def inception_module(input,
n_filters=64,
kernel_sizes=[3, 5],
is_training=None,
bn_decay=None,
scope='inception'):
one_by_one = tf_util.conv3d(input,
n_filters, [1, 1, 1],
scope=scope + '_conv1',
stride=[1, 1, 1],
padding='SAME',
bn=True,
bn_decay=bn_decay,
is_training=is_training)
three_by_three = tf_util.conv3d(
one_by_one,
int(n_filters / 2),
[kernel_sizes[0], kernel_sizes[0], kernel_sizes[0]],
scope=scope + '_conv2',
stride=[1, 1, 1],
padding='SAME',
bn=True,
bn_decay=bn_decay,
is_training=is_training)
five_by_five = tf_util.conv3d(
one_by_one,
int(n_filters / 2),
[kernel_sizes[1], kernel_sizes[1], kernel_sizes[1]],
scope=scope + '_conv3',
stride=[1, 1, 1],
padding='SAME',
bn=True,
bn_decay=bn_decay,
is_training=is_training)
average_pooling = tf_util.avg_pool3d(
input, [kernel_sizes[0], kernel_sizes[0], kernel_sizes[0]],
scope=scope + '_avg_pool',
stride=[1, 1, 1],
padding='SAME')
average_pooling = tf_util.conv3d(average_pooling,
n_filters, [1, 1, 1],
scope=scope + '_conv4',
stride=[1, 1, 1],
padding='SAME',
bn=True,
bn_decay=bn_decay,
is_training=is_training)
output = tf.concat(
[one_by_one, three_by_three, five_by_five, average_pooling], axis=4)
#output = output + tf.tile(input) ??? #resnet
return output
def inception_module(input, n_filters=64, kernel_sizes=[3,5], is_training=None, bn_decay=None, scope='inception'):
'''
:param input: [B,K,K,K,FV]
:param n_filters:
:return: output: [B,K,K,K,n_filters*2]
'''
one_by_one = tf_util.conv3d(input, n_filters, [1,1,1], scope= scope + '_conv1',
stride=[1, 1, 1], padding='SAME', bn=True,
bn_decay=bn_decay, is_training=is_training)
three_by_three = tf_util.conv3d(one_by_one, int(n_filters), [kernel_sizes[0], kernel_sizes[0], kernel_sizes[0]], scope= scope + '_conv2',
stride=[1, 1, 1], padding='SAME', bn=True,
bn_decay=bn_decay, is_training=is_training)
five_by_five = tf_util.conv3d(one_by_one, int(n_filters), [kernel_sizes[1], kernel_sizes[1], kernel_sizes[1]], scope=scope + '_conv3',
stride=[1, 1, 1], padding='SAME', bn=True,
bn_decay=bn_decay, is_training=is_training)
average_pooling = tf_util.avg_pool3d(input, [kernel_sizes[0], kernel_sizes[0], kernel_sizes[0]], scope=scope+'_avg_pool', stride=[1, 1, 1], padding='SAME')
average_pooling = tf_util.conv3d(average_pooling, n_filters, [1,1,1], scope= scope + '_conv4',
stride=[1, 1, 1], padding='SAME', bn=True,
bn_decay=bn_decay, is_training=is_training)
output = tf.concat([ one_by_one, three_by_three, five_by_five, average_pooling], axis=4)
return output
def inception_module(input, n_filters=64, kernel_sizes=[3, 5], is_training=None, bn_decay=None, scope='inception'):
"""
3D inception_module
"""
one_by_one = tf_util.conv3d(input, n_filters, [1, 1, 1], scope= scope + '_conv1',
stride=[1, 1, 1], padding='SAME', bn=True,
bn_decay=bn_decay, is_training=is_training)
