def __getitem__(self, index):
# Load training image
im_name = self.im_list[index]
im_path = os.path.join(self.root, self.dataset + '_images',
im_name + '.jpg')
parsing_anno_path = os.path.join(self.root,
self.dataset + '_segmentations',
im_name + '.png')
im = cv2.imread(im_path, cv2.IMREAD_COLOR)
h, w, _ = im.shape
parsing_anno = np.zeros((h, w), dtype=np.long)
# Get center and scale
center, s = self._box2cs([0, 0, w - 1, h - 1])
r = 0
if self.dataset != 'test':
parsing_anno = cv2.imread(parsing_anno_path, cv2.IMREAD_GRAYSCALE)
if self.dataset == 'train' or self.dataset == 'trainval':
sf = self.scale_factor
rf = self.rotation_factor
s = s * np.clip(np.random.randn() * sf + 1, 1 - sf, 1 + sf)
r = np.clip(np.random.randn() * rf, -rf * 2, rf * 2) \
if random.random() <= 0.6 else 0
if random.random() <= self.flip_prob:
im = im[:, ::-1, :]
parsing_anno = parsing_anno[:, ::-1]
center[0] = im.shape[1] - center[0] - 1
right_idx = [15, 17, 19]
left_idx = [14, 16, 18]
for i in range(0, 3):
right_pos = np.where(parsing_anno == right_idx[i])
left_pos = np.where(parsing_anno == left_idx[i])
parsing_anno[right_pos[0], right_pos[1]] = left_idx[i]
parsing_anno[left_pos[0], left_pos[1]] = right_idx[i]
trans = get_affine_transform(center, s, r, self.crop_size)
input = cv2.warpAffine(
im,
trans, (int(self.crop_size[1]), int(self.crop_size[0])),
flags=cv2.INTER_LINEAR,
borderMode=cv2.BORDER_CONSTANT,
borderValue=(0, 0, 0))
if self.transform:
input = self.transform(input)
meta = {
'name': im_name,
'center': center,
'height': h,
'width': w,
'scale': s,
'rotation': r
}
if self.dataset != 'train':
return input, meta
else:
label_parsing = cv2.warpAffine(
parsing_anno,
trans, (int(self.crop_size[1]), int(self.crop_size[0])),
flags=cv2.INTER_NEAREST,
borderMode=cv2.BORDER_CONSTANT,
borderValue=(255))
label_edge = generate_edge(label_parsing)
label_parsing = torch.from_numpy(label_parsing)
label_edge = torch.from_numpy(label_edge)
return input, label_parsing, label_edge, meta
def __getitem__(self, index):
im_name = self.im_list[index]
im_path = os.path.join(self.root, self.dataset + '_images',
im_name + '.jpg')
parsing_anno_path = os.path.join(self.root,
self.dataset + '_segmentations',
im_name + '.png')
im = cv2.imread(im_path, cv2.IMREAD_COLOR)
h, w, _ = im.shape
parsing_anno = np.zeros((h, w), dtype=np.long)
# get pose anno
if self.dataset == 'train' or self.dataset == 'val':
joints_all_info = np.array(self.pose_info[im_name])
joints_loc = np.zeros((joints_all_info.shape[0], 2))
joints_loc[:, :] = joints_all_info[:, 0:2] # 1st and 2nd column
# get visibility of joints
coord_sum = np.sum(joints_loc, axis=1)
visibility = coord_sum != 0
# Get center and scale
center, s = self._box2cs([0, 0, w - 1, h - 1])
r = 0
if self.dataset != 'test':
parsing_anno = cv2.imread(parsing_anno_path, cv2.IMREAD_GRAYSCALE)
if self.dataset == 'train' or self.dataset == 'trainval':
sf = self.scale_factor
rf = self.rotation_factor
s = s * np.clip(np.random.randn() * sf + 1, 1 - sf, 1 + sf)
r = np.clip(np.random.randn() * rf, -rf * 2, rf * 2) \
if random.random() <= 0.6 else 0
if random.random() <= self.flip_prob:
im = im[:, ::-1, :]
parsing_anno = parsing_anno[:, ::-1]
center[0] = im.shape[1] - center[0] - 1
right_idx = [15, 17, 19]
left_idx = [14, 16, 18]
for i in range(0, 3):
right_pos = np.where(parsing_anno == right_idx[i])
left_pos = np.where(parsing_anno == left_idx[i])
parsing_anno[right_pos[0], right_pos[1]] = left_idx[i]
parsing_anno[left_pos[0], left_pos[1]] = right_idx[i]
# flip the joints
joints_loc = flip_joints(joints_loc, w)
# swap the visibility of left and right joints
r_joint = [0, 1, 2, 10, 11, 12]
l_joint = [3, 4, 5, 13, 14, 15]
for i in range(0, 6):
temp_visibility = visibility[r_joint[i]]
visibility[r_joint[i]] = visibility[l_joint[i]]
visibility[l_joint[i]] = temp_visibility
trans = get_affine_transform(center, s, r, self.crop_size)
input = cv2.warpAffine(
im,
trans, (int(self.crop_size[1]), int(self.crop_size[0])),
flags=cv2.INTER_LINEAR,
borderMode=cv2.BORDER_CONSTANT,
borderValue=(0, 0, 0))
if self.transform:
input = self.transform(input)
meta = {
'name': im_name,
'center': center,
'height': h,
'width': w,
'scale': s,
'rotation': r
}
if self.dataset == 'test':
return input, meta
else:
label_parsing = cv2.warpAffine(
parsing_anno,
trans, (int(self.crop_size[1]), int(self.crop_size[0])),
flags=cv2.INTER_NEAREST,
borderMode=cv2.BORDER_CONSTANT,
borderValue=(255))
grid_x = int(self.crop_size[1] / self.pose_net_stride)
grid_y = int(self.crop_size[0] / self.pose_net_stride)
for i in range(joints_all_info.shape[0]):
if visibility[i] > 0:
joints_loc[i, 0:2] = self.affine_trans(
joints_loc[i, 0:2], trans)
label_pose = generate_pose(joints_loc, visibility, trans, grid_x,
grid_y, self.pose_net_stride,
self.sigma)
label_edge = generate_edge(label_parsing)
return input, label_parsing, label_pose, label_edge, meta