def _compute_vert_context_soft(self, edge_factor, vert_factor, reuse=False):
"""
attention-based vertex(node) message pooling
"""
out_edge = utils.pad_and_gather(edge_factor, self.edge_pair_mask_inds[:,0])
in_edge = utils.pad_and_gather(edge_factor, self.edge_pair_mask_inds[:,1])
# gather correspounding vert factors
vert_factor_gathered = tf.gather(vert_factor, self.edge_pair_segment_inds)
# concat outgoing edges and ingoing edges with gathered vert_factors
out_edge_w_input = tf.concat(concat_dim=1, values=[out_edge, vert_factor_gathered])
in_edge_w_input = tf.concat(concat_dim=1, values=[in_edge, vert_factor_gathered])
# compute compatibility scores
(self.feed(out_edge_w_input)
.fc(1, relu=False, reuse=reuse, name='out_edge_w_fc')
.sigmoid(name='out_edge_score'))
(self.feed(in_edge_w_input)
.fc(1, relu=False, reuse=reuse, name='in_edge_w_fc')
.sigmoid(name='in_edge_score'))
out_edge_w = self.get_output('out_edge_score')
in_edge_w = self.get_output('in_edge_score')
# weight the edge factors with computed weigths
out_edge_weighted = tf.mul(out_edge, out_edge_w)
in_edge_weighted = tf.mul(in_edge, in_edge_w)
edge_sum = out_edge_weighted + in_edge_weighted
vert_ctx = tf.segment_sum(edge_sum, self.edge_pair_segment_inds)
return vert_ctx
def _compute_vert_context_fus(self, edge_factor, vert_factor, reuse=False):
"""
attention-based vertex(node) message pooling
also collecting messages from the detections of this object in other frames
"""
out_edge = utils.pad_and_gather(
edge_factor, self.edge_pair_mask_inds[:, 0]
) # from rel_pair_segment_inds and contains the indices of the relations which are going out
in_edge = utils.pad_and_gather(
edge_factor, self.edge_pair_mask_inds[:, 1]
) # if I have 5 objects, each of them is connected to 4 objects, so 5 times 4, edge_pair_mask_inds has size 20, but there is 25, and this 20 coming every time. dans data_utils, there is this pad with pad with dummy edge ind
# gather correspounding vert factors
vert_factor_gathered = tf.gather(
vert_factor, self.edge_pair_segment_inds
) # in Eq.3 you compute sum_j v_1*[h_i,hi->j]hi->j. So you want to concatenate each h_i with hi->j. Here, you are building the matrix vert_factor_gathered, contains the h_i part. Later you jus have to concatenate this matrix with out_edge which contains the hi->j. vert_factor_gathered will contains all the hi. vert_factor_gathered is also used to concatenate with in_edge, because self.edge_pair_segment_inds[k] is build to be the segment id corresponding to self.edge_pair_mask_inds[k,:]
vert_factor_matched = utils.pad_and_gather(
vert_factor, self.obj_fus_mask_inds[:]
) # This tells where is this object matched in the other frames, and select the corresponding features
vert_factor_gathered_vid = tf.gather(
vert_factor, self.obj_fus_segment_inds
) # instead of having number of output +1 I need to have the number of frames
# concat outgoing edges and ingoing edges with gathered vert_factors
out_edge_w_input = tf.concat(concat_dim=1,
values=[out_edge, vert_factor_gathered])
in_edge_w_input = tf.concat(concat_dim=1,
values=[in_edge, vert_factor_gathered])
vid_edge_w_input = tf.concat(
concat_dim=1,
values=[vert_factor_matched, vert_factor_gathered_vid])
# compute compatibility scores
(self.feed(out_edge_w_input).fc(
1, relu=False, reuse=reuse,
name='out_edge_w_fc').sigmoid(name='out_edge_score'))
(self.feed(in_edge_w_input).fc(
1, relu=False, reuse=reuse,
name='in_edge_w_fc').sigmoid(name='in_edge_score'))
(self.feed(vid_edge_w_input).fc(
1, relu=False, reuse=reuse,
name='vid_vert_w_fc').sigmoid(name='vid_vert_score'))
out_edge_w = self.get_output('out_edge_score')
in_edge_w = self.get_output('in_edge_score')
vid_vert_w = self.get_output('vid_vert_score')
# weight the edge factors with computed weigths
out_edge_weighted = tf.mul(out_edge, out_edge_w)
in_edge_weighted = tf.mul(in_edge, in_edge_w)
vid_vert_weighted = tf.mul(vert_factor_matched, vid_vert_w)
edge_sum = out_edge_weighted + in_edge_weighted
vert_ctx = tf.segment_sum(
edge_sum, self.edge_pair_segment_inds) + tf.segment_sum(
vid_vert_weighted, self.obj_fus_segment_inds)
return vert_ctx
def _compute_vert_context_soft(self,
edge_factor,
vert_factor,
reuse=False):
"""
attention-based vertex(node) message pooling
"""
out_edge = utils.pad_and_gather(
edge_factor, self.edge_pair_mask_inds[:, 0]
) # from rel_pair_segment_inds and contains the indices of the relations which are going out
in_edge = utils.pad_and_gather(
edge_factor, self.edge_pair_mask_inds[:, 1]
) # 100 x 512 i.e. edge_factor[self.edge_pair_mask_inds[:,1],:] self.edge_pair_mask_inds[:,1] is 100,1
# gather correspounding vert factors
vert_factor_gathered = tf.gather(
vert_factor, self.edge_pair_segment_inds
) # will tell you which vert_factor correspond to which segment id maybe?
