def __getitem__(self, index):
# data basename
base_name, _ = self.data_list[index].split('.')
# read image file
img = Image.open(
os.path.join(self.data_dir, "bg_imgs/" + base_name + ".jpg"))
img = img.convert(self.image_mode)
# get face bounding box
pt2d = get_label_from_txt(
os.path.join(self.data_dir, "bbox/" + base_name + ".txt"))
x_min, y_min, x_max, y_max = pt2d
# crop face loosely:k=0to 0.2
k = np.random.random_sample() * 0.1
x_min -= 0.6 * k * abs(x_max - x_min)
y_min -= k * abs(y_max - y_min)
x_max += 0.6 * 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)))
# Augmentation:Blur?
if np.random.random_sample() < 0.05:
img = img.filter(ImageFilter.BLUR)
# Augmentation:Gray?
if np.random.random_sample() < 0.5 and base_name.find('ID') < 0:
img = img.convert('L').convert("RGB")
# transform
if self.transform:
img = self.transform(img)
# RGB2BGR
img = img[np.array([2, 1, 0]), :, :]
# get pose quat
quat = get_label_from_txt(
os.path.join(self.data_dir, "info/" + base_name + '.txt'))
# face orientation vector
vector_label = get_attention_vector(quat)
vector_label = torch.FloatTensor(vector_label)
# classification label
classify_label = torch.LongTensor(np.digitize(vector_label, self.bins))
classify_label = np.where(classify_label > self.num_classes,
self.num_classes, classify_label)
classify_label = np.where(classify_label < 1, 1, classify_label)
# soft label
soft_label_x = get_soft_label(classify_label[0], self.num_classes)
soft_label_y = get_soft_label(classify_label[1], self.num_classes)
soft_label_z = get_soft_label(classify_label[2], self.num_classes)
soft_label = torch.stack([soft_label_x, soft_label_y, soft_label_z])
return img, soft_label, vector_label, os.path.join(
self.data_dir, "bg_imgs/" + base_name + ".jpg")
def __getitem__(self, index):
base_name = self.data_list[index][:-4]
img = Image.open(
os.path.join(self.data_dir, 'bg_imgs/' + base_name + '.jpg'))
img = img.convert(self.image_mode)
# get face bbox
bbox_path = os.path.join(self.data_dir, 'bbox/' + base_name + '.txt')
pt2d = get_label_from_txt(bbox_path)
x_min = pt2d[0]
y_min = pt2d[1]
x_max = pt2d[2]
y_max = pt2d[3]
# Crop the face loosely
k = 0.1
x_min -= k * abs(x_max - x_min)
y_min -= k * abs(y_max - y_min)
x_max += k * abs(x_max - x_min)
y_max += 0.3 * k * abs(y_max - y_min)
img = img.crop((int(x_min), int(y_min), int(x_max), int(y_max)))
# get pose angle pitch,yaw,roll(degrees)
angle_path = os.path.join(self.data_dir,
'angles/' + base_name + '.txt')
angle = get_label_from_txt(angle_path)
angle = torch.FloatTensor(angle)
# get pose quat
quat_path = os.path.join(self.data_dir, 'info/' + base_name + '.txt')
quat = get_label_from_txt(quat_path)
# Attention vector
attention_vector = get_attention_vector(quat)
vector_label = torch.FloatTensor(attention_vector)
# classification label
bins = np.array(range(-99, 100, self.bin_size)) / 99
classify_label = torch.LongTensor(np.digitize(attention_vector,
bins)) # 1-num_classes
classify_label = np.where(classify_label > self.num_classes,
self.num_classes, classify_label)
classify_label = np.where(classify_label < 1, 1, classify_label)
# soft label
soft_label_x = get_soft_label(classify_label[0], self.num_classes)
soft_label_y = get_soft_label(classify_label[1], self.num_classes)
soft_label_z = get_soft_label(classify_label[2], self.num_classes)
soft_label = torch.stack([soft_label_x, soft_label_y, soft_label_z])
if self.transform is not None:
img = self.transform(img)
# RGB2BGR
img = img[np.array([2, 1, 0]), :, :]
return img, soft_label, vector_label, angle, torch.FloatTensor(
pt2d), os.path.join(self.data_dir, 'bg_imgs/' + base_name + '.jpg')
def __getitem__(self, index, crop=False):
# data basename
base_name, _ = self.data_list[index].split('.')
