def add_dataset(
dset_fp,
list_ids,
up3d_fp, # pylint: disable=too-many-locals, too-many-arguments, too-many-statements, too-many-branches, unused-argument
train_dset,
val_dset,
test_dset,
train_spec,
val_spec,
test_spec,
target_person_size,
landmarks,
train_crop,
test_crop,
train_steps_x,
train_steps_y,
running_idx,
only_missing=False):
"""Add a dataset to the collection."""
test_ids = [int(id_[1:6]) for id_ in test_spec]
train_ids = [int(id_[1:6]) for id_ in train_spec]
val_ids = [int(id_[1:6]) for id_ in val_spec]
LOGGER.info("Split: %d train, %d val, %d test.", len(train_ids),
len(val_ids), len(test_ids))
LOGGER.info("Writing dataset...")
for im_idx in tqdm.tqdm(train_ids + val_ids + test_ids):
image = scipy.misc.imread(
path.join(up3d_fp, '%05d_image.png' % (im_idx)))
with open(path.join(up3d_fp, '%05d_fit_crop_info.txt' % (im_idx)),
'r') as inf:
cropinfo = [int(val) for val in inf.readline().strip().split()]
fac_y = cropinfo[0] / float(cropinfo[3] - cropinfo[2])
fac_x = cropinfo[1] / float(cropinfo[5] - cropinfo[4])
rec_scale = np.mean([fac_x, fac_y])
rec_x = cropinfo[4]
rec_y = cropinfo[2]
assert image.ndim == 3
out_exists = (path.exists(
path.join(dset_fp, '%05d_image.png' % (running_idx)))
and path.exists(
path.join(dset_fp, '%05d_ann_vis.png' %
(running_idx))))
joints = np.load(path.join(up3d_fp, '%05d_joints.npy' % (im_idx)))
joints = np.vstack((joints, np.all(joints > 0, axis=0)[None, :]))
person_size = robust_person_size(joints)
norm_factor = float(target_person_size) / person_size
joints[:2, :] *= norm_factor
image = scipy.misc.imresize(image, norm_factor, interp='bilinear')
if im_idx in test_ids:
crop = test_crop
else:
crop = train_crop
if image.shape[0] > crop or image.shape[1] > crop:
LOGGER.debug(
"Image (original %d, here %d) too large (%s)! Cropping...",
im_idx, running_idx, str(image.shape[:2]))
person_center = np.mean(joints[:2, joints[2, :] == 1], axis=1)
crop_y, crop_x = get_crop(image, person_center, crop)
image = image[crop_y[0]:crop_y[1], crop_x[0]:crop_x[1], :]
assert image.shape[0] == crop or image.shape[1] == crop, (
"Error cropping image (original %d, here %d)!" %
(im_idx, running_idx))
else:
crop_x = [0, image.shape[1]]
crop_y = [0, image.shape[0]]
assert image.shape[0] <= crop and image.shape[
1] <= crop and image.shape[2] == 3, (
"Wrong image shape (original %d, here %d)!" %
(im_idx, running_idx))
if not (only_missing and out_exists):
if im_idx in test_ids:
steps_x = 1
steps_y = 1
else:
steps_x = train_steps_x
steps_y = train_steps_y
LOGGER.debug('Crop infos: x: %s, y: %s', str(crop_x), str(crop_y))
landmark_pos_list, full_parameter_list = get_landmark_positions(
path.join(up3d_fp, '%05d_body.pkl' % (im_idx)),
(image.shape[1], image.shape[0]),
(cropinfo[1], cropinfo[0]),
landmarks,
trans=(
-crop_x[0] - rec_x, # pylint: disable=line-too-long
-crop_y[0] - rec_y), # pylint: disable=line-too-long
scale=norm_factor / rec_scale, # pylint: disable=line-too-long
steps_x=steps_x,
steps_y=steps_y)
if im_idx in train_ids:
append_dset = train_dset
elif im_idx in val_ids:
append_dset = val_dset
elif im_idx in test_ids:
append_dset = test_dset
for rend_idx, (landmark_pos, full_parameters) in enumerate( # pylint: disable=unused-variable
zip(landmark_pos_list, full_parameter_list)):
append_dset.resize(append_dset.shape[0] + 1, axis=0)
append_dset[-1, :] = landmark_pos + full_parameters
running_idx += 1
return running_idx
def add_dataset(
dset_fp,
dset_fromroot,
list_ids,
up3d_fp, # pylint: disable=too-many-locals, too-many-arguments, too-many-statements, too-many-branches
train_list_f,
val_list_f,
train_val_list_f,
test_list_f,
scale_f,
train_spec,
val_spec,
test_spec,
target_person_size,
landmarks,
train_crop,
test_crop,
running_idx,
only_missing=False,
with_rlswap=True,
write_gtjoints_as_lm=False,
human_annotations=False):
"""Add a dataset to the collection."""
