def eval(data, batch_size):
bpps = 0.
IoUs = 0.
# generate input data.
for i in range(len(data) // batch_size):
samples = data[i * batch_size:(i + 1) * batch_size]
samples_points = []
for _, f in enumerate(samples):
points = h5py.File(f, 'r')['data'][:].astype('int')
samples_points.append(points)
voxels = points2voxels(samples_points, 64).astype('float32')
x = tf.convert_to_tensor(voxels)
y = analysis_transform(x)
y_tilde, likelihoods = entropy_bottleneck(
y, training=False) # TODO: repalce noise by quantization.
x_tilde = synthesis_transform(y_tilde)
num_points = tf.reduce_sum(
tf.cast(tf.greater(tf.reduce_sum(x, -1), 0), 'float32'))
train_bpp_ae = tf.reduce_sum(
tf.log(likelihoods)) / (-np.log(2) * num_points)
points_nums = tf.cast(tf.reduce_sum(x, axis=(1, 2, 3, 4)), 'int32')
output = select_voxels(x_tilde, points_nums, 1.0)
# output = output.numpy()
_, _, IoU = get_classify_metrics(output, x)
bpps = bpps + train_bpp_ae
IoUs = IoUs + IoU
return bpps / (i + 1), IoUs / (i + 1)
def eval(data, batch_size):
bpps_ae = 0.
bpps_hyper = 0.
IoUs = 0.
for i in range(len(data) // batch_size):
samples = data[i * batch_size:(i + 1) * batch_size]
samples_points = []
for _, f in enumerate(samples):
points = h5py.File(f, 'r')['data'][:].astype('int')
samples_points.append(points)
voxels = points2voxels(samples_points, 64).astype('float32')
x = tf.convert_to_tensor(voxels)
y = analysis_transform(x)
z = hyper_encoder(y)
z_tilde, likelihoods_hyper = entropy_bottleneck(z, training=False)
loc, scale = hyper_decoder(z_tilde)
scale = tf.maximum(scale, lower_bound)
y_tilde, likelihoods = conditional_entropy_model(y,
loc,
scale,
training=False)
x_tilde = synthesis_transform(y_tilde)
num_points = tf.reduce_sum(
tf.cast(tf.greater(tf.reduce_sum(x, -1), 0), 'float32'))
train_bpp_ae = tf.reduce_sum(
tf.log(likelihoods)) / (-np.log(2) * num_points)
train_bpp_hyper = tf.reduce_sum(
tf.log(likelihoods_hyper)) / (-np.log(2) * num_points)
points_nums = tf.cast(tf.reduce_sum(x, axis=(1, 2, 3, 4)), 'int32')
output = select_voxels(x_tilde, points_nums, 1.0)
output = output.numpy()
_, _, IoU = get_classify_metrics(output, x)
bpps_ae = bpps_ae + train_bpp_ae
bpps_hyper = bpps_hyper + train_bpp_hyper
IoUs = IoUs + IoU
return bpps_ae / (i + 1), bpps_hyper / (i + 1), IoUs / (i + 1)
def train():
start = time.time()
train_list = file_list[len(file_list) // RATIO_EVAL:]
train_bpp_ae_sum = 0.
train_IoU_sum = 0.
num = 0.
for step in range(int(global_step), int(NUM_ITEATION + 1)):
# generate input data.
samples = random.sample(train_list, BATCH_SIZE)
samples_points = []
for _, f in enumerate(samples):
points = h5py.File(f, 'r')['data'][:].astype('int')
samples_points.append(points)
voxels = points2voxels(samples_points, 64).astype('float32')
x = tf.convert_to_tensor(voxels)
with tf.GradientTape() as model_tape:
y = analysis_transform(x)
y_tilde, likelihoods = entropy_bottleneck(y, training=True)
x_tilde = synthesis_transform(y_tilde)
# losses.
num_points = tf.reduce_sum(
tf.cast(tf.greater(tf.reduce_sum(x, -1), 0), 'float32'))
train_bpp_ae = tf.reduce_sum(
tf.log(likelihoods)) / -np.log(2) / num_points
train_zeros, train_ones = get_bce_loss(x_tilde, x)
train_distortion = beta * train_zeros + 1.0 * train_ones
train_loss = alpha * train_distortion + 1.0 * train_bpp_ae
# metrics.
_, _, IoU = get_classify_metrics(x_tilde, x)
# gradients.
gradients = model_tape.gradient(
train_loss, analysis_transform.variables +
synthesis_transform.variables + entropy_bottleneck.variables)
# optimization.
main_optimizer.apply_gradients(
zip(
gradients, analysis_transform.variables +
synthesis_transform.variables +
entropy_bottleneck.variables))
# post-process: classification.
points_nums = tf.cast(tf.reduce_sum(x, axis=(1, 2, 3, 4)), 'int32')
output = select_voxels(x_tilde, points_nums, 1.0)
# output = output.numpy()
train_bpp_ae_sum += train_bpp_ae
_, _, IoU = get_classify_metrics(output, x)
train_IoU_sum += IoU
num += 1
# Display.
if (step + 1) % DISPLAY_STEP == 0:
train_bpp_ae_sum /= num
train_IoU_sum /= num
print("Iteration:{0:}".format(step))
print("Bpps: {0:.4f}".format(train_bpp_ae_sum.numpy()))
print("IoU: ", train_IoU_sum.numpy())
print('Running time:(mins):', round((time.time() - start) / 60.))
print()
with writer.as_default(
), tf.contrib.summary.record_summaries_every_n_global_steps(100):
tf.contrib.summary.scalar('bpp', train_bpp_ae_sum)
tf.contrib.summary.scalar('IoU', train_IoU_sum)
num = 0.
train_bpp_ae_sum = 0.
train_bpp_hyper_sum = 0.
train_IoU_sum = 0.
print('evaluating...')
eval_list = random.sample(file_list[:len(file_list) // RATIO_EVAL],
16)
bpp_eval, IoU_eval = eval(eval_list, batch_size=8)
print("BPP:{0:.4f}, IoU:{1:.4f}".format(bpp_eval, IoU_eval))
with eval_writer.as_default(
), tf.contrib.summary.record_summaries_every_n_global_steps(1):
tf.contrib.summary.scalar('bpp', bpp_eval)
tf.contrib.summary.scalar('IoU', IoU_eval)
# Update global steps.
global_step.assign_add(1)
# Save checkpoints.
if (step + 1) % SAVE_STEP == 0:
checkpoint.save(file_prefix=checkpoint_prefix)