def forward(self, data):
data.x = F.elu(self.conv1(data.x, data.edge_index))
data.x = self.bn1(data.x)
cluster = voxel_grid(data.pos, data.batch, size=[4,4])
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
data.x = F.elu(self.conv2(data.x, data.edge_index))
data.x = self.bn2(data.x)
cluster = voxel_grid(data.pos, data.batch, size=[6,6])
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
data.x = F.elu(self.conv3(data.x, data.edge_index))
data.x = self.bn3(data.x)
cluster = voxel_grid(data.pos, data.batch, size=[20,20])
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
data.x = F.elu(self.conv4(data.x, data.edge_index))
data.x = self.bn4(data.x)
cluster = voxel_grid(data.pos, data.batch, size=[32,32])
x = max_pool_x(cluster, data.x, data.batch, size=32)
x = x.view(-1, self.fc1.weight.size(1))
x = F.elu(self.fc1(x))
x = F.dropout(x, training=self.training)
x = self.fc2(x)
return F.log_softmax(x, dim=1)
def forward(self, data):
row, col = data.edge_index
data.edge_attr = (data.pos[col] - data.pos[row]) / (2 * 28 *
cutoff) + 0.5
# print(data.edge_index.shape)
# print(data.edge_index[:, -20:])
data.x = F.elu(self.conv1(data.x, data.edge_index, data.edge_attr))
weight = normalized_cut_2d(data.edge_index, data.pos)
cluster = graclus(data.edge_index, weight, data.x.size(0))
data.edge_attr = None
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
row, col = data.edge_index
data.edge_attr = (data.pos[col] - data.pos[row]) / (2 * 28 *
cutoff) + 0.5
data.x = F.elu(self.conv2(data.x, data.edge_index, data.edge_attr))
weight = normalized_cut_2d(data.edge_index, data.pos)
cluster = graclus(data.edge_index, weight, data.x.size(0))
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
row, col = data.edge_index
data.edge_attr = (data.pos[col] - data.pos[row]) / (2 * 28 *
cutoff) + 0.5
data.x = F.elu(self.conv3(data.x, data.edge_index, data.edge_attr))
x = global_mean_pool(data.x, data.batch)
return self.fc1(x)
x = F.elu(self.fc1(x))
x = F.dropout(x, training=self.training)
return F.log_softmax(self.fc2(x), dim=1)
def forward(self, data):
x, edge_index = data.x, data.edge_index
x = self.conv1(x, edge_index)
x = x.relu()
cluster1 = graclus(edge_index, num_nodes=x.shape[0])
pooled_1 = data
pooled_1.x = x
pooled_1 = max_pool(cluster1, pooled_1)
edge_index_2 = pooled_1.edge_index
x2 = pooled_1.x
x2 = self.conv2(x2, edge_index_2)
x2 = x2.relu()
cluster2 = graclus(edge_index_2, num_nodes=x2.shape[0])
pooled_2 = pooled_1
pooled_2.x = x2
pooled_2 = max_pool(cluster2, pooled_2)
edge_index_3 = pooled_2.edge_index
x3 = pooled_2.x
x3 = self.conv3(x3, edge_index_3)
x3 = x3.relu()
x3 = self.conv4(x3, edge_index_3)
x3 = x3.relu()
x3 = knn_interpolate(x3, pooled_2.pos, pooled_1.pos)
x3 = torch.cat((x2, x3), dim=1)
x3 = self.conv5(x3, edge_index_2)
x3 = x3.relu()
x3 = knn_interpolate(x3, pooled_1.pos, data.pos)
x = torch.cat((x, x3), dim=1)
x = self.lin1(x)
x = x.relu()
x = self.lin2(x)
x = x.relu()
x = torch.sigmoid(self.out(x))
return x
def forward(self, data):
data.x = F.elu(
self.bn1(self.conv1(data.x, data.edge_index, data.edge_attr)))
cluster = voxel_grid(data.pos, data.batch, size=4)
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
data = self.block1(data)
cluster = voxel_grid(data.pos, data.batch, size=6)
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
data = self.block2(data)
cluster = voxel_grid(data.pos, data.batch, size=24)