test_ids = [int(id_[1:6]) for id_ in test_spec]
train_ids = [int(id_[1:6]) for id_ in train_spec]
val_ids = [int(id_[1:6]) for id_ in val_spec]
LOGGER.info("Split: %d train, %d val, %d test.", len(train_ids),
len(val_ids), len(test_ids))
LOGGER.info("Writing dataset...")
for im_idx in tqdm.tqdm(train_ids + val_ids + test_ids):
image = scipy.misc.imread(
path.join(up3d_fp, '%05d_image.png' % (im_idx)))
with open(path.join(up3d_fp, '%05d_fit_crop_info.txt' % (im_idx)),
'r') as inf:
cropinfo = [int(val) for val in inf.readline().strip().split()]
assert image.ndim == 3
out_exists = (path.exists(
path.join(dset_fp, '%05d_image.png' % (running_idx)))
and path.exists(
path.join(dset_fp, '%05d_ann_vis.png' %
(running_idx))))
if with_rlswap and im_idx not in test_ids:
out_exists = out_exists and (path.exists(
path.join(dset_fp, '%05d_image.png' %
(running_idx + 1))) and path.exists(
path.join(dset_fp, '%05d_ann_vis.png' %
(running_idx + 1))))
if not (only_missing and out_exists or write_gtjoints_as_lm):
if human_annotations:
landmark_pos = np.load(
path.join(up3d_fp, '%05d_joints.npy' % (im_idx)))
else:
landmark_pos = get_landmark_positions(
path.join(up3d_fp, '%05d_body.pkl' % (im_idx)),
(cropinfo[1], cropinfo[0]), landmarks)
fac_y = cropinfo[0] / float(cropinfo[3] - cropinfo[2])
fac_x = cropinfo[1] / float(cropinfo[5] - cropinfo[4])
landmark_pos[:2, :] /= np.mean([fac_x, fac_y])
landmark_pos[0, :] += cropinfo[4]
landmark_pos[1, :] += cropinfo[2]
joints = np.load(path.join(up3d_fp, '%05d_joints.npy' % (im_idx)))
joints = np.vstack((joints, np.all(joints > 0, axis=0)[None, :]))
person_size = robust_person_size(joints)
norm_factor = float(target_person_size) / person_size
joints[:2, :] *= norm_factor
if not (only_missing and out_exists or write_gtjoints_as_lm):
landmark_pos[:2, :] *= norm_factor
if write_gtjoints_as_lm:
landmark_pos = joints.copy()
image = scipy.misc.imresize(image, norm_factor, interp='bilinear')
if im_idx in test_ids:
crop = test_crop
else:
crop = train_crop
if image.shape[0] > crop or image.shape[1] > crop:
LOGGER.debug(
"Image (original %d, here %d) too large (%s)! Cropping...",
im_idx, running_idx, str(image.shape[:2]))
person_center = np.mean(joints[:2, joints[2, :] == 1], axis=1)
crop_y, crop_x = get_crop(image, person_center, crop)
image = image[crop_y[0]:crop_y[1], crop_x[0]:crop_x[1], :]
landmark_pos[0, :] -= crop_x[0]
landmark_pos[1, :] -= crop_y[0]
assert image.shape[0] == crop or image.shape[1] == crop, (
"Error cropping image (original %d, here %d)!" %
(im_idx, running_idx))
assert image.shape[0] <= crop and image.shape[
1] <= crop and image.shape[2] == 3, (
"Wrong image shape (original %d, here %d)!" %
(im_idx, running_idx))
vis_im = vs.visualize_pose(image, landmark_pos, scale=1.)