# read image file
img = Image.open(
os.path.join(self.data_dir,
"dataset/bg_imgs/" + base_name + ".jpg"))
img = img.convert(self.image_mode)
if crop:
# get face bounding box
pt2d = get_label_from_txt(
os.path.join(self.data_dir, "bbox/" + base_name + ".txt"))
x_min, y_min, x_max, y_max = pt2d
# crop face loosely:k=0to 0.2
k = np.random.random_sample() * 0.1
x_min -= 0.6 * k * abs(x_max - x_min)
y_min -= k * abs(y_max - y_min)
x_max += 0.6 * 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)))
# Augmentation:Blur?
if np.random.random_sample() < 0.05:
img = img.filter(ImageFilter.BLUR)
# Augmentation:Gray?
if np.random.random_sample() < 0.5 and base_name.find('ID') < 0:
img = img.convert('L').convert("RGB")
# transform
if self.transform:
img = self.transform(img)
# RGB2BGR
img = img[np.array([2, 1, 0]), :, :]
# get pose quat
#quat = get_label_from_txt(os.path.join(self.data_dir, "info/" + base_name + '.txt'))
info = get_info_from_txt(
os.path.join(self.data_dir, "info_all/" + base_name + '.txt'))
# face orientation vector
#vector_label = get_attention_vector(quat)
#get one front vector
#vector_label = angle2vector(os.path.join(self.data_dir, "info/" + base_name + '.txt'))
#vector_label = torch.FloatTensor(vector_label)
#get front vector and right vector
front_vector, right_vector, up_vector = get_vectors(info)
#print(np.dot(np.array(front_vector),np.array(right_vector)))
#print(np.dot(np.array(front_vector),np.array(up_vector)))
#print(np.dot(np.array(right_vector),np.array(up_vector)))
vector_label_f = torch.FloatTensor(front_vector)
vector_label_r = torch.FloatTensor(right_vector)
vector_label_u = torch.FloatTensor(up_vector)
#----------------front vector-------------------------
# classification label
classify_label = torch.LongTensor(np.digitize(
front_vector, self.bins)) # return the index
classify_label = np.where(classify_label > self.num_classes,
self.num_classes, classify_label)
classify_label = np.where(classify_label < 1, 1, classify_label)
# soft label
soft_label_x = get_soft_label(classify_label[0], self.num_classes)
soft_label_y = get_soft_label(classify_label[1], self.num_classes)
soft_label_z = get_soft_label(classify_label[2], self.num_classes)
soft_label_f = torch.stack([soft_label_x, soft_label_y, soft_label_z])
#-------------------right vector--------------
classify_label = torch.LongTensor(np.digitize(
right_vector, self.bins)) # return the index
classify_label = np.where(classify_label > self.num_classes,
self.num_classes, classify_label)
classify_label = np.where(classify_label < 1, 1, classify_label)
# soft label
soft_label_x = get_soft_label(classify_label[0], self.num_classes)
soft_label_y = get_soft_label(classify_label[1], self.num_classes)
soft_label_z = get_soft_label(classify_label[2], self.num_classes)
soft_label_r = torch.stack([soft_label_x, soft_label_y, soft_label_z])
#------------------up vector-------------------
classify_label = torch.LongTensor(np.digitize(
up_vector, self.bins)) # return the index
classify_label = np.where(classify_label > self.num_classes,
self.num_classes, classify_label)
classify_label = np.where(classify_label < 1, 1, classify_label)
# soft label
soft_label_x = get_soft_label(classify_label[0], self.num_classes)
soft_label_y = get_soft_label(classify_label[1], self.num_classes)
soft_label_z = get_soft_label(classify_label[2], self.num_classes)
soft_label_u = torch.stack([soft_label_x, soft_label_y, soft_label_z])
return img, soft_label_f, soft_label_r, soft_label_u, vector_label_f, vector_label_r, vector_label_u, os.path.join(
self.data_dir, "dataset/bg_imgs/" + base_name + ".jpg")
def __getitem__(self, index, crop=False):
base_name, _ = self.data_list[index].split('.')
