def __getitem__(self, idx):
image_path = os.path.join(self.data_root,
self.landmarks_frame.iloc[idx, 0])
scale = self.landmarks_frame.iloc[idx, 1]
center_w = self.landmarks_frame.iloc[idx, 2]
center_h = self.landmarks_frame.iloc[idx, 3]
center = torch.Tensor([center_w, center_h])
pts = self.landmarks_frame.iloc[idx, 4:].values
pts = pts.astype('float').reshape(-1, 2)
scale *= 1.25
nparts = pts.shape[0]
img = np.array(Image.open(image_path).convert('RGB'), dtype=np.float32)
r = 0
if self.is_train:
scale = scale * (random.uniform(1 - self.scale_factor,
1 + self.scale_factor))
r = random.uniform(-self.rot_factor, self.rot_factor) \
if random.random() <= 0.6 else 0
if random.random() <= 0.5 and self.flip:
img = np.fliplr(img)
pts = fliplr_joints(pts, width=img.shape[1], dataset='WFLW')
center[0] = img.shape[1] - center[0]
img = crop(img, center, scale, self.input_size, rot=r)
target = np.zeros((nparts, self.output_size[0], self.output_size[1]))
tpts = pts.copy()
for i in range(nparts):
if tpts[i, 1] > 0:
tpts[i, 0:2] = transform_pixel(tpts[i, 0:2] + 1,
center,
scale,
self.output_size,
rot=r)
target[i] = generate_target(target[i],
tpts[i] - 1,
self.sigma,
label_type=self.label_type)
img = img.astype(np.float32)
img = (img / 255.0 - self.mean) / self.std
img = img.transpose([2, 0, 1])
target = torch.Tensor(target)
tpts = torch.Tensor(tpts)
center = torch.Tensor(center)
meta = {
'index': idx,
'center': center,
'scale': scale,
'pts': torch.Tensor(pts),
'tpts': tpts
}
return img, target, meta
def __getitem__(self, idx):
img = self.images[idx][0]
if len(img.shape) == 2:
img = img.reshape(img.shape[0], img.shape[1], 1)
img = np.repeat(img, 3, axis=2)
pts = self.pts[idx][0:58].reshape(2, -1).transpose()
xmin = np.min(pts[:, 0])
xmax = np.max(pts[:, 0])
ymin = np.min(pts[:, 1])
ymax = np.max(pts[:, 1])
center_w = (math.floor(xmin) + math.ceil(xmax)) / 2.0
center_h = (math.floor(ymin) + math.ceil(ymax)) / 2.0
scale = max(math.ceil(xmax) - math.floor(xmin), math.ceil(ymax) - math.floor(ymin)) / 200.0
center = torch.Tensor([center_w, center_h])
scale *= 1.25
nparts = pts.shape[0]
r = 0
if self.is_train:
scale = scale * (random.uniform(1 - self.scale_factor,
1 + self.scale_factor))
r = random.uniform(-self.rot_factor, self.rot_factor) \
if random.random() <= 0.6 else 0
if random.random() <= 0.5 and self.flip:
img = np.fliplr(img)
pts = fliplr_joints(pts, width=img.shape[1], dataset='COFW')
center[0] = img.shape[1] - center[0]
img = crop(img, center, scale, self.input_size, rot=r)
target = np.zeros((nparts, self.output_size[0], self.output_size[1]))
tpts = pts.copy()
for i in range(nparts):
if tpts[i, 1] > 0:
tpts[i, 0:2] = transform_pixel(tpts[i, 0:2]+1, center,
scale, self.output_size, rot=r)
target[i] = generate_target(target[i], tpts[i]-1, self.sigma,
label_type=self.label_type)
img = img.astype(np.float32)
img = (img/255 - self.mean) / self.std
img = img.transpose([2, 0, 1])
target = torch.Tensor(target)
tpts = torch.Tensor(tpts)
center = torch.Tensor(center)
meta = {'index': idx, 'center': center, 'scale': scale,
'pts': torch.Tensor(pts), 'tpts': tpts}
return img, target, meta
def get_training_image(img_path,
bbox=None,
inp_res=256,
mean=(0.6419, 0.6292, 0.5994),
std=(0.2311, 0.2304, 0.2379)):
img = load_image(img_path)
if bbox is not None:
x0, y0, x1, y1 = bbox[0][0], bbox[0][1], bbox[1][0], bbox[1][1]
c = np.array([(x0 + x1), (y0 + y1)]) / 2 # center
s = np.sqrt((y1 - y0) * (x1 - x0)) / 60.0 # scale
else:
c = np.array([img.shape[2] / 2, img.shape[1] / 2])
s = 5.0 # THIS HAS TO BE FIXED !!!