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
data = self.block3(data)
cluster = voxel_grid(data.pos, data.batch, size=64)
x = max_pool_x(cluster, data.x, data.batch, size=8)
# if your torch-geometric version is below 1.3.2(roughly, we do not test all versions), use x.view() instead of x[0].view()
# x = x.view(-1, self.fc1.weight.size(1))
x = x[0].view(-1, self.fc1.weight.size(1))
x = self.fc1(x)
x = F.elu(x)
x = self.bn(x)
x = self.drop_out(x)
x = self.fc2(x)
return F.log_softmax(x, dim=1)
def forward(self, data):
data.x = F.elu(self.conv1(data.x, data.edge_index, data.edge_attr))
weight = normalized_cut_2d(data.edge_index, data.pos)
cluster = graclus(data.edge_index, weight, data.x.size(0))
data.edge_attr = None
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
row, col = data.edge_index
data.edge_attr = (data.pos[col] -
data.pos[row]) / (2 * self.args.cutoff) + 0.5
data.x = F.elu(self.conv2(data.x, data.edge_index, data.edge_attr))
weight = normalized_cut_2d(data.edge_index, data.pos)
cluster = graclus(data.edge_index, weight, data.x.size(0))
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
row, col = data.edge_index
data.edge_attr = (data.pos[col] -
data.pos[row]) / (2 * self.args.cutoff) + 0.5
data.x = F.elu(self.conv3(data.x, data.edge_index, data.edge_attr))
x = global_mean_pool(data.x, data.batch)
x = F.elu(self.fc1(x))
x = F.dropout(x, training=self.training, p=self.args.disc_dropout)
y = self.fc2(x)
if (self.args.wgan):
return y
return torch.sigmoid(y)
def forward(self, data):
data.x = F.elu(
self.bn1(self.conv0(data.x, data.edge_index, data.edge_attr)))
cluster = voxel_grid(data.pos, data.batch, size=[4, 3])
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
data = self.conv1(data)
cluster = voxel_grid(data.pos, data.batch, size=[16, 12])
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
data = self.conv2(data)
cluster = voxel_grid(data.pos, data.batch, size=[30, 23])
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
data = self.conv3(data)
cluster = voxel_grid(data.pos, data.batch, size=[60, 45])
x = max_pool_x(cluster, data.x, data.batch, size=16)
# x = max_pool_x(cluster, data.x, data.batch)
x = x[0].view(-1, self.fc1.weight.size(1))
x = self.fc1(x)
x = F.elu(x)
x = self.bn(x)
x = self.drop_out(x)
x = self.fc2(x)
return F.log_softmax(x, dim=1)
def forward(self, data):
data.x = F.elu(self.conv1a(data.x, data.edge_index, data.edge_attr))
data.x = F.elu(self.conv1b(data.x, data.edge_index, data.edge_attr))
# data.x = F.elu(self.conv1c(data.x, data.edge_index, data.edge_attr))
# data.x = self.bn1(data.x)
weight = normalized_cut_2d(data.edge_index, data.pos)
cluster1 = graclus(data.edge_index, weight, data.x.size(0))
pos1 = data.pos
edge_index1 = data.edge_index
batch1 = data.batch if hasattr(data, 'batch') else None
# weights1 = bweights(data, cluster1)
data = max_pool(cluster1, data, transform=T.Cartesian(cat=False))
data.x = F.elu(self.conv2a(data.x, data.edge_index, data.edge_attr))
data.x = F.elu(self.conv2b(data.x, data.edge_index, data.edge_attr))
# data.x = F.elu(self.conv2c(data.x, data.edge_index, data.edge_attr))
weight = normalized_cut_2d(data.edge_index, data.pos)
cluster2 = graclus(data.edge_index, weight, data.x.size(0))
pos2 = data.pos
edge_index2 = data.edge_index
batch2 = data.batch if hasattr(data, 'batch') else None
# weights2 = bweights(data, cluster2)
data = max_pool(cluster2, data, transform=T.Cartesian(cat=False))
