def __init__(self, num_split):
lmdb_file = "/srv/share/vgoswami8/conceptual_captions/training_feat_all.lmdb"
caption_path = "/srv/share/vgoswami8/conceptual_captions/caption_train.json"
print("Loading from %s" % lmdb_file)
ds = td.LMDBSerializer.load(lmdb_file, shuffle=False)
self.num_dataset = int(len(ds) / num_split) + 1
ds = td.PrefetchDataZMQ(ds, nr_proc=1)
ds = td.FixedSizeData(ds, self.num_dataset, keep_state=True)
self.ds = ds
self.ds.reset_state()
def get_dataflow(files, params):
"""
Build a tensorflow Dataset from appropriate tfrecords files.
:param files: list a file paths corresponding to appropriate tfrecords data
:param params: parsed arguments
:param is_training: bool, true for training.
:return: (nextdata, num_samples).
nextdata: list of tensorflow ops that produce the next input with the following elements:
true_states, global_map, init_particles, observations, odometries, is_first_step.
See House3DTrajData.get_data for definitions.
"""
mapmode = params.mapmode
obsmode = params.obsmode
batchsize = params.batchsize
trajlen = params.trajlen
num_particles = params.num_particles
# build initial covariance matrix of particles, in pixels and radians
particle_std = params.init_particles_std.copy()
particle_std[0] = particle_std[0] / params.map_pixel_in_meters # convert meters to pixels
particle_std2 = np.square(particle_std) # variance
init_particles_cov = np.diag(particle_std2[(0, 0, 1),])
df = House3DFilterData(
files, mapmode, obsmode, trajlen, num_particles,
params.init_particles_distr, init_particles_cov,
seed=params.seed
)
df = dataflow.FixedSizeData(df, size=df.size(), keep_state=False)
df = BatchDataWithPad(df, batchsize, padded_indices=(2, 3))
num_samples = df.size()
df.reset_state()
# # test dataflow
# df = dataflow.TestDataSpeed(dataflow.PrintData(df), 100)
# df.start()
types = [tf.float32, tf.float32, tf.float32, tf.float32, tf.float32, tf.float32, tf.float32, tf.float32, tf.bool]
sizes = [(batchsize, trajlen, 3), # True states
(batchsize, num_particles, 3), # Initial particles
(batchsize, None, None, 2), # Global map: wall, door
(batchsize, None, None, 3), # Special maps: empty space map, wall margin map, room type map
(batchsize, trajlen, 56, 56, 1), # Depth images, 1 channel
(batchsize, trajlen, 3), # Odometry
(batchsize, trajlen, num_directions), # Rotation angles
(batchsize, trajlen, num_directions, 56, 2), # Points on each wall filter for each direction
(batchsize,), ] # is_first_step,
# turn it into a tf dataset
def tuplegen():
for dp in df.get_data():
yield tuple(dp)
dataset = tf.data.Dataset.from_generator(tuplegen, tuple(types), tuple(sizes))
iterator = dataset.make_one_shot_iterator()
nextdata = iterator.get_next()
return nextdata, num_samples
def get_dataflow(files, params, is_training):
"""
Build a tensorflow Dataset from appropriate tfrecords files.
:param files: list a file paths corresponding to appropriate tfrecords data
:param params: parsed arguments
:param is_training: bool, true for training.
:return: (nextdata, num_samples).
nextdata: list of tensorflow ops that produce the next input with the following elements:
true_states, global_map, init_particles, observations, odometries, is_first_step.
See House3DTrajData.get_data for definitions.
num_samples: number of samples that make an epoch
"""
mapmode = params.mapmode
obsmode = params.obsmode
batchsize = params.batchsize
num_particles = params.num_particles
trajlen = params.trajlen
bptt_steps = params.bptt_steps
# build initial covariance matrix of particles, in pixels and radians
particle_std = params.init_particles_std.copy()
particle_std[0] = particle_std[
0] / params.map_pixel_in_meters # convert meters to pixels
particle_std2 = np.square(particle_std) # element-wise variance
init_particles_cov = np.diag(particle_std2[(0, 0,
1), ]) # index is (0,0,1)
df = House3DTrajData(
files,
mapmode,
obsmode,
trajlen,
num_particles,
params.init_particles_distr,
init_particles_cov,
seed=(params.seed if params.seed is not None and params.seed > 0 else
(params.validseed if not is_training else None)))
# data: true_states, global_map, init_particles, observation, odometry
# make it a multiple of batchsize
df = dataflow.FixedSizeData(df,
size=(df.size() // batchsize) * batchsize,
keep_state=False)
# shuffle
if is_training:
df = dataflow.LocallyShuffleData(
df, 100 * batchsize) # buffer_size = 100 * batchsize
# repeat data for the number of epochs
df = dataflow.RepeatedData(df, params.epochs)
# batch
df = BatchDataWithPad(df, batchsize, padded_indices=(1, ))
# break trajectory into multiple segments for BPTT training. Augment df with is_first_step indicator
df = BreakForBPTT(df,
timed_indices=(0, 3, 4),
trajlen=trajlen,
bptt_steps=bptt_steps)
# data: true_states, global_map, init_particles, observation, odometry, is_first_step
num_samples = df.size() // params.epochs
df.reset_state()
# # test dataflow
# df = dataflow.TestDataSpeed(dataflow.PrintData(df), 100)
# df.start()
obs_ch = {'rgb': 3, 'depth': 1, 'rgb-depth': 4}
map_ch = {
'wall': 1,
'wall-door': 2,
'wall-roomtype': 10,
'wall-door-roomtype': 11
} # every semantic is a channel
types = [
tf.float32, tf.float32, tf.float32, tf.float32, tf.float32, tf.bool
]
sizes = [
(batchsize, bptt_steps, 3),
(batchsize, None, None, map_ch[mapmode]),
(batchsize, num_particles, 3),
(batchsize, bptt_steps, 56, 56, obs_ch[obsmode]),
(batchsize, bptt_steps, 3),
(),
]
# turn it into a tf dataset
def tuplegen():
for dp in df.get_data():
yield tuple(dp)
dataset = tf.data.Dataset.from_generator(tuplegen, tuple(types),
tuple(sizes))
iterator = dataset.make_one_shot_iterator() # only read once
nextdata = iterator.get_next()
return nextdata, num_samples