r = 0 # rotation
inp = crop(img, c, s, [inp_res, inp_res], rot=r)
inp = color_normalize(inp, mean, std)
meta = {'center': c, 'scale': s}
return inp, meta
def __getitem__(self, idx):
if self.landmarks_frame.iloc[idx, 0].find('/ibug/image_092_01.jpg'):
self.landmarks_frame.iloc[idx, 0] = self.landmarks_frame.iloc[
idx, 0].replace('image_092_01.jpg', 'image_092 _01.jpg')
image_path = os.path.join(self.data_root,
self.landmarks_frame.iloc[idx, 0])
scale = self.landmarks_frame.iloc[idx, 1]
center_w = self.landmarks_frame.iloc[idx, 2]
center_h = self.landmarks_frame.iloc[idx, 3]
center = torch.Tensor([center_w, center_h])
pts = self.landmarks_frame.iloc[idx, 4:].values
pts = pts.astype('float').reshape(-1, 2)
scale *= 1.25
nparts = pts.shape[0]
img = np.array(Image.open(image_path).convert('RGB'), dtype=np.float32)
r = 0
img = crop(img, center, scale, self.input_size, rot=r)
trans_imgs = []
trans_factors = []
for _ in range(self.n_trans):
x_factor = random.uniform(-self.trans_factor, self.trans_factor)
y_factor = random.uniform(-self.trans_factor, self.trans_factor)
M = np.float32([[1, 0, self.input_size[0] * x_factor],
[0, 1, self.input_size[1] * y_factor]])
trans_img = cv2.warpAffine(img, M, self.input_size)
trans_img = trans_img.astype(np.float32)
trans_img = (trans_img / 255.0 - self.mean) / self.std
trans_img = trans_img.transpose([2, 0, 1])
trans_imgs.append(trans_img)
trans_factors.append([x_factor, y_factor])
img = img.astype(np.float32)
img = (img / 255.0 - self.mean) / self.std
img = img.transpose([2, 0, 1])
targets = []
offsets = []
for output_size in self.output_size:
target = np.zeros((nparts, output_size[0], output_size[1]))
tpts = pts.copy()
for i in range(nparts):
if tpts[i, 1] > 0:
tpts[i, 0:2] = transform_pixel(tpts[i, 0:2],
center,
scale,
output_size,
rot=r)
x, y = tpts[i].astype(int)
if 0 <= y < output_size[0] and 0 <= x < output_size[1]:
target[i, y, x] = 1
xx_channel, yy_channel = self._generate_offset(
nparts, tpts, output_size, self.offset_mode, self.offset_dim)
offset = [torch.Tensor(xx_channel), torch.Tensor(yy_channel)]
targets.append(torch.Tensor(target))
offsets.append(offset)
trans_imgs = torch.Tensor(trans_imgs)
trans_factors = torch.Tensor(trans_factors)
tpts = torch.Tensor(tpts)
center = torch.Tensor(center)
meta = {
'index': idx,
'center': center,
'scale': scale,
'pts': torch.Tensor(pts),
'tpts': tpts
}
return img, trans_imgs, trans_factors, targets, offsets, meta
def __getitem__(self, index):
sf = self.scale_factor
rf = self.rot_factor
if self.is_train:
a = self.anno[self.train_list[index]]
else:
a = self.anno[self.valid_list[index]]
img_path = os.path.join(self.img_folder, a['img_paths'])
pts = torch.Tensor(a['joint_self'])
# pts[:, 0:2] -= 1 # Convert pts to zero based
# c = torch.Tensor(a['objpos']) - 1
c = torch.Tensor(a['objpos'])
s = a['scale_provided']
# Adjust center/scale slightly to avoid cropping limbs
if c[0] != -1:
c[1] = c[1] + 15 * s
s = s * 1.25
# For single-person pose estimation with a centered/scaled figure
nparts = pts.size(0)
img = load_image(img_path) # CxHxW
r = 0
if self.is_train:
s = s * torch.randn(1).mul_(sf).add_(1).clamp(1 - sf, 1 + sf)[0]
r = torch.randn(1).mul_(rf).clamp(
-2 * rf, 2 * rf)[0] if random.random() <= 0.6 else 0
# Flip
if random.random() <= 0.5:
img = fliplr(img)
pts = shufflelr(pts, img.size(2), self.DATA_INFO.hflip_indices)
c[0] = img.size(2) - c[0]
# Color
img[0, :, :].mul_(random.uniform(0.8, 1.2)).clamp_(0, 1)
img[1, :, :].mul_(random.uniform(0.8, 1.2)).clamp_(0, 1)
img[2, :, :].mul_(random.uniform(0.8, 1.2)).clamp_(0, 1)
# Prepare image and groundtruth map
inp = crop(img, c, s, self.inp_res, rot=r)
inp = color_normalize(inp, self.DATA_INFO.rgb_mean,
self.DATA_INFO.rgb_stddev)
# Generate ground truth
tpts = pts.clone()
target = torch.zeros(nparts, *self.out_res)
target_weight = tpts[:, 2].clone().view(nparts, 1)
for i in range(nparts):