# upsample
# data = recover_grid_barycentric(data, weights=weights2, pos=pos2, edge_index=edge_index2, cluster=cluster2,
# batch=batch2, transform=T.Cartesian(cat=False))
data.x = F.elu(self.conv3a(data.x, data.edge_index, data.edge_attr))
data.x = F.elu(self.conv3b(data.x, data.edge_index, data.edge_attr))
data = recover_grid(data,
pos2,
edge_index2,
cluster2,
batch=batch2,
transform=T.Cartesian(cat=False))
# data = recover_grid_barycentric(data, weights=weights1, pos=pos1, edge_index=edge_index1, cluster=cluster1,
# batch=batch1, transform=T.Cartesian(cat=False))
data.x = F.elu(self.conv4a(data.x, data.edge_index, data.edge_attr))
data.x = F.elu(self.conv4b(data.x, data.edge_index, data.edge_attr))
data = recover_grid(data,
pos1,
edge_index1,
cluster1,
batch=batch1,
transform=T.Cartesian(cat=False))
# TODO handle contract on trainer and evaluator
data.x = F.elu(self.convout(data.x, data.edge_index, data.edge_attr))
x = data.x
# return F.sigmoid(x)
return x
def forward(self, data):
x, edge_index = data.x, data.edge_index
x = self.pre_lin(x) if self.masif_descr else x
x = self.conv1(x, edge_index)
x = self.s1(x)
x = self.conv2(x, edge_index)
x = self.s2(x)
x = self.conv3(x, edge_index)
x = self.s3(x)
cluster = graclus(edge_index, num_nodes=x.shape[0])
inter = data
inter.x = x
inter = max_pool(cluster, inter)
interx = self.inters1(self.interconv1(inter.x, inter.edge_index))
inter = knn_interpolate(interx, inter.pos, data.pos)
x1 = self.affine1(x)
x1 += inter
x = self.conv4(x, edge_index)
x = self.s4(x)
x = self.conv5(x, edge_index)
x = self.s5(x)
x = self.conv6(x, edge_index)
x = self.s6(x)
inter = data
inter.x = x
inter = max_pool(cluster, inter)
interx = self.inters2(self.interconv1(inter.x, inter.edge_index))
inter = knn_interpolate(interx, inter.pos, data.pos)
x2 = self.affine1(x)
x2 += inter
x = self.conv7(x, edge_index)
x = self.s7(x)
x = self.conv8(x, edge_index)
x = self.s8(x)
x = self.conv9(x, edge_index)
x = self.s9(x)
x = x + x1 + x2
x = self.conv10(x, edge_index)
x = self.s10(x)
x = self.lin1(x)
x = self.s11(x)
x = self.lin2(x)
x = self.s12(x)
x = self.out(x)
x = torch.sigmoid(x)
return x
def forward(self, data):
data.x = F.elu(self.conv1(data.x, data.edge_index, data.edge_attr))
weight = normalized_cut_2d(data.edge_index, data.pos)
cluster = graclus(data.edge_index, weight, data.x.size(0))
data.edge_attr = None
data = max_pool(cluster, data, transform=transform)
data.x = F.elu(self.conv2(data.x, data.edge_index, data.edge_attr))
weight = normalized_cut_2d(data.edge_index, data.pos)
cluster = graclus(data.edge_index, weight, data.x.size(0))
x, batch = max_pool_x(cluster, data.x, data.batch)
#x = global_mean_pool(x, batch)
x_min = torch_scatter.scatter_min(x, batch, dim=0)[0]
gather_idxs = batch.expand(x.shape[1], -1).t()
gather_mins = torch.gather(x_min, 0, gather_idxs)
s = F.relu(-gather_mins)
x = x + s
x = self.aggregator(x, batch)
s_out = self.aggregator(s, batch)
x = x - s_out
x = F.elu(self.fc1(x))
x = F.dropout(x, training=self.training)
return F.log_softmax(self.fc2(x), dim=1)
def forward(self, data):
data.x = self.datanorm * data.x
data.x = self.inputnet(data.x)
data.edge_index = to_undirected(
knn_graph(data.x,
self.k,
data.batch,
loop=False,
flow=self.edgeconv1.flow))
data.x = self.edgeconv1(data.x, data.edge_index)
weight = normalized_cut_2d(data.edge_index, data.x)
cluster = graclus(data.edge_index, weight, data.x.size(0))
