def build(self, inputs):
"""Use config dictionary to generate all important attributes for head.
Args:
inputs: dictionary of the shape of input args as a dictionary of lists.
"""
keys = [int(key) for key in inputs.keys()]
self._min_level = min(keys)
self._max_level = max(keys)
self._min_depth = inputs[str(self._min_level)][-1]
self._depths = self.get_raw_depths(self._min_depth, inputs)
# directly connect to an input path and process it
self.preprocessors = dict()
# resample an input and merge it with the output of another path
# inorder to aggregate backbone outputs
self.resamples = dict()
# set of convoltion layers and upsample layers that are used to
# prepare the FPN processors for output
for level, depth in zip(
reversed(range(self._min_level, self._max_level + 1)),
self._depths):
if level == self._min_level:
self.resamples[str(level)] = nn_blocks.PathAggregationBlock(
filters=depth // 2,
inverted=True,
upsample=True,
drop_final=self._csp_stack == 0,
upsample_size=2,
**self._base_config)
self.preprocessors[str(level)] = _IdentityRoute()
elif level != self._max_level:
self.resamples[str(level)] = nn_blocks.PathAggregationBlock(
filters=depth // 2,
inverted=True,
upsample=True,
drop_final=False,
upsample_size=2,
**self._base_config)
self.preprocessors[str(level)] = nn_blocks.DarkRouteProcess(
filters=depth,
repetitions=self._fpn_depth -
int(level == self._min_level),
block_invert=True,
insert_spp=False,
csp_stack=self._csp_stack,
**self._base_config)
else:
self.preprocessors[str(level)] = nn_blocks.DarkRouteProcess(
filters=depth,
repetitions=self._max_fpn_depth +
1 * int(self._csp_stack == 0),
insert_spp=True,
block_invert=False,
csp_stack=min(self._csp_stack, self._max_fpn_depth),
**self._base_config)
def test_gradient_pass_though(self, width, height, filters, repetitions,
spp):
loss = tf.keras.losses.MeanSquaredError()
optimizer = tf.keras.optimizers.SGD()
test_layer = nn_blocks.DarkRouteProcess(filters=filters,
repetitions=repetitions,
insert_spp=spp)
if repetitions == 1:
filter_y1 = filters
else:
filter_y1 = filters // 2
init = tf.random_normal_initializer()
x = tf.Variable(initial_value=init(shape=(1, width, height, filters),
dtype=tf.float32))
y_0 = tf.Variable(initial_value=init(shape=(1, width, height, filters),
dtype=tf.float32))
y_1 = tf.Variable(initial_value=init(
shape=(1, width, height, filter_y1), dtype=tf.float32))
with tf.GradientTape() as tape:
x_hat_0, x_hat_1 = test_layer(x)
grad_loss_0 = loss(x_hat_0, y_0)
grad_loss_1 = loss(x_hat_1, y_1)
grad = tape.gradient([grad_loss_0, grad_loss_1],
test_layer.trainable_variables)
optimizer.apply_gradients(zip(grad, test_layer.trainable_variables))
self.assertNotIn(None, grad)
return
def test_pass_through(self, width, height, filters, repetitions, spp):
x = tf.keras.Input(shape=(width, height, filters))
test_layer = nn_blocks.DarkRouteProcess(
filters=filters, repetitions=repetitions, insert_spp=spp)
outx = test_layer(x)
self.assertLen(outx, 2, msg='len(outx) != 2')
if repetitions == 1:
filter_y1 = filters
else:
filter_y1 = filters // 2
self.assertAllEqual(
outx[1].shape.as_list(), [None, width, height, filter_y1])
self.assertAllEqual(
filters % 2,
0,
msg='Output of a DarkRouteProcess layer has an odd number of filters')
self.assertAllEqual(outx[0].shape.as_list(), [None, width, height, filters])
def build(self, inputs):
"""Use config dictionary to generate all important attributes for head.
Args:
inputs: dictionary of the shape of input args as a dictionary of lists.
"""
# define the key order
keys = [int(key) for key in inputs.keys()]
self._min_level = min(keys)
self._max_level = max(keys)
self._min_depth = inputs[str(self._min_level)][-1]
self._depths = self.get_raw_depths(self._min_depth, inputs)
# directly connect to an input path and process it
self.preprocessors = dict()
# resample an input and merge it with the output of another path
# inorder to aggregate backbone outputs
self.resamples = dict()
# FPN will reverse the key process order for the backbone, so we need
# adjust the order that objects are created and processed to adjust for
# this. not using an FPN will directly connect the decoder to the backbone
# therefore the object creation order needs to be done from the largest
# to smallest level.
if self._fpn_input:
# process order {... 3, 4, 5}
self._iterator = range(self._min_level, self._max_level + 1)
self._check = lambda x: x < self._max_level
self._key_shift = lambda x: x + 1
self._input = self._min_level
downsample = True
upsample = False
else:
# process order {5, 4, 3, ...}
self._iterator = list(
reversed(range(self._min_level, self._max_level + 1)))
self._check = lambda x: x > self._min_level
self._key_shift = lambda x: x - 1
self._input = self._max_level
downsample = False
upsample = True
if self._csp_stack == 0:
proc_filters = lambda x: x
resample_filters = lambda x: x // 2
else:
proc_filters = lambda x: x * 2
resample_filters = lambda x: x
for level, depth in zip(self._iterator, self._depths):
if level == self._input:
self.preprocessors[str(level)] = nn_blocks.DarkRouteProcess(
filters=proc_filters(depth),
repetitions=self._max_level_process_len,
insert_spp=self._embed_spp,
block_invert=False,
insert_sam=self._use_spatial_attention,
csp_stack=self._csp_stack,
**self._base_config)
else:
self.resamples[str(level)] = nn_blocks.PathAggregationBlock(
filters=resample_filters(depth),
upsample=upsample,
downsample=downsample,
inverted=False,
drop_final=self._csp_stack == 0,
**self._base_config)
self.preprocessors[str(level)] = nn_blocks.DarkRouteProcess(
filters=proc_filters(depth),
repetitions=self._path_process_len,
insert_spp=False,
insert_sam=self._use_spatial_attention,
csp_stack=self._csp_stack,
**self._base_config)
