def execute(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = nn.relu(out)
spx = jt.split(out, self.width, 1)
for i in range(self.nums):
if ((i == 0) or (self.stype == 'stage')):
sp = spx[i]
else:
sp = (sp + spx[i])
sp = self.convs[i](sp)
sp = nn.relu(self.bns[i](sp))
if (i == 0):
out = sp
else:
out = jt.contrib.concat((out, sp), dim=1)
if ((self.scale != 1) and (self.stype == 'normal')):
out = jt.contrib.concat((out, spx[self.nums]), dim=1)
elif ((self.scale != 1) and (self.stype == 'stage')):
out = jt.contrib.concat((out, self.pool(spx[self.nums])), dim=1)
out = self.conv3(out)
out = self.bn3(out)
if (self.downsample is not None):
residual = self.downsample(x)
out += residual
out = nn.relu(out)
return out
def execute(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
spx = jt.split(out, self.width, 1)
for i in range(self.nums):
if i == 0 or self.stype == 'stage':
sp = spx[i]
else:
sp = sp + spx[i]
sp = self.convs[i](sp)
sp = self.relu(self.bns[i](sp))
if i == 0:
out = sp
else:
out = jt.concat((out, sp), 1)
if self.scale != 1 and self.stype == 'normal':
out = jt.concat((out, spx[self.nums]), 1)
elif self.scale != 1 and self.stype == 'stage':
out = jt.concat((out, self.pool(spx[self.nums])), 1)
out = self.conv3(out)
out = self.bn3(out)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
def execute(self, x):
input_pts, input_views = jt.split(x,
[self.input_ch, self.input_ch_views],
dim=-1)
h = input_pts
for i, l in enumerate(self.pts_linears):
h = self.pts_linears[i](h)
h = jt.nn.relu(h)
if i in self.skips:
h = jt.concat([input_pts, h], -1)
if self.use_viewdirs:
alpha = self.alpha_linear(h)
feature = self.feature_linear(h)
h = jt.concat([feature, input_views], -1)
for i, l in enumerate(self.views_linears):
h = self.views_linears[i](h)
h = jt.nn.relu(h)
rgb = self.rgb_linear(h)
outputs = jt.concat([rgb, alpha], -1)
else:
outputs = self.output_linear(h)
return outputs
def prepare_targets(self, points, targets, im_w, im_h):
object_sizes_of_interest = self.object_sizes_of_interest
expanded_object_sizes_of_interest = []
for l, points_per_level in enumerate(points):
object_sizes_of_interest_per_level = \
points_per_level.new_tensor(object_sizes_of_interest[l])
expanded_object_sizes_of_interest.append(
object_sizes_of_interest_per_level[None].expand(
len(points_per_level), -1))
expanded_object_sizes_of_interest = jt.contrib.concat(
expanded_object_sizes_of_interest, dim=0)
num_points_per_level = [
len(points_per_level) for points_per_level in points
]
self.num_points_per_level = num_points_per_level
points_all_level = jt.contrib.concat(points, dim=0)
labels, reg_targets, matched_idxes = self.compute_targets_for_locations(
points_all_level, targets, expanded_object_sizes_of_interest, im_w,
im_h)
labels_split = []
reg_targets_split = []
for i in range(len(labels)):
labels_split.append(
jt.split(labels[i], num_points_per_level, dim=0))
reg_targets_split.append(
jt.split(reg_targets[i], num_points_per_level, dim=0))
labels_level_first = []
reg_targets_level_first = []
for level in range(len(points)):
labels_level_first.append(
jt.contrib.concat(
[labels_per_im[level] for labels_per_im in labels_split],
dim=0))
reg_targets_per_level = \
jt.contrib.concat([reg_targets_per_im[level] for reg_targets_per_im in reg_targets_split], dim=0)
if self.norm_reg_targets:
reg_targets_per_level = reg_targets_per_level / self.fpn_strides[
level]
reg_targets_level_first.append(reg_targets_per_level)
matched_idxes = jt.stack(matched_idxes)
return labels_level_first, reg_targets_level_first, labels, reg_targets, matched_idxes
def prepare_targets(self, points, targets):
object_sizes_of_interest = [
[-1, 64],
[64, 128],
[128, 256],
[256, 512],
[512, INF],
]
expanded_object_sizes_of_interest = []
for l, points_per_level in enumerate(points):
object_sizes_of_interest_per_level = \
points_per_level.new_tensor(object_sizes_of_interest[l])
expanded_object_sizes_of_interest.append(
object_sizes_of_interest_per_level[None].expand(len(points_per_level), -1)
)
expanded_object_sizes_of_interest = jt.contrib.concat(expanded_object_sizes_of_interest, dim=0)
num_points_per_level = [len(points_per_level) for points_per_level in points]
self.num_points_per_level = num_points_per_level
points_all_level = jt.contrib.concat(points, dim=0)
labels, reg_targets = self.compute_targets_for_locations(
points_all_level, targets, expanded_object_sizes_of_interest
)
for i in range(len(labels)):
labels[i] = jt.split(labels[i], num_points_per_level, dim=0)
reg_targets[i] = jt.split(reg_targets[i], num_points_per_level, dim=0)
labels_level_first = []
reg_targets_level_first = []
for level in range(len(points)):
labels_level_first.append(
jt.contrib.concat([labels_per_im[level] for labels_per_im in labels], dim=0)
)
reg_targets_level_first.append(
jt.contrib.concat([reg_targets_per_im[level] for reg_targets_per_im in reg_targets], dim=0)
)
return labels_level_first, reg_targets_level_first