data.edge_attr = None
data = max_pool(cluster, data)
data.edge_index = to_undirected(
knn_graph(data.x,
self.k,
data.batch,
loop=False,
flow=self.edgeconv2.flow))
data.x = self.edgeconv2(data.x, data.edge_index)
weight = normalized_cut_2d(data.edge_index, data.x)
cluster = graclus(data.edge_index, weight, data.x.size(0))
x, batch = max_pool_x(cluster, data.x, data.batch)
x = global_max_pool(x, batch)
return self.output(x).squeeze(-1)
def forward(self, data):
x, edge_index, batch = data.x, data.edge_index, data.batch
if self.encode_edge:
x = self.atom_encoder(x)
x = self.conv1(x, edge_index, data.edge_attr)
else:
x = self.conv1(x, edge_index)
x = F.relu(x)
xs = [global_mean_pool(x, batch)]
for i, conv in enumerate(self.convs):
x = F.relu(conv(x, edge_index))
xs += [global_mean_pool(x, batch)]
if self.pooling_type != 'none':
if self.pooling_type == 'complement':
complement = batched_negative_edges(edge_index=edge_index, batch=batch, force_undirected=True)
cluster = graclus(complement, num_nodes=x.size(0))
elif self.pooling_type == 'graclus':
cluster = graclus(edge_index, num_nodes=x.size(0))
data = Batch(x=x, edge_index=edge_index, batch=batch)
data = max_pool(cluster, data)
x, edge_index, batch = data.x, data.edge_index, data.batch
if not self.no_cat:
x = self.jump(xs)
else:
x = global_mean_pool(x, batch)
x = F.relu(self.lin1(x))
x = self.lin2(x)
return x
def forward(self, data):
inputs = data.x
x = self.uconv0(inputs)
x = self.activate_feature(x, self.bn0)
if (not self.is_strided):
x = self.kp_conv(pos=(data.points[self.layer_ind],
data.points[self.layer_ind]),
neighbors=data.list_neigh[self.layer_ind],
x=x)
x = self.activate_feature(x, self.bn1)
else:
x = self.kp_conv(pos=(data.points[self.layer_ind],
data.points[self.layer_ind + 1]),
neighbors=data.list_pool[self.layer_ind],
x=x)
x = self.activate_feature(x, self.bn1)
x = self.uconv1(x)
x = self.activate_feature(x, self.bn2)
if (not self.is_strided):
data.x = x + self.shortcut_op(inputs)
else:
data.x = x + self.shortcut_op(
max_pool(inputs, data.list_pool[self.layer_ind]))
return data
def forward(self, data):
data.x = F.elu(self.conv1(data.x, data.edge_index, data.edge_attr))
weight = normalized_cut_2d(data.edge_index, data.pos)
cluster = graclus(data.edge_index, weight, data.x.size(0))
data.edge_attr = None
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
data.x = F.elu(self.conv2(data.x, data.edge_index, data.edge_attr))
weight = normalized_cut_2d(data.edge_index, data.pos)
cluster = graclus(data.edge_index, weight, data.x.size(0))
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
data.x = F.elu(self.conv3(data.x, data.edge_index, data.edge_attr))
x = global_mean_pool(data.x, data.batch)
x = F.elu(self.fc1(x))
x = F.dropout(x, training=self.training)
return F.log_softmax(self.fc2(x), dim=1)
def forward(self, data):
data.x = F.elu(self.conv1(data.x, data.edge_index, data.edge_attr))
cluster = voxel_grid(data.pos, data.batch, size=5, start=0, end=28)
data = max_pool(cluster, data, transform=transform)
data.x = F.elu(self.conv2(data.x, data.edge_index, data.edge_attr))
cluster = voxel_grid(data.pos, data.batch, size=7, start=0, end=28)
data = max_pool(cluster, data, transform=transform)
data.x = F.elu(self.conv3(data.x, data.edge_index, data.edge_attr))
cluster = voxel_grid(data.pos, data.batch, size=14, start=0, end=27.99)
x = max_pool_x(cluster, data.x, data.batch, size=4)
x = x.view(-1, self.fc1.weight.size(1))