three_by_three = tf_util.conv3d(one_by_one, int(n_filters/2), [kernel_sizes[0], kernel_sizes[0], kernel_sizes[0]], scope= scope + '_conv2',
stride=[1, 1, 1], padding='SAME', bn=True,
bn_decay=bn_decay, is_training=is_training)
five_by_five = tf_util.conv3d(one_by_one, int(n_filters/2), [kernel_sizes[1], kernel_sizes[1], kernel_sizes[1]], scope=scope + '_conv3',
stride=[1, 1, 1], padding='SAME', bn=True,
bn_decay=bn_decay, is_training=is_training)
average_pooling = tf_util.avg_pool3d(input, [kernel_sizes[0], kernel_sizes[0], kernel_sizes[0]], scope=scope+'_avg_pool', stride=[1, 1, 1], padding='SAME')
average_pooling = tf_util.conv3d(average_pooling, n_filters, [1,1,1], scope= scope + '_conv4',
stride=[1, 1, 1], padding='SAME', bn=True,
bn_decay=bn_decay, is_training=is_training)
output = tf.concat([ one_by_one, three_by_three, five_by_five, average_pooling], axis=4)
#output = output + tf.tile(input) ??? #resnet
return output
if __name__ == '__main__':
with tf.Graph().as_default():
inputs = tf.zeros((32, 1024, 3))
outputs = get_model(inputs, tf.constant(True))
print (outputs)
def pointnet_sa_module(cascade_id,
xyz,
points,
bidmap,
mlp_configs,
block_bottom_center_mm,
configs,
sgf_config_pls,
is_training,
bn_decay,
scope,
bn=True,
tnet_spec=None,
use_xyz=True,
IsShowModel=False):
'''
Input cascade_id==0:
xyz is grouped_points: (batch_size,nsubblock0,npoint_subblock0,6)
points: None
bidmap: None
Input cascade_id==1:
xyz: (batch_size,nsubblock0,3)
points: (batch_size,nsubblock0,channel)
bidmap: (batch_size,nsubblock1,npoint_subblock1)
Medium cascade_id==1:
grouped_xyz: (batch_size,nsubblock1,npoint_subblock1,3)
new_xyz: (batch_size,nsubblock1,3)
group_points: (batch_size,nsubblock1,npoint_subblock1,channel)
output cascade_id==1:
new_xyz: (batch_size,nsubblock1,3)
new_points: (batch_size,nsubblock1,channel)
'''
block_bottom_center_mm = tf.cast(
block_bottom_center_mm, tf.float32, name='block_bottom_center_mm'
) # gpu_0/sa_layer3/block_bottom_center_mm:0
batch_size = xyz.get_shape()[0].value
with tf.variable_scope(scope) as sc:
cascade_num = configs['flatten_bm_extract_idx'].shape[
0] - 1 # include global here (Note: cascade_num does not include global in block_pre_util )
assert configs['sub_block_step_candis'].size == cascade_num - 1
if cascade_id == 0:
indrop_keep_mask = tf.get_default_graph().get_tensor_by_name(
'indrop_keep_mask:0') # indrop_keep_mask:0
assert len(xyz.shape) == 3
if bidmap == None:
grouped_xyz = tf.expand_dims(xyz, 1)
grouped_points = tf.expand_dims(points, 1)
new_xyz = None
valid_mask = None
else:
batch_idx = tf.reshape(tf.range(batch_size), [batch_size, 1, 1, 1])
nsubblock = bidmap.get_shape()[1].value
npoint_subblock = bidmap.get_shape()[2].value
batch_idx_ = tf.tile(batch_idx, [1, nsubblock, npoint_subblock, 1])
bidmap = tf.expand_dims(bidmap, axis=-1, name='bidmap')