if not (only_missing and out_exists):
scipy.misc.imsave(
path.join(dset_fp, '%05d_image.png' % (running_idx)), image)
scipy.misc.imsave(
path.join(dset_fp, '%05d_ann_vis.png' % (running_idx)), vis_im)
if with_rlswap and im_idx not in test_ids:
if landmark_pos.shape[1] == 14:
landmark_pos_swapped = landmark_pos[:, rlswap_lsp]
else:
landmark_pos_swapped = landmark_pos[:, rlswap_landmarks_91]
landmark_pos_swapped[
0, :] = image.shape[1] - landmark_pos_swapped[0, :]
image_swapped = image[:, ::-1, :]
# Use core visualization for 14 joints.
vis_im_swapped = vs.visualize_pose(image_swapped,
landmark_pos_swapped,
scale=1)
if not (only_missing and out_exists):
scipy.misc.imsave(
path.join(dset_fp, '%05d_image.png' % (running_idx + 1)),
image_swapped)
scipy.misc.imsave(
path.join(dset_fp, '%05d_ann_vis.png' % (running_idx + 1)),
vis_im_swapped)
list_fs = []
list_id_ids = []
if im_idx in train_ids:
list_fs.append(train_val_list_f)
list_id_ids.append(2)
list_fs.append(train_list_f)
list_id_ids.append(0)
elif im_idx in val_ids:
list_fs.append(train_val_list_f)
list_id_ids.append(2)
list_fs.append(val_list_f)
list_id_ids.append(1)
elif im_idx in test_ids:
list_fs.append(test_list_f)
list_id_ids.append(3)
for list_f, list_id_idx in zip(list_fs, list_id_ids):
# pylint: disable=bad-continuation
list_f.write("""# %d
%s
3
%d
%d
%d
""" % (list_ids[list_id_idx],
path.join('/' + dset_fromroot, '%05d_image.png' % (running_idx)),
image.shape[0], image.shape[1], landmark_pos.shape[1]))
for landmark_idx, landmark_point in enumerate(landmark_pos.T):
list_f.write("%d %d %d\n" %
(landmark_idx + 1, int(
landmark_point[0]), int(landmark_point[1])))
list_f.flush()
list_ids[list_id_idx] += 1
scale_f.write("%05d_image.png %f\n" % (running_idx, norm_factor))
scale_f.flush()
running_idx += 1
if with_rlswap and im_idx not in test_ids:
for list_f, list_id_idx in zip(list_fs, list_id_ids):
# pylint: disable=bad-continuation
list_f.write("""# %d
%s
3
%d
%d
%d
""" % (list_ids[list_id_idx],
path.join('/' + dset_fromroot, '%05d_image.png' % (running_idx)),
image.shape[0], image.shape[1], landmark_pos.shape[1]))
for landmark_idx, landmark_point in enumerate(
landmark_pos_swapped.T):
list_f.write(
"%d %d %d\n" % (landmark_idx + 1, int(
landmark_point[0]), int(landmark_point[1])))
list_f.flush()
list_ids[list_id_idx] += 1
scale_f.write("%05d_image.png %f\n" % (running_idx, norm_factor))
scale_f.flush()
running_idx += 1
return running_idx
def add_dataset(dset_fp, dset_rel_fp, up3d_fp, # pylint: disable=too-many-locals, too-many-arguments, too-many-statements, too-many-branches
train_list_f, val_list_f, test_list_f,
train_spec, val_spec, test_spec,
target_person_size, landmarks, partspec, crop, running_idx,
only_missing=False):
"""Add a dataset to the collection."""
test_ids = [int(id_[1:6]) for id_ in test_spec]
train_ids = [int(id_[1:6]) for id_ in train_spec]
val_ids = [int(id_[1:6]) for id_ in val_spec]
ids_list = sorted(train_ids + val_ids + test_ids)
LOGGER.info("Split: %d train, %d val, %d test.",
len(train_ids), len(val_ids), len(test_ids))
LOGGER.info("Writing dataset...")