x = F.elu(self.fc1(x))
x = F.dropout(x, training=self.training)
x = self.fc2(x)
return F.log_softmax(x, dim=1)
def cluster_grid(grid):
data = grid
# data.x = conv1(data.x, data.edge_index, data.edge_attr)
weight = normalized_cut_2d(data.edge_index, data.pos)
cluster = graclus(data.edge_index, weight, data.x.size(0))
data.edge_attr = None
data.batch = None
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
return data, cluster
def forward(self, data):
inputs = data.x
if (data.pools[self.layer_ind].shape[1] > 2):
x = max_pool(inputs, data.pools[self.layer_ind])
else:
raise NotImplementedError("implement for list of edges")
x = None
data.x = x
return data
def forward(self, data):
x, edge_index = data.x, data.edge_index
x = self.pre_lin(x) if self.masif_descr else x
x = self.conv1(x, edge_index)
x = self.s1(x)
x = self.conv2(x, edge_index)
x = self.s2(x)
x = self.conv3(x, edge_index)
x = self.s3(x)
cluster1 = graclus(edge_index, num_nodes=x.shape[0])
inter1 = data
inter1.x = x
inter1 = max_pool(cluster1, inter1)
x = self.s4(self.conv4(inter1.x, inter1.edge_index))
edge_index = inter1.edge_index
x = self.conv5(x, edge_index)
x = self.s5(x)
x = self.conv6(x, edge_index)
x = self.s6(x)
cluster2 = graclus(edge_index, num_nodes=x.shape[0])
inter2 = inter1
inter2.x = x
inter2 = max_pool(cluster2, inter2)
x = self.s7(self.conv7(inter2.x, inter2.edge_index))
x = knn_interpolate(x, inter2.pos, inter1.pos)
x = self.conv8(x, edge_index)
x = self.s8(x)
x = knn_interpolate(x, inter1.pos, data.pos)
edge_index = data.edge_index
x = self.conv9(x, edge_index)
x = self.s9(x)
x = self.conv10(x, edge_index)
x = self.s10(x)
x = self.lin1(x)
x = self.s11(x)
x = self.lin2(x)
x = self.s12(x)
x = self.out(x)
x = torch.sigmoid(x)
return x
def forward(self, data):
x, edge_index_1 = data.x, data.edge_index
# define downscaled samples.
cluster1 = graclus(edge_index_1, num_nodes=x.shape[0])
downsample_1 = avg_pool(cluster1, data)
edge_index_2 = downsample_1.edge_index
cluster2 = graclus(edge_index_2, num_nodes=downsample_1.x.shape[0])
downsample_2 = avg_pool(cluster2, downsample_1)
edge_index_3 = downsample_2.edge_index
x = self.conv1(x, edge_index_1)
x = self.s1(x)
inter1 = data
inter1.x = x
inter1 = max_pool(cluster1, inter1)
x2 = inter1.x
x2 = torch.cat((self.affine1(downsample_1.x), x2), dim=1)
x2 = self.conv2(x2, edge_index_2)
x2 = self.s2(x2)
inter2 = inter1
inter2.x = x2
inter2 = max_pool(cluster2, inter2)
x3 = inter2.x
x3 = torch.cat((self.affine2(downsample_2.x), x3), dim=1)
x3 = self.conv3(x3, edge_index_3)
x3 = self.s3(x3)
x3 = knn_interpolate(x3, downsample_2.pos, downsample_1.pos)
x2 = torch.cat((x2, x3), dim=1)
x2 = knn_interpolate(x2, downsample_1.pos, data.pos)
x = torch.cat((x, x2), dim=1)
x = self.conv4(x, edge_index_1)
x = self.s4(x)
x = self.conv5(x, edge_index_1)
x = self.s5(x)
x = self.s6(self.lin1(x))
x = self.s7(self.lin2(x))
return torch.sigmoid(self.out(x))
def forward(self, data):
data = self.conv1(data)
cluster = voxel_grid(data.pos, data.batch, size=2)
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
data = self.conv2(data)
cluster = voxel_grid(data.pos, data.batch, size=4)
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
data = self.conv3(data)
cluster = voxel_grid(data.pos, data.batch, size=7)
x = max_pool_x(cluster, data.x, data.batch, size=25)
# x = max_pool_x(cluster, data.x, data.batch)
x = x[0].view(-1, self.fc1.weight.size(1))