bidmap_concat = tf.concat(
[batch_idx_, bidmap], axis=-1,
name='bidmap_concat') # gpu_0/sa_layer0/bidmap_concat:0
# The value for invalid item in bidmap is -17.
# On GPU, the responding grouped_xyz and grouped_points is 0.
# NOT WORK on CPU !!!
# invalid indices comes from merge_blocks_while_fix_bmap
# set point_indices_f for invalid points as
# NETCONFIG['redundant_points_in_block'] ( shoud be set < -500)
valid_mask = tf.greater(bidmap, tf.constant(
-500, tf.int32), 'valid_mask') # gpu_0/sa_layer0/valid_mask:0
grouped_xyz = tf.gather_nd(
xyz, bidmap_concat,
name='grouped_xyz') # gpu_0/sa_layer0/grouped_xyz:0
grouped_points = tf.gather_nd(points,
bidmap_concat,
name='group_points')
if cascade_id == 0 and len(indrop_keep_mask.get_shape()) != 0:
grouped_indrop_keep_mask = tf.gather_nd(
indrop_keep_mask,
bidmap_concat,
name='grouped_indrop_keep_mask'
) # gpu_0/sa_layer0/grouped_indrop_keep_mask:0
# new_xyz is the "voxel center" or "mean position of points in the voxel"
if configs['mean_grouping_position'] and (
not mlp_configs['block_learning'] == '3DCNN'):
new_xyz = tf.reduce_mean(grouped_xyz, -2)
else:
new_xyz = block_bottom_center_mm[:, :, 3:6] * tf.constant(
0.001, tf.float32)
# the mid can be mean or block center, decided by configs['mean_grouping_position']
sub_block_mid = tf.expand_dims(
new_xyz, -2, name='sub_block_mid') # gpu_1/sa_layer0/sub_block_mid
global_block_mid = tf.reduce_mean(sub_block_mid,
1,
keepdims=True,
name='global_block_mid')
grouped_xyz_submid = grouped_xyz - sub_block_mid
grouped_xyz_glomid = grouped_xyz - global_block_mid
grouped_xyz_feed = []
if 'raw' in configs['xyz_elements']:
grouped_xyz_feed.append(grouped_xyz)
if 'sub_mid' in configs['xyz_elements']:
grouped_xyz_feed.append(grouped_xyz_submid)
if 'global_mid' in configs['xyz_elements']:
grouped_xyz_feed.append(grouped_xyz_glomid)
grouped_xyz_feed = tf.concat(grouped_xyz_feed, -1)
if cascade_id == 0:
# xyz must be at the first in feed_data_elements !!!!
grouped_points = tf.concat(
[grouped_xyz_feed, grouped_points[..., 3:]], -1)
if len(indrop_keep_mask.get_shape()) != 0:
if InDropMethod == 'set1st':
# set all the dropped item as the first item
tmp1 = tf.multiply(grouped_points,
grouped_indrop_keep_mask)
points_1st = grouped_points[:, :, 0:1, :]
points_1st = tf.tile(points_1st,
[1, 1, grouped_points.shape[2], 1])
indrop_mask_inverse = 1 - grouped_indrop_keep_mask
tmp2 = indrop_mask_inverse * points_1st
grouped_points = tf.add(
tmp1, tmp2, name='grouped_points_droped'
) # gpu_0/sa_layer0/grouped_points_droped
#tf.add_to_collection( 'check', grouped_points )
elif InDropMethod == 'set0':
valid_mask = tf.logical_and(
valid_mask,
tf.equal(grouped_indrop_keep_mask, 0),
name='valid_mask_droped'
) # gpu_1/sa_layer0/valid_mask_droped
elif use_xyz:
grouped_points = tf.concat([grouped_xyz_feed, grouped_points],
axis=-1)
tf.add_to_collection('grouped_xyz', grouped_xyz)
tf.add_to_collection('grouped_xyz_submid', grouped_xyz_submid)
tf.add_to_collection('grouped_xyz_glomid', grouped_xyz_glomid)
if cascade_id > 0 and use_xyz and (not cascade_id == cascade_num - 1):
grouped_points = tf.concat([grouped_xyz_feed, grouped_points],
axis=-1)
nsample = grouped_points.get_shape()[2].value # the conv kernel size
if IsShowModel:
print(
