| | |
|---|
| | | |
|---|
| | | # Crop the face |
|---|
| | | pt2d = utils.get_pt2d_from_mat(mat_path) |
|---|
| | | |
|---|
| | | x_min = min(pt2d[0,:]) |
|---|
| | | y_min = min(pt2d[1,:]) |
|---|
| | | x_max = max(pt2d[0,:]) |
|---|
| | | y_max = max(pt2d[1,:]) |
|---|
| | | |
|---|
| | | k = 0.15 |
|---|
| | | x_min -= 0.6 * k * abs(x_max - x_min) |
|---|
| | | k = 0.20 |
|---|
| | | x_min -= 2 * k * abs(x_max - x_min) |
|---|
| | | y_min -= 2 * k * abs(y_max - y_min) |
|---|
| | | x_max += 0.6 * k * abs(x_max - x_min) |
|---|
| | | x_max += 2 * k * abs(x_max - x_min) |
|---|
| | | y_max += 0.6 * k * abs(y_max - y_min) |
|---|
| | | img = img.crop((int(x_min), int(y_min), int(x_max), int(y_max))) |
|---|
| | | |
|---|
| | |
|---|
| | | # 2,000 |
|---|
| | | return self.length |
|---|
| | | |
|---|
| | | class AFLW2000_ds(Dataset): |
|---|
| | | def __init__(self, data_dir, filename_path, transform, img_ext='.jpg', annot_ext='.mat', image_mode='RGB'): |
|---|
| | | self.data_dir = data_dir |
|---|
| | | self.transform = transform |
|---|
| | | self.img_ext = img_ext |
|---|
| | | self.annot_ext = annot_ext |
|---|
| | | |
|---|
| | | filename_list = get_list_from_filenames(filename_path) |
|---|
| | | |
|---|
| | | self.X_train = filename_list |
|---|
| | | self.y_train = filename_list |
|---|
| | | self.image_mode = image_mode |
|---|
| | | self.length = len(filename_list) |
|---|
| | | |
|---|
| | | def __getitem__(self, index): |
|---|
| | | img = Image.open(os.path.join(self.data_dir, self.X_train[index] + self.img_ext)) |
|---|
| | | img = img.convert(self.image_mode) |
|---|
| | | mat_path = os.path.join(self.data_dir, self.y_train[index] + self.annot_ext) |
|---|
| | | |
|---|
| | | # Crop the face |
|---|
| | | pt2d = utils.get_pt2d_from_mat(mat_path) |
|---|
| | | x_min = min(pt2d[0,:]) |
|---|
| | | y_min = min(pt2d[1,:]) |
|---|
| | | x_max = max(pt2d[0,:]) |
|---|
| | | y_max = max(pt2d[1,:]) |
|---|
| | | |
|---|
| | | k = 0.20 |
|---|
| | | x_min -= 2 * k * abs(x_max - x_min) |
|---|
| | | y_min -= 2 * k * abs(y_max - y_min) |
|---|
| | | x_max += 2 * k * abs(x_max - x_min) |
|---|
| | | y_max += 0.6 * k * abs(y_max - y_min) |
|---|
| | | img = img.crop((int(x_min), int(y_min), int(x_max), int(y_max))) |
|---|
| | | |
|---|
| | | ds = 5 |
|---|
| | | original_size = img.size |
|---|
| | | img = img.resize((img.size[0] / ds, img.size[1] / ds), resample=0) |
|---|
| | | img = img.resize((original_size[0], original_size[1]), resample=0) |
|---|
| | | |
|---|
| | | # We get the pose in radians |
|---|
| | | pose = utils.get_ypr_from_mat(mat_path) |
|---|
| | | # And convert to degrees. |
|---|
| | | pitch = pose[0] * 180 / np.pi |
|---|
| | | yaw = pose[1] * 180 / np.pi |
|---|
| | | roll = pose[2] * 180 / np.pi |
|---|
| | | # Bin values |
|---|
| | | bins = np.array(range(-99, 102, 3)) |
|---|
| | | labels = torch.LongTensor(np.digitize([yaw, pitch, roll], bins) - 1) |
|---|
| | | cont_labels = torch.FloatTensor([yaw, pitch, roll]) |
|---|
| | | |
|---|
| | | if self.transform is not None: |
|---|
| | | img = self.transform(img) |
|---|
| | | |
|---|
| | | return img, labels, cont_labels, self.X_train[index] |
|---|
| | | |
|---|
| | | def __len__(self): |
|---|
| | | # 2,000 |
|---|
| | | return self.length |
|---|
| | | |
|---|
| | | class AFLW_aug(Dataset): |
|---|
| | | def __init__(self, data_dir, filename_path, transform, img_ext='.jpg', annot_ext='.txt', image_mode='RGB'): |
|---|
| | | self.data_dir = data_dir |
|---|