x = self.fc1(x)
x = F.elu(x)
x = self.bn(x)
x = self.drop_out(x)
x = self.fc2(x)
return F.log_softmax(x, dim=1)
def forward(self, data):
data.x = F.elu(self.conv1(data.x, data.edge_index, data.edge_attr))
weight = normalized_cut_2d(data.edge_index, data.pos)
cluster = graclus(data.edge_index, weight, data.x.size(0))
data.edge_attr = None
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
data.x = F.elu(self.conv2(data.x, data.edge_index, data.edge_attr))
weight = normalized_cut_2d(data.edge_index, data.pos)
cluster = graclus(data.edge_index, weight, data.x.size(0))
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
data.x = F.elu(self.conv3(data.x, data.edge_index, data.edge_attr))
x = F.elu(self.fc1(data.x))
x = F.dropout(x, training=self.training, p=self.dropout)
x = self.fc2(x)
y = global_mean_pool(x, data.batch)
if (self.wgan):
return y
return torch.sigmoid(y)
def forward(self, data):
x = F.relu(self.conv1(data.x, data.edge_index))
cluster = graclus(data.edge_index, num_nodes=x.shape[0])
data = max_pool(
cluster, Data(x=x, batch=data.batch, edge_index=data.edge_index))
x = F.relu(self.conv2(data.x, data.edge_index))
cluster = graclus(data.edge_index, num_nodes=x.shape[0])
x, batch = max_pool_x(cluster, x, data.batch)
x = global_mean_pool(x, batch)
x = F.relu(self.fc1(x))
x = F.dropout(x, training=self.training)
x = self.fc2(x)
return x
def forward(self, data):
for i in range(self.layers_num):
data.x = self.conv_layers[i](data.x, data.pos, data.edge_index)
if self.use_cluster_pooling:
weight = normalized_cut_2d(data.edge_index, data.pos)
cluster = graclus(data.edge_index, weight, data.x.size(0))
data = max_pool(cluster,
data,
transform=T.Cartesian(cat=False))
data.x = global_mean_pool(data.x, data.batch)
x = self.fc1(data.x)
return F.log_softmax(x, dim=1)
def forward(self, data):
x, edge_index, batch = data.x, data.edge_index, data.batch
x = F.relu(self.conv1(x, edge_index))
xs = [global_mean_pool(x, batch)]
for i, conv in enumerate(self.convs):
x = F.relu(conv(x, edge_index))
xs += [global_mean_pool(x, batch)]
if i % 2 == 0 and i < len(self.convs) - 1:
cluster = graclus(edge_index, num_nodes=x.size(0))
data = Batch(x=x, edge_index=edge_index, batch=batch)
data = max_pool(cluster, data)
x, edge_index, batch = data.x, data.edge_index, data.batch
x = self.jump(xs)
x = F.relu(self.lin1(x))
x = F.dropout(x, p=0.5, training=self.training)
x = self.lin2(x)
return F.log_softmax(x, dim=-1)
def forward(self, data):
x, edge_index, edge_attr = data.x, data.edge_index, data.edge_attr
x = self.conv1(x)
x = F.elu(x)
weight = normalized_cut_2d(data.edge_index, data.pos)
cluster = graclus(data.edge_index, weight, x.size(0))
data.edge_attr = None
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
x = F.elu(self.conv1(x, edge_index, edge_attr))
x = self.conv2(x, edge_index, edge_attr)
x = F.elu(self.conv3(x, edge_index, edge_attr))
x = self.conv4(x, edge_index, edge_attr)
x = F.elu(self.conv5(x, edge_index, edge_attr))
x = self.conv6(x, edge_index, edge_attr)
x = F.dropout(x, training=self.training)
return F.log_softmax(x, dim=1)
def forward(self, sub_data):
"""
polyline vector set in torch_geometric.data.Data format
args:
sub_data (Data): [x, y, cluster, edge_index, valid_len]
"""
x, edge_index = sub_data.x, sub_data.edge_index
for name, layer in self.layer_seq.named_modules():
if isinstance(layer, GraphLayerProp):
x = layer(x, edge_index)
sub_data.x = x