# concat outgoing edges and ingoing edges with gathered vert_factors
out_edge_w_input = tf.concat(concat_dim=1,
values=[out_edge, vert_factor_gathered
]) # 100 x 1024
in_edge_w_input = tf.concat(concat_dim=1,
values=[in_edge, vert_factor_gathered])
# compute compatibility scores
(self.feed(out_edge_w_input).fc(
1, relu=False, reuse=reuse,
name='out_edge_w_fc').sigmoid(name='out_edge_score'))
(self.feed(in_edge_w_input).fc(
1, relu=False, reuse=reuse,
name='in_edge_w_fc').sigmoid(name='in_edge_score'))
out_edge_w = self.get_output('out_edge_score')
in_edge_w = self.get_output('in_edge_score')
# weight the edge factors with computed weigths
out_edge_weighted = tf.mul(out_edge, out_edge_w)
in_edge_weighted = tf.mul(in_edge, in_edge_w)
edge_sum = out_edge_weighted + in_edge_weighted
vert_ctx = tf.segment_sum(edge_sum, self.edge_pair_segment_inds)
return vert_ctx
def _compute_vert_context_hard(self, edge_factor, vert_factor, reduction_mode='max'):
"""
max or average message pooling
"""
edge_factor_gathered = utils.pad_and_gather(edge_factor, self.edge_mask_inds, None)
vert_ctx = utils.padded_segment_reduce(edge_factor_gathered, self.edge_segment_inds,
vert_factor.get_shape()[0], reduction_mode)
return vert_ctx
def _compute_edge_context_3d_fus(self,
vert_factor,
edge_factor,
reuse=False):
"""
attention-based edge message pooling
this output will be the input edge_ctx of _edge_rnn_forward(edge_ctx, ...
edge_factor and vert_factor are gru_cell
"""
vert_pairs = utils.gather_vec_pairs(
vert_factor, self.relations
) #Tensor("Reshape:0", shape=(?, 1024), dtype=float32) if relation is [24 2], vert_pairs is [24 2*512] so I guess the corresponding object feature for each relation
geo_pairs = utils.gather_vec_pairs(
self.geo_state, self.relations
) #utils.gather_vec_pairs(self.geo_state, self.relations)
self.geo_pairs = geo_pairs
edge_factor_matched = utils.pad_and_gather(
edge_factor, self.rel_fus_mask_inds[:]
) # getting the output for this relation in every frame
edge_factor_gathered_vid = tf.gather(
edge_factor, self.rel_fus_segment_inds
) # getting the same but in other order. This way it is just a matter of concatenate and sum
vid_edge_w_input = tf.concat(
concat_dim=1,
values=[edge_factor_matched, edge_factor_gathered_vid])
sub_vert, obj_vert = tf.split(
split_dim=1, num_split=2, value=vert_pairs
) # I guess putting the in (subject) on one part and the out (object) on the other part, because subject verb object, so each is 24 z 512
sub_geo, obj_geo = tf.split(split_dim=1, num_split=2, value=geo_pairs)
sub_vert_w_input = tf.concat(concat_dim=1,
values=[sub_vert, edge_factor])
obj_vert_w_input = tf.concat(concat_dim=1,
values=[obj_vert, edge_factor])
# compute compatibility scores
(self.feed(sub_vert_w_input).fc(
1, relu=False, reuse=reuse,
name='sub_vert_w_fc').sigmoid(name='sub_vert_score')
) # passing the input messages from the relation to a fc layer
(self.feed(obj_vert_w_input).fc(
1, relu=False, reuse=reuse,
name='obj_vert_w_fc').sigmoid(name='obj_vert_score')
) # passing the previous state of the object node to a fc layer
# encoding the geomtery of the relation
geo_pairs = self.norm_geo_pairs(geo_pairs, sc=500)
#sub_geo, obj_geo = tf.split(split_dim=1, num_split=2, value=geo_pairs)
#geo_conc = tf.concat(concat_dim=1, values=[sub_geo, obj_geo])
(self.feed(geo_pairs).fc(
100, relu=False, reuse=reuse,
name='geo_fc1_obj').sigmoid(name='geo_encoded_pre').fc(
512, relu=False, reuse=reuse,
name='geo_fc2_obj').sigmoid(name='geo_encoded')
) # passing the previous state of the object node to a fc layer
geo_encoded = self.get_output('geo_encoded')
# then concatenating wiht the relation feature (edge_factor) and getting a weight out of that
geo_encoded_w_input = tf.concat(concat_dim=1,
values=[geo_encoded, edge_factor])
(self.feed(geo_encoded_w_input).fc(
1, relu=False, reuse=reuse,
name='geo_w_fc').sigmoid(name='geo_vert_score')
) # passing the previous state of the object node to a fc layer
# will compute weigts from the messages in each relations
(self.feed(vid_edge_w_input).fc(
1, relu=False, reuse=reuse,
name='vid_edge_w_fc').sigmoid(name='vid_edge_score'))
sub_vert_w = self.get_output(
'sub_vert_score'
) #this guy is 24 x 1, and the relations vector is 24,which count for the 4 objects present in the 2 images.
obj_vert_w = self.get_output('obj_vert_score')
geo_vert_w = self.get_output('geo_vert_score')
vid_edge_w = self.get_output('vid_edge_score')
weighted_sub = tf.mul(sub_vert, sub_vert_w)
weighted_obj = tf.mul(obj_vert, obj_vert_w)
weighted_geo = tf.mul(geo_encoded, geo_vert_w)
vid_edge_weighted = tf.mul(edge_factor_matched, vid_edge_w)
return weighted_sub + weighted_obj + weighted_geo + tf.segment_sum(
vid_edge_weighted, self.rel_fus_segment_inds)