for im_idx in tqdm.tqdm(ids_list):
image = scipy.misc.imread(path.join(up3d_fp, '%05d_image.png' % (im_idx)))
with open(path.join(up3d_fp, '%05d_fit_crop_info.txt' % (im_idx)), 'r') as inf:
cropinfo = [int(val) for val in inf.readline().strip().split()]
assert image.ndim == 3
out_exists = (path.exists(path.join(dset_fp, '%05d_image.png' % (running_idx))) and
path.exists(path.join(dset_fp, '%05d_ann.png' % (running_idx))) and
path.exists(path.join(dset_fp, '%05d_ann_vis.png' % (running_idx))) and
path.exists(path.join(dset_fp, '%05d_render.png' % (running_idx))) and
path.exists(path.join(dset_fp, '%05d_render_light.png' % (running_idx))))
if not (only_missing and out_exists):
rendering = uncrop(render_body_impl(path.join(up3d_fp, '%05d_body.pkl' % (im_idx)),
resolution=(cropinfo[1],
cropinfo[0]),
quiet=True,
use_light=False)[0],
image.shape[:2],
cropinfo)
rendering_l = uncrop(render_body_impl(path.join(up3d_fp, '%05d_body.pkl' % (im_idx)),
resolution=(cropinfo[1],
cropinfo[0]),
quiet=True,
use_light=True)[0],
image.shape[:2],
cropinfo)
joints = np.load(path.join(up3d_fp, '%05d_joints.npy' % (im_idx)))
joints = np.vstack((joints, np.all(joints > 0, axis=0)[None, :]))
person_size = robust_person_size(joints)
norm_factor = float(target_person_size) / person_size
landmark_pos = get_landmark_positions(path.join(up3d_fp, '%05d_body.pkl' % (im_idx)),
(cropinfo[1], cropinfo[0]),
landmarks)
fac_y = cropinfo[0] / float(cropinfo[3] - cropinfo[2])
fac_x = cropinfo[1] / float(cropinfo[5] - cropinfo[4])
landmark_pos[:2, :] /= np.mean([fac_x, fac_y])
landmark_pos[0, :] += cropinfo[4]
landmark_pos[1, :] += cropinfo[2]
landmark_pos[:2, :] *= norm_factor
if not (only_missing and out_exists):
image = scipy.misc.imresize(image, norm_factor, interp='bilinear')
rendering = scipy.misc.imresize(rendering, norm_factor, interp='nearest')
rendering_l = scipy.misc.imresize(rendering_l, norm_factor, interp='bilinear')
if image.shape[0] > crop or image.shape[1] > crop:
LOGGER.debug("Image (original %d, here %d) too large (%s)! Cropping...",
im_idx, running_idx, str(image.shape[:2]))
person_center = np.mean(joints[:2, joints[2, :] == 1], axis=1) * norm_factor
crop_y, crop_x = get_crop(image, person_center, crop)
image = image[crop_y[0]:crop_y[1],
crop_x[0]:crop_x[1], :]
rendering = rendering[crop_y[0]:crop_y[1],
crop_x[0]:crop_x[1], :]
rendering_l = rendering_l[crop_y[0]:crop_y[1],
crop_x[0]:crop_x[1], :]
landmark_pos[0, :] -= crop_x[0]
landmark_pos[1, :] -= crop_y[0]
assert image.shape[0] == crop or image.shape[1] == crop, (
"Error cropping image (original %d, here %d)!" % (im_idx,
running_idx))
assert image.shape[0] <= crop and image.shape[1] <= crop and image.shape[2] == 3, (
"Wrong image shape (original %d, here %d)!" % (im_idx, running_idx))
class_groups = six_region_groups if partspec == '6' else None
annotation = regions_to_classes(rendering, class_groups, warn_id=str(im_idx))
if partspec == '1':
annotation = (annotation > 0).astype('uint8')
assert np.max(annotation) <= int(partspec), (
"Wrong annotation value (original %d, here %d): %s!" % (
im_idx, running_idx, str(np.unique(annotation))))
if running_idx == 0:
assert np.max(annotation) == int(partspec), (
"Probably an error in the number of parts!")
pose_vis_im = vs.visualize_pose(cv2.cvtColor(annotation*8, cv2.COLOR_GRAY2RGB),
landmark_pos,
scale=1.)
scipy.misc.imsave(path.join(dset_fp, '%05d_image.png' % (running_idx)), image)
scipy.misc.imsave(path.join(dset_fp, '%05d_ann.png' % (running_idx)), annotation)
scipy.misc.imsave(path.join(dset_fp, '%05d_seg_ann_vis.png' % (running_idx)),
apply_colormap(annotation, vmax=int(partspec)))
# scipy.misc.imsave(path.join(dset_fp, '%05d_render.png' % (running_idx)), rendering)
scipy.misc.imsave(path.join(dset_fp, '%05d_render_light.png' % (running_idx)), rendering_l) # pylint: disable=line-too-long
scipy.misc.imsave(path.join(dset_fp, '%05d_pose_ann_vis.png' % (running_idx)), pose_vis_im)
landmark_pos = np.concatenate((landmark_pos, joints[2][None, :]))
np.save(str(path.join(dset_fp, '%05d_joints.npy' % (running_idx))), landmark_pos, allow_pickle=False)
if im_idx in train_ids:
list_f = train_list_f
elif im_idx in val_ids:
list_f = val_list_f
elif im_idx in test_ids:
list_f = test_list_f
list_f.write("/%s/%05d_image.png /%s/%05d_ann.png %f\n" % (
dset_rel_fp, running_idx, dset_rel_fp, running_idx, norm_factor))
list_f.flush()
running_idx += 1
return running_idx