'\n\npointnet_sa_module cascade_id:%d\n xyz:%s\n grouped_xyz:%s\n new_xyz:%s\n grouped_points:%s\n nsample:%d'
% (cascade_id, shape_str([xyz]), shape_str([grouped_xyz]),
shape_str([new_xyz]), shape_str([grouped_points]), nsample))
new_points = grouped_points
if valid_mask != None:
new_points = new_points * tf.cast(valid_mask[:, :, :, 0:1],
tf.float32)
if 'growth_rate' in mlp_configs['point_encoder'][cascade_id]:
new_points = tf_util.dense_net( new_points, mlp_configs['point_encoder'][cascade_id], bn, is_training, bn_decay,\
scope = 'dense_cascade_%d_point_encoder'%(cascade_id) , is_show_model = IsShowModel )
else:
for i, num_out_channel in enumerate(
mlp_configs['point_encoder'][cascade_id]):
new_points = tf_util.conv2d(new_points,
num_out_channel, [1, 1],
padding='VALID',
stride=[1, 1],
bn=bn,
is_training=is_training,
scope='conv%d' % (i),
bn_decay=bn_decay)
if configs['Cnn_keep_prob'] < 1:
if (not configs['only_last_layer_ineach_cascade']
) or i == len(
mlp_configs['point_encoder'][cascade_id]) - 1:
new_points = tf_util.dropout(
new_points,
keep_prob=configs['Cnn_keep_prob'],
is_training=is_training,
scope='dropout',
name='cnn_dp%d' % (i))
if IsShowModel:
print('point encoder1 %d, new_points:%s' %
(i, shape_str([new_points])))
if cascade_id == 0:
root_point_features = new_points
#if InDropMethod == 'set0':
# if len(indrop_keep_mask.get_shape()) != 0:
# new_points = tf.identity(new_points,'points_before_droped') # gpu_0/sa_layer0/points_before_droped:0
# new_points = tf.multiply( new_points, grouped_indrop_keep_mask, name='droped_points' ) # gpu_0/sa_layer0/droped_points:0
else:
root_point_features = None
pooling = mlp_configs['block_learning']
if pooling == '3DCNN' and (cascade_id == 0):
pooling = 'max'
#if pooling=='avg':
# new_points = tf_util.avg_pool2d(new_points, [1,nsample], stride=[1,1], padding='VALID', scope='avgpool1')
#elif pooling=='weighted_avg':
# with tf.variable_scope('weighted_avg1'):
# dists = tf.norm(grouped_xyz,axis=-1,ord=2,keep_dims=True)
# exp_dists = tf.exp(-dists * 5)
# weights = exp_dists/tf.reduce_sum(exp_dists,axis=2,keep_dims=True) # (batch_size, npoint, nsample, 1)
# new_points *= weights # (batch_size, npoint, nsample, mlps_0[-1])
# new_points = tf.reduce_sum(new_points, axis=2, keep_dims=True)
if pooling == 'max':
# Even the grouped_points and grouped_xyz are 0 for invalid points, the
# vaule after mlp will not be. It has to be set as 0 forcely before
# pooling.
if valid_mask != None:
new_points = new_points * tf.cast(valid_mask[:, :, :, 0:1],
tf.float32)
new_points = tf.identity(
new_points,
'points_before_max') # gpu_0/sa_layer0/points_before_max
new_points = tf.reduce_max(new_points,
axis=[2],
keepdims=True,
name='points_after_max')
#elif pooling=='min':
# new_points = tf_util.max_pool2d(-1*new_points, [1,nsample], stride=[1,1], padding='VALID', scope='minpool1')
#elif pooling=='max_and_avg':
# avg_points = tf_util.max_pool2d(new_points, [1,nsample], stride=[1,1], padding='VALID', scope='maxpool1')
# max_points = tf_util.avg_pool2d(new_points, [1,nsample], stride=[1,1], padding='VALID', scope='avgpool1')
# new_points = tf.concat([avg_points, max_points], axis=-1)
elif pooling == '3DCNN':
new_points = grouped_points_to_voxel_points(
cascade_id,
new_points,
valid_mask,
block_bottom_center_mm,
configs,
