def forward(self, net, batched_inputs):
del batched_inputs
cls_net = wnnl.non_local_blockv1(net,
scope=f"NonLocalROIHeadsHook_cls",
normalizer_fn=wnnl.evo_norm_s0,
activation_fn=None,
weighed_sum=False)
reg_net = wnnl.non_local_blockv1(net,
scope=f"NonLocalROIHeadsHook_reg",
normalizer_fn=wnnl.evo_norm_s0,
activation_fn=None,
weighed_sum=False)
return cls_net, reg_net
def forward(self, net, batched_inputs, reuse=None):
del batched_inputs
net = wnnl.non_local_blockv1(net,
scope=f"NonLocalROIHeadsHook",
normalizer_fn=wnnl.evo_norm_s0,
activation_fn=None,
weighed_sum=False)
return net
def forward(self, features, batched_inputs):
normalizer_fn, normalizer_params = odt.get_norm(
"evo_norm_s0", is_training=self.is_training)
res = OrderedDict()
with tf.variable_scope("BalanceNonLocalBackboneHook"):
del batched_inputs
ref_index = 1
end_points = list(features.items())
k0, v0 = end_points[ref_index]
mfeatures = []
with tf.name_scope("fusion"):
shape0 = wmlt.combined_static_and_dynamic_shape(v0)
for i, (k, v) in enumerate(end_points):
if i == ref_index:
net = v
else:
net = tf.image.resize_bilinear(v,
shape0[1:3],
name=f"resize{i}")
mfeatures.append(net)
net = tf.add_n(mfeatures) / float(len(mfeatures))
net = slim.conv2d(net,
net.get_shape().as_list()[-1], [3, 3],
activation_fn=None,
normalizer_fn=normalizer_fn,
normalizer_params=normalizer_params,
scope=f"smooth")
for i, (k, v) in enumerate(end_points):
with tf.variable_scope(f"merge{i}"):
shape = wmlt.combined_static_and_dynamic_shape(v)
v0 = tf.image.resize_bilinear(net, shape[1:3])
net = v + v0
if i > 0:
net = wnnl.non_local_blockv1(
net,
inner_dims_multiplier=[1, 1, 1],
normalizer_fn=normalizer_fn,
normalizer_params=normalizer_params,
activation_fn=None,
weighed_sum=False)
res[k] = net
return res
def forward(self, x, batched_inputs, reuse=None):
del batched_inputs
if isinstance(x, (list, tuple)) and len(x) == 2:
iou_x = wnnl.non_local_blockv3(x[0],
x[1],
x[1],
inner_dims_multiplier=[1, 1, 1],
scope=f"NonLocalROIHeadsHook_iou",
normalizer_fn=wnnl.evo_norm_s0,
activation_fn=None,
weighed_sum=False,
skip_connect=False)
return x[0], x[0], iou_x
else:
iou_x = wnnl.non_local_blockv1(x,
scope=f"NonLocalROIHeadsHook_iou",
normalizer_fn=wnnl.evo_norm_s0,
activation_fn=None,
weighed_sum=False)
return x, x, iou_x
def forward(self, features, batched_inputs):
del batched_inputs
res = OrderedDict()
normalizer_fn, normalizer_params = odt.get_norm(
"evo_norm_s0", is_training=self.is_training)
with tf.variable_scope("NonLocalBackboneHook"):
for k, v in features.items():
if k[0] not in ["C", "P"]:
continue
level = int(k[1:])
if level <= 3:
res[k] = v
continue
res[k] = wnnl.non_local_blockv1(
v,
inner_dims_multiplier=[1, 1, 1],
normalizer_fn=normalizer_fn,
normalizer_params=normalizer_params,
activation_fn=None,
weighed_sum=False)
return res