
continue
test_dataset = dataset.SfMDataset(
image_file_names=test_filenames,
folder_list=folder_list,
adjacent_range=adjacent_range,
image_downsampling=image_downsampling,
inlier_percentage=inlier_percentage,
network_downsampling=network_downsampling,
load_intermediate_data=load_intermediate_data,
intermediate_data_root=precompute_root,
phase="test",
pre_workers=num_pre_workers,
visible_interval=visibility_overlap)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
batch_size=1,
shuffle=False,
num_workers=num_workers)
# Update progress bar
tq = tqdm.tqdm(total=len(test_loader),
dynamic_ncols=True,
ncols=40)
tq.set_description('Test')
print("Tensorboard visualization at {}".format(str(log_root)))
# Get color image filenames
train_filenames, val_filenames, test_filenames = utils.get_color_file_names_by_bag(training_data_root,
validation_patient_id=validation_patient_id,
testing_patient_id=testing_patient_id,
id_range=id_range)
folder_list = utils.get_parent_folder_names(training_data_root,
id_range=id_range)
# Build training and validation dataset
train_dataset = dataset.SfMDataset(image_file_names=train_filenames,
folder_list=folder_list,
adjacent_range=adjacent_range, transform=training_transforms,
downsampling=input_downsampling,
network_downsampling=network_downsampling, inlier_percentage=inlier_percentage,
use_store_data=load_intermediate_data,
store_data_root=training_data_root,
phase="train", is_hsv=is_hsv,
num_pre_workers=num_workers, visible_interval=30, rgb_mode="rgb")
validation_dataset = dataset.SfMDataset(image_file_names=val_filenames,
folder_list=folder_list,
adjacent_range=adjacent_range,
transform=None,
downsampling=input_downsampling,
network_downsampling=network_downsampling,
inlier_percentage=inlier_percentage,
use_store_data=True,
store_data_root=training_data_root,
phase="validation", is_hsv=is_hsv,
num_pre_workers=num_workers, visible_interval=30, rgb_mode="rgb")
train_filenames, val_filenames, test_filenames = \
utils.get_color_file_names_by_bag(root=training_data_root, training_patient_id=training_patient_id,
validation_patient_id=validation_patient_id,
testing_patient_id=testing_patient_id)
sequence_path_list = utils.get_parent_folder_names(training_data_root, id_range=id_range)
# Build training and validation dataset
train_dataset = dataset.SfMDataset(image_file_names=train_filenames,
folder_list=sequence_path_list,
adjacent_range=adjacent_range,
image_downsampling=image_downsampling,
inlier_percentage=inlier_percentage,
network_downsampling=network_downsampling,
load_intermediate_data=load_intermediate_data,
intermediate_data_root=precompute_root,
sampling_size=sampling_size,
phase="train", heatmap_sigma=heatmap_sigma,
pre_workers=num_pre_workers,
visible_interval=visibility_overlap,
num_iter=num_iter)
train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True,
num_workers=num_workers)
val_dataset = dataset.SfMDataset(image_file_names=val_filenames,
folder_list=sequence_path_list,
adjacent_range=adjacent_range,
image_downsampling=image_downsampling,
inlier_percentage=inlier_percentage,
network_downsampling=network_downsampling,
# Get color image filenames
test_filenames = utils.get_filenames_from_frame_indexes(
sequence_root, selected_frame_index_list)
folder_list = utils.get_parent_folder_names(evaluation_data_root,
id_range=id_range)
if phase == "validation":
test_dataset = dataset.SfMDataset(
image_file_names=test_filenames,
folder_list=folder_list,
adjacent_range=adjacent_range,
transform=None,
downsampling=input_downsampling,
network_downsampling=network_downsampling,
inlier_percentage=inlier_percentage,
use_store_data=load_intermediate_data,
store_data_root=evaluation_data_root,
phase="validation",
is_hsv=is_hsv,
num_pre_workers=num_pre_workers,
visible_interval=visibility_overlap,
rgb_mode="rgb")
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
batch_size=batch_size,
shuffle=False,
num_workers=0)
depth_estimation_model = models.FCDenseNet57(n_classes=1)
# Initialize the depth estimation network with Kaiming He initialization
utils.init_net(depth_estimation_model,
try:
results_root.mkdir(mode=0o777, parents=True)
except OSError:
pass
# Get color image filenames
train_filenames, val_filenames, test_filenames = utils.get_color_file_names_by_bag(training_data_root,
which_bag=which_bag,
split_ratio=(0.5, 0.5))
training_folder_list, val_folder_list = utils.get_parent_folder_names(training_data_root, which_bag=which_bag)
# Build training and validation dataset
train_dataset = dataset.SfMDataset(image_file_names=train_filenames,
folder_list=training_folder_list + val_folder_list,
adjacent_range=adjacent_range, to_augment=True, transform=training_transforms,
downsampling=downsampling,
net_depth=teacher_depth, inlier_percentage=inlier_percentage,
use_store_data=load_intermediate_data,
store_data_root=precompute_root,
use_view_indexes_per_point=use_view_indexes_per_point, visualize=visualize,
phase="train", is_hsv=is_hsv)
train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=shuffle,
num_workers=num_workers)
# Load trained teacher model
depth_estimation_model_teacher = models.UNet(in_channels=3, out_channels=1, depth=teacher_depth, wf=filter_base,
padding=True, up_mode='upsample')
# Initialize the depth estimation network with Kaiming He initialization
utils.init_net(depth_estimation_model_teacher, type="kaiming", mode="fan_in", activation_mode="relu",
distribution="normal")
# Multi-GPU running
depth_estimation_model_teacher = torch.nn.DataParallel(depth_estimation_model_teacher)
depth_estimation_model_teacher.train()