grouped_xyz,
IsShowVoxelModel=IsShowModel)
if IsShowModel:
print('voxel points:%s' % (shape_str([new_points])))
for i, num_out_channel in enumerate(
mlp_configs['voxel_channels'][cascade_id]):
kernel_i = [mlp_configs['voxel_kernels'][cascade_id][i]] * 3
stride_i = [mlp_configs['voxel_strides'][cascade_id][i]] * 3
if new_points.shape[1] % 2 == 0:
padding_i = np.array([[0, 0], [1, 0], [1, 0], [1, 0], [
0, 0
]]) * mlp_configs['voxel_paddings'][cascade_id][i]
else:
padding_i = np.array([[0, 0], [1, 1], [1, 1], [1, 1], [
0, 0
]]) * mlp_configs['voxel_paddings'][cascade_id][i]
new_points = tf.pad(new_points, padding_i, "CONSTANT")
if type(num_out_channel) == int:
new_points = tf_util.conv3d(new_points,
num_out_channel,
kernel_i,
scope='3dconv_%d' % (i),
stride=stride_i,
padding='VALID',
bn=bn,
is_training=is_training,
bn_decay=bn_decay,
name='points_3dcnn_%d' % (i))
if IsShowModel:
print('block learning by 3dcnn %d, new_points:%s' %
(i, shape_str([new_points])))
elif num_out_channel == 'max':
new_points = tf_util.max_pool3d(new_points,
kernel_i,
scope='3dmax_%d' % (i),
stride=stride_i,
padding='VALID')
if IsShowModel:
print('block learning max pooling %d, new_points:%s' %
(i, shape_str([new_points])))
elif num_out_channel == 'avg':
new_points = tf_util.avg_pool3d(new_points,
kernel_i,
scope='3dmax_%d' % (i),
stride=stride_i,
padding='VALID')
if IsShowModel:
print('block learning avg pooling %d, new_points:%s' %
(i, shape_str([new_points])))
# gpu_0/sa_layer1/3dconv_0/points_3dcnn_0:0
if configs['Cnn_keep_prob'] < 1:
if (not configs['only_last_layer_ineach_cascade']
) or i == len(
mlp_configs['voxel_channels'][cascade_id]) - 1:
new_points = tf_util.dropout(
new_points,
keep_prob=configs['Cnn_keep_prob'],
is_training=is_training,
scope='dropout',
name='3dcnn_dp%d' % (i))
# gpu_0/sa_layer4/3dconv_0/points_3dcnn_0:0
new_points = tf.squeeze(new_points, [1, 2, 3])
new_points = tf.reshape(
new_points, [batch_size, -1, 1, new_points.shape[-1].value])
if IsShowModel:
print('after %s, new_points:%s' %
(pooling, shape_str([new_points])))
if 'growth_rate' in mlp_configs['block_encoder'][cascade_id]:
new_points = tf_util.dense_net(
new_points,
mlp_configs['block_encoder'][cascade_id],
bn,
is_training,
bn_decay,
scope='dense_cascade_%d_block_encoder' % (cascade_id),
is_show_model=IsShowModel)
else:
for i, num_out_channel in enumerate(
mlp_configs['block_encoder'][cascade_id]):
new_points = tf_util.conv2d(new_points,
num_out_channel, [1, 1],
padding='VALID',
stride=[1, 1],
bn=bn,
is_training=is_training,
scope='conv_post_%d' % (i),
bn_decay=bn_decay)
if configs['Cnn_keep_prob'] < 1:
if (not configs['only_last_layer_ineach_cascade']
) or i == len(
mlp_configs['block_encoder'][cascade_id]) - 1:
new_points = tf_util.dropout(
new_points,
keep_prob=configs['Cnn_keep_prob'],
is_training=is_training,
scope='dropout',
name='cnn_dp%d' % (i))
if IsShowModel:
print('block encoder %d, new_points:%s' %
(i, shape_str([new_points])))
# (2, 512, 1, 64)
new_points = tf.squeeze(new_points,
[2]) # (batch_size, npoints, mlps_1[-1])
if IsShowModel:
print(
'pointnet_sa_module return\n new_xyz: %s\n new_points:%s\n\n' %
(shape_str([new_xyz]), shape_str([new_points])))
#import pdb;pdb.set_trace()
# (2, 512, 64)
return new_xyz, new_points, root_point_features