def vis_mask_(im, mask, save_path):
assert im.shape[:2] == mask.shape
ori_mask = mask
mask = mask[..., np.newaxis] * np.array([[[255, 0, 0]]])
mask[ori_mask == 0] = im[ori_mask == 0]
im = im * 0.3 + mask * 0.7
save_im(im, save_path, transpose=False, check_bound=True)
def fuse_parts_(mask_f, new_mask_f):
ori_mask = read_im(mask_f,
convert_rgb=False,
resize_h_w=None,
transpose=False)
mask = ori_mask.copy()
for m in mapping:
mask[ori_mask == m[0]] = m[1]
save_im(mask, new_mask_f, transpose=False, check_bound=False)
def vis_mask_each_part_no_superimpose_(im, mask, save_path, num_parts):
"""
im: [H, W, 3]
mask: [H, W]
"""
assert im.shape[:2] == mask.shape
ims = [im.transpose(2, 0, 1)]
for i in range(num_parts + 1):
m = np.zeros_like(mask)
m[mask == i] = 255
m = np.repeat(m[np.newaxis, ...], 3, 0)
ims.append(m)
im = make_im_grid(ims, 1, len(ims), 8, 128)
save_im(im, save_path, transpose=True, check_bound=True)
def transform(ann, im_dir, save_im_dir, save_mask_dir, split_file):
"""input ann: loaded json"""
may_make_dir(osp.dirname(split_file))
fid = open(split_file, 'w')
im_id_to_name = get_im_id_to_name(ann)
anns = ann['annotations']
i = 0
for ann in anns:
if not 'dp_masks' in ann:
continue
bbox = np.array(ann['bbox']).astype(int)
im = read_im(osp.join(im_dir, im_id_to_name[ann['image_id']]),
resize_h_w=None,
transpose=False)
x1, y1, x2, y2 = bbox[0], bbox[1], bbox[0] + bbox[2], bbox[1] + bbox[3]
x1 = max([x1, 0])
y1 = max([y1, 0])
x2 = min([x2, im.shape[1]])
y2 = min([y2, im.shape[0]])
mask = GetDensePoseMask(ann['dp_masks']).astype(np.uint8)
mask = cv2.resize(mask, (x2 - x1, y2 - y1),
interpolation=cv2.INTER_NEAREST)
assert mask.min() >= 0, "mask.min is {}".format(mask.min())
assert mask.max() <= 14, "mask.max is {}".format(mask.max())
im = im[y1:y2, x1:x2, :]
save_im_name = im_id_to_name[ann['image_id']][:-4] + '_' + str(
ann['id']) + '.jpg'
save_im_path = osp.join(save_im_dir, save_im_name)
save_im(im, save_im_path, transpose=False, check_bound=False)
save_mask_name = im_id_to_name[ann['image_id']][:-4] + '_' + str(
ann['id']) + '.png'
save_mask_path = osp.join(save_mask_dir, save_mask_name)
save_im(mask, save_mask_path, transpose=False, check_bound=False)
rel_im_path = '/'.join(save_im_path.split('/')[-3:])
rel_mask_path = '/'.join(save_mask_path.split('/')[-3:])
fid.write('{}\t{}\n'.format(rel_im_path, rel_mask_path))
i += 1
fid.close()
return len(anns), i
def vis_mask_each_part_(im, mask, save_path, num_parts):
"""
im: [H, W, 3]
mask: [H, W]
"""
assert im.shape[:2] == mask.shape
H, W = mask.shape
# [3, H, W]
im = im.transpose(2, 0, 1)
# dim the image
dim_im = im * 0.5
ims = [im]
for i in range(num_parts + 1):
# [3, H, W]
m = np.array([0, 255, 0])[:, np.newaxis,
np.newaxis].repeat(H, 1).repeat(W, 2)
dim_im_copy = dim_im.copy()
dim_im_copy[:,
mask == i] = dim_im_copy[:, mask == i] * 0.4 + m[:, mask ==
i] * 0.6
ims.append(dim_im_copy)
im = make_im_grid(ims, 1, len(ims), 8, 128)
save_im(im, save_path, transpose=True, check_bound=True)
def vis_mask_(im, mask, save_path, num_parts):
assert im.shape[:2] == mask.shape
mask = cv2.applyColorMap((mask * (255 // num_parts)).astype(np.uint8),
cv2.COLORMAP_PARULA)
im = im * 0.2 + mask * 0.8
save_im(im, save_path, transpose=False, check_bound=True)
def transform(ann,
im_dir,
save_im_dir,
save_mask_dir,
split_file,
to_save_im=False):
"""
Args:
ann: loaded Densepose annotation json
to_save_im: If your cropped images have been saved when preparing part parsing, this can be False
"""
may_make_dir(osp.dirname(split_file))
fid = open(split_file, 'w')
im_id_to_name = get_im_id_to_name(ann)
anns = ann['annotations']
i = 0
n_dp = 0
n_fg = 0
for ann in anns:
i += 1
if not 'dp_masks' in ann:
continue
n_dp += 1
if not 'segmentation' in ann:
continue
n_fg += 1
bbox = np.array(ann['bbox']).astype(int)
im = read_im(osp.join(im_dir, im_id_to_name[ann['image_id']]),
resize_h_w=None,
transpose=False)
x1, y1, x2, y2 = bbox[0], bbox[1], bbox[0] + bbox[2], bbox[1] + bbox[3]
x1 = max([x1, 0])
y1 = max([y1, 0])
x2 = min([x2, im.shape[1]])
y2 = min([y2, im.shape[0]])
