def __getitem__(self, index):
if index < 10 and self.split == 'train':
self.idxs = np.random.choice(self.num_samples,
self.num_samples,
replace=False)
img = self._load_image(index)
gt_3d, pts, c, s = self._get_part_info(index)
r = 0
s = np.array([s, s])
s = adjust_aspect_ratio(s, self.aspect_ratio, self.opt.fit_short_side)
trans_input = get_affine_transform(
c, s, r, [self.opt.input_h, self.opt.input_w])
inp = cv2.warpAffine(img,
trans_input, (self.opt.input_h, self.opt.input_w),
flags=cv2.INTER_LINEAR)
inp = (inp.astype(np.float32) / 256. - self.mean) / self.std
inp = inp.transpose(2, 0, 1)
trans_output = get_affine_transform(
c, s, r, [self.opt.output_h, self.opt.output_w])
out = np.zeros((self.num_joints, self.opt.output_h, self.opt.output_w),
dtype=np.float32)
reg_target = np.zeros((self.num_joints, 1), dtype=np.float32)
reg_ind = np.zeros((self.num_joints), dtype=np.int64)
reg_mask = np.zeros((self.num_joints), dtype=np.uint8)
pts_crop = np.zeros((self.num_joints, 2), dtype=np.int32)
for i in range(self.num_joints):
pt = affine_transform(pts[i, :2], trans_output).astype(np.int32)
if pt[0] >= 0 and pt[1] >=0 and pt[0] < self.opt.output_w \
and pt[1] < self.opt.output_h:
pts_crop[i] = pt
out[i] = draw_gaussian(out[i], pt, self.opt.hm_gauss)
reg_target[i] = pts[i, 2] / s[0] # assert not fit_short
reg_ind[i] = pt[1] * self.opt.output_w * self.num_joints + \
pt[0] * self.num_joints + i # note transposed
reg_mask[i] = 1
meta = {
'index': self.idxs[index],
'center': c,
'scale': s,
'gt_3d': gt_3d,
'pts_crop': pts_crop
}
ret = {
'input': inp,
'target': out,
'meta': meta,
'reg_target': reg_target,
'reg_ind': reg_ind,
'reg_mask': reg_mask
}
return ret
def __getitem__(self, index):
img = self._load_image(index)
_, pts, c, s = self._get_part_info(index)
r = 0
if self.split == 'train':
sf = self.opt.scale
rf = self.opt.rotate
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 np.random.random() <= 0.6 else 0
s = min(s, max(img.shape[0], img.shape[1])) * 1.0
s = np.array([s, s])
s = adjust_aspect_ratio(s, self.aspect_ratio, self.opt.fit_short_side)
flipped = (
self.split == 'train' and np.random.random() < self.opt.flip)
if flipped:
img = img[:, ::-1, :]
c[0] = img.shape[1] - 1 - c[0]
pts[:, 0] = img.shape[1] - 1 - pts[:, 0]
for e in self.shuffle_ref:
pts[e[0]], pts[e[1]] = pts[e[1]].copy(), pts[e[0]].copy()
trans_input = get_affine_transform(
c, s, r, [self.opt.input_h, self.opt.input_w])
inp = cv2.warpAffine(
img,
trans_input,
(self.opt.input_h,
self.opt.input_w),
flags=cv2.INTER_LINEAR)
inp = (inp.astype(np.float32) / 256. - self.mean) / self.std
inp = inp.transpose(2, 0, 1)
trans_output = get_affine_transform(
c, s, r, [self.opt.output_h, self.opt.output_w])
out = np.zeros((self.num_joints, self.opt.output_h, self.opt.output_w),
dtype=np.float32)
pts_crop = np.zeros((self.num_joints, 2), dtype=np.int32)
for i in range(self.num_joints):
if pts[i, 0] > 0 or pts[i, 1] > 0:
pts_crop[i] = affine_transform(pts[i], trans_output)
out[i] = draw_gaussian(out[i], pts_crop[i], self.opt.hm_gauss)
meta = {'index': index, 'center': c, 'scale': s,
'pts_crop': pts_crop}
return {'input': inp, 'target': out, 'meta': meta}
def __getitem__(self, index):
if index == 0 and self.split == 'train':
self.idxs = np.random.choice(self.num_samples,
self.num_samples,
replace=False)
img = self._load_image(index)
gt_3d, pts, c, s = self._get_part_info(index)
r = 0
if self.split == 'train':
sf = self.opt.scale
s = s * np.clip(np.random.randn() * sf + 1, 1 - sf, 1 + sf)
# rf = self.opt.rotate
# r = np.clip(np.random.randn()*rf, -rf*2, rf*2) \
# if np.random.random() <= 0.6 else 0
flipped = (self.split == 'train'
and np.random.random() < self.opt.flip)
if flipped:
img = img[:, ::-1, :]
c[0] = img.shape[1] - 1 - c[0]
gt_3d[:, 0] *= -1
pts[:, 0] = img.shape[1] - 1 - pts[:, 0]
for e in self.shuffle_ref_3d:
gt_3d[e[0]], gt_3d[e[1]] = gt_3d[e[1]].copy(), gt_3d[
e[0]].copy()
for e in self.shuffle_ref:
pts[e[0]], pts[e[1]] = pts[e[1]].copy(), pts[e[0]].copy()
s = min(s, max(img.shape[0], img.shape[1])) * 1.0
s = np.array([s, s])
s = adjust_aspect_ratio(s, self.aspect_ratio, self.opt.fit_short_side)
trans_input = get_affine_transform(
c, s, r, [self.opt.input_w, self.opt.input_h])
inp = cv2.warpAffine(img,
trans_input, (self.opt.input_w, self.opt.input_h),
flags=cv2.INTER_LINEAR)
inp = (inp.astype(np.float32) / 256. - self.mean) / self.std
inp = inp.transpose(2, 0, 1)
trans_output = get_affine_transform(
c, s, r, [self.opt.output_w, self.opt.output_h])
out = np.zeros((self.num_joints, self.opt.output_h, self.opt.output_w),
dtype=np.float32)
reg_target = np.zeros((self.num_joints, 1), dtype=np.float32)
reg_ind = np.zeros((self.num_joints), dtype=np.int64)
reg_mask = np.zeros((self.num_joints), dtype=np.uint8)
pts_crop = np.zeros((self.num_joints, 2), dtype=np.int32)
for i in range(self.num_joints):
pt = affine_transform(pts[i, :2], trans_output).astype(np.int32)
if pt[0] >= 0 and pt[1] >=0 and pt[0] < self.opt.output_w \
and pt[1] < self.opt.output_h:
pts_crop[i] = pt
out[i] = draw_gaussian(out[i], pt, self.opt.hm_gauss)
reg_target[i] = pts[i, 2] / s[
0] # assert not self.opt.fit_short_side
reg_ind[i] = pt[1] * self.opt.output_w * self.num_joints + \
pt[0] * self.num_joints + i # note transposed
reg_mask[i] = 1
meta = {
'index': self.idxs[index],
'center': c,
'scale': s,
'gt_3d': gt_3d,
'pts_crop': pts_crop
}
return {
'input': inp,
'target': out,
'meta': meta,
'reg_target': reg_target,
'reg_ind': reg_ind,
'reg_mask': reg_mask
}