def FeatureMap(self):
return {
'image/source_id':
tf.FixedLenFeature((), tf.string, ''),
'object/image/bbox/xmin':
tf.VarLenFeature(tf.float32),
'object/image/bbox/xmax':
tf.VarLenFeature(tf.float32),
'object/image/bbox/ymin':
tf.VarLenFeature(tf.float32),
'object/image/bbox/ymax':
tf.VarLenFeature(tf.float32),
'object/label':
tf.VarLenFeature(tf.string),
'object/has_3d_info':
tf.VarLenFeature(dtype=tf.int64),
'object/occlusion':
tf.VarLenFeature(dtype=tf.int64),
'object/truncation':
tf.VarLenFeature(dtype=tf.float32),
'object/velo/bbox/xyz':
tf.VarLenFeature(dtype=tf.float32),
'object/velo/bbox/dim_xyz':
tf.VarLenFeature(dtype=tf.float32),
'object/velo/bbox/phi':
tf.VarLenFeature(dtype=tf.float32),
'transform/velo_to_image_plane':
tf.FixedLenFeature(shape=(3, 4), dtype=tf.float32),
}
def FeatureMap(self):
"""Return a dictionary from tf.Example feature names to Features."""
p = self.params
features = {}
features['pose'] = tf.VarLenFeature(dtype=tf.float32)
for camera_name in p.camera_names:
features['image_%s' % camera_name] = tf.VarLenFeature(dtype=tf.string)
features['image_%s_shape' % camera_name] = (
tf.VarLenFeature(dtype=tf.int64))
features['camera_%s_intrinsics' %
camera_name] = tf.VarLenFeature(dtype=tf.float32)
features['camera_%s_extrinsics' %
camera_name] = tf.VarLenFeature(dtype=tf.float32)
features['camera_%s_rolling_shutter_direction' %
camera_name] = tf.FixedLenFeature(
dtype=tf.int64, shape=())
features['image_%s_pose' %
camera_name] = tf.VarLenFeature(dtype=tf.float32)
features['image_%s_velocity' %
camera_name] = tf.VarLenFeature(dtype=tf.float32)
for feat in [
'pose_timestamp', 'shutter', 'camera_trigger_time',
'camera_readout_done_time'
]:
features['image_%s_%s' % (camera_name, feat)] = tf.FixedLenFeature(
dtype=tf.float32, shape=())
return features
def FeatureMap(self):
"""Return a dictionary from tf.Example feature names to Features."""
feature_map = {}
feature_map['pose'] = tf.VarLenFeature(dtype=tf.float32)
feature_map['run_segment'] = tf.FixedLenFeature((), tf.string, '')
feature_map['run_start_offset'] = tf.FixedLenFeature((), tf.int64, 0)
feature_map['time_of_day'] = tf.FixedLenFeature((), tf.string, '')
feature_map['location'] = tf.FixedLenFeature((), tf.string, '')
feature_map['weather'] = tf.FixedLenFeature((), tf.string, '')
return feature_map
def FeatureMap(self):
p = self.params
feature_map = {
'image/format':
tf.FixedLenFeature((), tf.string, default_value='png'),
'image/height':
tf.FixedLenFeature((), tf.int64, default_value=1),
'image/width':
tf.FixedLenFeature((), tf.int64, default_value=1),
'image/source_id':
tf.FixedLenFeature((), tf.string, default_value=''),
# The camera calibration matrices can be used later with width/height
# to perform out of camera frustum point dropping.
'transform/velo_to_image_plane':
tf.FixedLenFeature(shape=(3, 4), dtype=tf.float32),
'transform/velo_to_camera':
tf.FixedLenFeature(shape=(4, 4), dtype=tf.float32),
'transform/camera_to_velo':
tf.FixedLenFeature(shape=(4, 4), dtype=tf.float32),
}
if p.decode_image:
feature_map['image/encoded'] = tf.FixedLenFeature((),
tf.string,
default_value='')
return feature_map
def GetFeatureSpec(self):
return {'audio': tf.FixedLenFeature([48000], tf.float32)}