# The same resolution as whole image.
MaskIm = annToMask(ann, im.shape[0], im.shape[1])
assert len(MaskIm.shape) == 2, "len(MaskIm.shape) {}".format(
len(MaskIm.shape))
assert MaskIm.shape == im.shape[:
2], "MaskIm.shape {}, im.shape {}".format(
MaskIm.shape, im.shape)
# print('=> im.shape', im.shape)
# print('=> MaskIm.shape', MaskIm.shape)
# print('=> MaskIm.dtype', MaskIm.dtype)
# print('=> np.unique(MaskIm)', np.unique(MaskIm))
# The same resolution as bbox
MaskIm = MaskIm[y1:y2, x1:x2]
# print('=> MaskIm.shape', MaskIm.shape)
check_mask_value_(MaskIm)
save_im_name = im_id_to_name[ann['image_id']][:-4] + '_' + str(
ann['id']) + '.jpg'
save_im_path = osp.join(save_im_dir, save_im_name)
if to_save_im:
im = im[y1:y2, x1:x2, :]
save_im(im, save_im_path, transpose=False, check_bound=False)
save_mask_name = im_id_to_name[ann['image_id']][:-4] + '_' + str(
ann['id']) + '_fg' + '.png'
save_mask_path = osp.join(save_mask_dir, save_mask_name)
save_im(MaskIm, save_mask_path, transpose=False, check_bound=False)
rel_im_path = '/'.join(save_im_path.split('/')[-3:])
rel_mask_path = '/'.join(save_mask_path.split('/')[-3:])
fid.write('{}\t{}\n'.format(rel_im_path, rel_mask_path))
if i % 200 == 0:
print('{}/{} Done'.format(i, len(anns)))
fid.close()
return len(anns), n_dp, n_fg
# infer_im_path_mask_path_file = 'datasets/cuhk03/detected/infer_im_path_mask_path.txt'
infer_im_path_mask_path_file = 'datasets/duke/infer_im_path_mask_path.txt'
lines = read_lines(infer_im_path_mask_path_file, strip=True)
im_paths, mask_paths = zip(*[l.split('\t') for l in lines])
rand_inds = np.random.permutation(range(len(im_paths)))
im_paths = np.array(im_paths)[rand_inds]
mask_paths = np.array(mask_paths)[rand_inds]
num_vis_ims = 64
im_grid_list = []
for i in range(num_vis_ims):
im = read_im(im_paths[i],
convert_rgb=True,
resize_h_w=None,
transpose=False)
mask = read_im(mask_paths[i],
convert_rgb=False,
resize_h_w=None,
transpose=False)
vis_one_im(im,
mask,
nclass,
resize_h_w=(128, 64),
im_grid_list=im_grid_list)
n_cols = 8
n_rows = int(np.ceil(len(im_grid_list) / n_cols))
vis_im = make_im_grid(im_grid_list, n_rows, n_cols, 8, 255)
save_im(vis_im,
'exp/vis_coco_part_pred/cuhk03_detected/vis_im.jpg',
transpose=True,
check_bound=True)
print('# np.unique(MaskIm)', np.unique(MaskIm))
################
MaskBool = np.tile((MaskIm == 0)[:, :, np.newaxis], [1, 1, 3])
# Replace the visualized mask image with I_vis.
Mask_vis = MaskIm[..., np.newaxis] * np.array([[[255, 0, 0]]])
Mask_vis[MaskBool] = im[MaskBool]
im = im.copy().astype(np.float)
im = im * 0.3 + Mask_vis * 0.7
return im
im_dir = '/home/users/houjing.huang/Dataset/coco/val2014/'
ann_json = '/home/users/houjing.huang/Dataset/coco/annotations/densepose_coco_2014_minival.json'
ann = load_json(ann_json)
im_id_to_name = {rec['id']: rec['file_name'] for rec in ann['images']}
save_dir = 'exp/vis_dense_pose/val_set'
i = 0
for ann_ in ann['annotations']:
if not 'dp_masks' in ann_:
continue
i += 1
if i == 11:
break
im = vis_fg(im_dir, ann_)
save_name = im_id_to_name[ann_['image_id']][:-4] + '_' + str(
ann_['id']) + '_fg' + '.jpg'
save_im(im,
osp.join(save_dir, save_name),
transpose=False,
check_bound=True)
