Cleanup

natanielruiz

2017-08-12 fdf1fedb0d3b4beb672464a438c22b94b9cb7d0f

 code/datasets.py

@@ -7,6 +7,10 @@

import utils

def stack_grayscale_tensor(tensor):
    tensor = torch.cat([tensor, tensor, tensor], 0)
    return tensor

class Pose_300W_LP(Dataset):
    def __init__(self, data_dir, filename_path, transform, img_ext='.jpg', annot_ext='.mat'):
        self.data_dir = data_dir
@@ -66,7 +70,7 @@
        return self.length

class Pose_300W_LP_binned(Dataset):
    def __init__(self, data_dir, filename_path, transform, img_ext='.jpg', annot_ext='.mat'):
    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
@@ -76,12 +80,14 @@

        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('RGB')
        img = img.convert(self.image_mode)
        mat_path = os.path.join(self.data_dir, self.y_train[index] + self.annot_ext)
        shape_path = os.path.join(self.data_dir, self.y_train[index] + '_shape.npy')

        # Crop the face
        pt2d = utils.get_pt2d_from_mat(mat_path)
@@ -105,7 +111,12 @@
        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)
        binned_pose = np.digitize([yaw, pitch, roll], bins) - 1

        # Get shape
        shape = np.load(shape_path)

        labels = torch.LongTensor(np.concatenate((binned_pose, shape), axis = 0))

        if self.transform is not None:
            img = self.transform(img)
@@ -117,7 +128,7 @@
        return self.length

class AFLW2000_binned(Dataset):
    def __init__(self, data_dir, filename_path, transform, img_ext='.jpg', annot_ext='.mat'):
    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
@@ -127,11 +138,12 @@

        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('RGB')
        img = img.convert(self.image_mode)
        mat_path = os.path.join(self.data_dir, self.y_train[index] + self.annot_ext)

        # Crop the face
@@ -167,6 +179,46 @@
        # 2,000
        return self.length

class AFLW(Dataset):
    def __init__(self, data_dir, filename_path, transform, img_ext='.jpg', annot_ext='.txt', 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)
        txt_path = os.path.join(self.data_dir, self.y_train[index] + self.annot_ext)

        # We get the pose in radians
        annot = open(txt_path, 'r')
        line = annot.readline().split(' ')
        pose = [float(line[1]), float(line[2]), float(line[3])]
        # And convert to degrees.
        yaw = pose[0] * 180 / np.pi
        pitch = 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)

        if self.transform is not None:
            img = self.transform(img)

        return img, labels, self.X_train[index]

    def __len__(self):
        # Check how many
        return self.length

def get_list_from_filenames(file_path):
    # input:    relative path to .txt file with file names
    # output:   list of relative path names