img = Image.open(
os.path.join(self.data_dir,
'dataset/bg_imgs/' + base_name + '.jpg'))
img = img.convert(self.image_mode)
if crop:
# get face bbox
bbox_path = os.path.join(self.data_dir,
'bbox/' + base_name + '.txt')
pt2d = get_label_from_txt(bbox_path)
x_min = pt2d[0]
y_min = pt2d[1]
x_max = pt2d[2]
y_max = pt2d[3]
# Crop the face loosely
k = 0.1
x_min -= k * abs(x_max - x_min)
y_min -= k * abs(y_max - y_min)
x_max += k * abs(x_max - x_min)
y_max += 0.3 * k * abs(y_max - y_min)
img = img.crop((int(x_min), int(y_min), int(x_max), int(y_max)))
# get pose angle pitch,yaw,roll(degrees) ANGLES NO NEEDED!!!
#angle_path = os.path.join(self.data_dir, 'angles/' + base_name + '.txt')
#angle = get_label_from_txt(angle_path)
#angle = torch.FloatTensor(angle)
if self.transform is not None:
img = self.transform(img)
# RGB2BGR
img = img[np.array([2, 1, 0]), :, :]
# get pose quat
#quat = get_label_from_txt(os.path.join(self.data_dir, "info/" + base_name + '.txt'))
info = get_info_from_txt(
os.path.join(self.data_dir, "info_all/" + base_name + '.txt'))
# face orientation vector
#vector_label = get_attention_vector(quat)
#get one front vector
#vector_label = angle2vector(os.path.join(self.data_dir, "info/" + base_name + '.txt'))
#vector_label = torch.FloatTensor(vector_label)
#get front vector and right vector
front_vector, right_vector, up_vector = get_vectors(info)
#print(np.dot(np.array(front_vector),np.array(right_vector)))
#print(np.dot(np.array(front_vector),np.array(up_vector)))
#print(np.dot(np.array(right_vector),np.array(up_vector)))
vector_label_f = torch.FloatTensor(front_vector)
vector_label_r = torch.FloatTensor(right_vector)
vector_label_u = torch.FloatTensor(up_vector)
bins = np.array(range(-99, 100, self.bin_size)) / 99
#----------------front vector-------------------------
# classification label
classify_label = torch.LongTensor(np.digitize(
front_vector, bins)) # return the index
classify_label = np.where(classify_label > self.num_classes,
self.num_classes, classify_label)
classify_label = np.where(classify_label < 1, 1, classify_label)
# soft label
soft_label_x = get_soft_label(classify_label[0], self.num_classes)
soft_label_y = get_soft_label(classify_label[1], self.num_classes)
soft_label_z = get_soft_label(classify_label[2], self.num_classes)
soft_label_f = torch.stack([soft_label_x, soft_label_y, soft_label_z])
#-------------------right vector--------------
classify_label = torch.LongTensor(np.digitize(
right_vector, bins)) # return the index
classify_label = np.where(classify_label > self.num_classes,
self.num_classes, classify_label)
classify_label = np.where(classify_label < 1, 1, classify_label)
# soft label
soft_label_x = get_soft_label(classify_label[0], self.num_classes)
soft_label_y = get_soft_label(classify_label[1], self.num_classes)
soft_label_z = get_soft_label(classify_label[2], self.num_classes)
soft_label_r = torch.stack([soft_label_x, soft_label_y, soft_label_z])
#------------------up vector-------------------
classify_label = torch.LongTensor(np.digitize(
up_vector, bins)) # return the index
classify_label = np.where(classify_label > self.num_classes,
self.num_classes, classify_label)
classify_label = np.where(classify_label < 1, 1, classify_label)
# soft label
soft_label_x = get_soft_label(classify_label[0], self.num_classes)
soft_label_y = get_soft_label(classify_label[1], self.num_classes)
soft_label_z = get_soft_label(classify_label[2], self.num_classes)
soft_label_u = torch.stack([soft_label_x, soft_label_y, soft_label_z])
return img, soft_label_f, soft_label_r, soft_label_u, vector_label_f, vector_label_r, vector_label_u, os.path.join(
self.data_dir, "dataset/bg_imgs/" + base_name + ".jpg")