# if tpts[i, 2] > 0: # This is evil!!
if tpts[i, 1] > 0:
tpts[i, 0:2] = to_torch(
transform(tpts[i, 0:2] + 1, c, s, self.out_res, rot=r))
target[i], vis = draw_labelmap(target[i],
tpts[i] - 1,
self.sigma,
type=self.label_type)
target_weight[i, 0] *= vis
# Meta info
if not isinstance(s, torch.Tensor):
s = torch.Tensor(s)
meta = {
'index': index,
'center': c,
'scale': s,
'pts': pts,
'tpts': tpts,
'target_weight': target_weight
}
return inp, target, meta
def __getitem__(self, idx):
if self.landmarks_frame.iloc[idx, 0].find('/ibug/image_092_01.jpg'):
self.landmarks_frame.iloc[idx, 0] = self.landmarks_frame.iloc[
idx, 0].replace('image_092_01.jpg', 'image_092 _01.jpg')
image_path = os.path.join(self.data_root,
self.landmarks_frame.iloc[idx, 0])
scale = self.landmarks_frame.iloc[idx, 1]
center_w = self.landmarks_frame.iloc[idx, 2]
center_h = self.landmarks_frame.iloc[idx, 3]
center = torch.Tensor([center_w, center_h])
pts = self.landmarks_frame.iloc[idx, 4:].values
pts = pts.astype('float').reshape(-1, 2)
scale *= 1.3
nparts = pts.shape[0]
img = np.array(Image.open(image_path).convert('RGB'), dtype=np.float32)
r = 0
t_x, t_y = (1, 1)
if self.is_train:
scale = scale * (random.uniform(1 - self.scale_factor,
1 + self.scale_factor))
r = random.uniform(-self.rot_factor, self.rot_factor) \
if random.random() <= 0.6 else 0
t_x = random.uniform(1-self.trans_factor, 1+self.trans_factor) \
if random.random() <= 0.5 else 1
t_y = random.uniform(1-self.trans_factor, 1+self.trans_factor) \
if random.random() <= 0.5 else 1
if random.random() <= 0.5 and self.flip:
img = np.fliplr(img)
pts = fliplr_joints(pts, width=img.shape[1], dataset='300W')
center[0] = img.shape[1] - center[0]
img = crop(img,
center,
scale,
self.input_size,
translation=(t_x, t_y),
rot=r)
if self.is_train:
if random.random() <= 0.3 and self.gaussian_blur:
radius = random.choice([1, 3, 5])
img = cv2.GaussianBlur(img, (radius, radius), sigmaX=1.0)
if random.random() <= 1.0 and self.occlusion:
img = add_occlusion(img, max_size=102)
targets = []
offsets = []
for output_size in self.output_size:
target = np.zeros((nparts, output_size[0], output_size[1]))
tpts = pts.copy()
for i in range(nparts):
if tpts[i, 1] > 0:
tpts[i, 0:2] = transform_pixel(tpts[i, 0:2],
center,
scale,
output_size,
translation=(t_x, t_y),
rot=r)
x, y = tpts[i].astype(int)
if 0 <= y < output_size[0] and 0 <= x < output_size[1]:
target[i, y, x] = 1
xx_channel, yy_channel = self._generate_offset(
nparts, tpts, output_size, self.offset_mode, self.offset_dim)
offset = [torch.Tensor(xx_channel), torch.Tensor(yy_channel)]
targets.append(torch.Tensor(target))
offsets.append(offset)
img = img.astype(np.float32)
img = (img / 255.0 - self.mean) / self.std
img = img.transpose([2, 0, 1])
tpts = torch.Tensor(tpts)
center = torch.Tensor(center)
meta = {
'index': idx,
'center': center,
'scale': scale,
'pts': torch.Tensor(pts),
'tpts': tpts
}
return img, targets, offsets, meta