out_data = max_pool(sub_data.cluster, sub_data)
# try:
assert out_data.x.shape[0] % int(sub_data.time_step_len[0]) == 0
# except:
# from pdb import set_trace; set_trace()
out_data.x = out_data.x / out_data.x.norm(dim=0)
return out_data
def forward(self, data):
data.x = F.elu(self.conv1(data.x, data.edge_index, data.edge_attr))
cluster = graclus(
data.edge_index,
torch.reshape(data.edge_attr, (data.edge_attr.shape[0], )),
data.x.size(0))
data = max_pool(cluster, data)
data.x = F.elu(self.conv2(data.x, data.edge_index, data.edge_attr))
cluster = graclus(
data.edge_index,
torch.reshape(data.edge_attr, (data.edge_attr.shape[0], )),
data.x.size(0))
x, batch = max_pool_x(cluster, data.x, data.batch)
x = global_mean_pool(x, batch)
x = F.elu(self.fc1(x))
x = F.dropout(x, training=self.training)
return F.log_softmax(self.fc2(x), dim=1)
def test_max_pool():
cluster = torch.tensor([0, 1, 0, 1, 2, 2])
x = torch.Tensor([[1, 2], [3, 4], [5, 6], [7, 8], [9, 10], [11, 12]])
pos = torch.Tensor([[0, 0], [1, 1], [2, 2], [3, 3], [4, 4], [5, 5]])
edge_index = torch.tensor([[0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3, 4, 5],
[1, 2, 3, 0, 2, 3, 0, 1, 3, 0, 1, 2, 5, 4]])
edge_attr = torch.Tensor([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1])
batch = torch.tensor([0, 0, 0, 0, 1, 1])
data = Batch(x=x, pos=pos, edge_index=edge_index, edge_attr=edge_attr,
batch=batch)
data = max_pool(cluster, data, transform=lambda x: x)
assert data.x.tolist() == [[5, 6], [7, 8], [11, 12]]
assert data.pos.tolist() == [[1, 1], [2, 2], [4.5, 4.5]]
assert data.edge_index.tolist() == [[0, 1], [1, 0]]
assert data.edge_attr.tolist() == [4, 4]
assert data.batch.tolist() == [0, 0, 1]
def forward(self, graph):
data = graph
data.x = torch.cat([data.pos, data.x], dim=1)
for i, monet_layer in enumerate(self.monet_layers[:-1]):
data.x = F.relu(
monet_layer(data.x, data.edge_index, data.edge_attr))
weight = normalized_cut_2d(data.edge_index, data.pos)
cluster = graclus(data.edge_index, weight, data.x.size(0))
if i == 0:
data.edge_attr = None
data = max_pool(cluster, data, transform=T.Cartesian(cat=False))
data.x = self.monet_layers[-1](data.x, data.edge_index, data.edge_attr)
for linear_layer in self.linear_layers[:-1]:
x = global_mean_pool(data.x, data.batch)
x = F.relu(linear_layer(x))
x = F.dropout(x)
return F.log_softmax(self.linear_layers[-1](x), dim=1)
def forward(self, data):
data.x = F.elu(self.conv1(data.x, data.edge_index, data.edge_attr))
######## calculate similarity between nodes
weight = normalized_cut_2d(data.edge_index, data.pos)
######### graph clustering without the need of eigenvector
cluster = graclus(data.edge_index, weight, data.x.size(0))
data.edge_attr = None
########## Pools and coarsens a graph. All nodes within the same cluster will be represented as one node and appply transform
data = max_pool(cluster, data, transform=transform)
########## 2nd conv net
data.x = F.elu(self.conv2(data.x, data.edge_index, data.edge_attr))
weight = normalized_cut_2d(data.edge_index, data.pos)
cluster = graclus(data.edge_index, weight, data.x.size(0))
############## Max-Pools node features according to the clustering defined in cluster
x, batch = max_pool_x(cluster, data.x, data.batch)
############## Returns batch-wise graph-level-outputs by averaging node features across the node dimension
x = global_mean_pool(x, batch)
x = F.elu(self.fc1(x))
x = F.dropout(x, training=self.training)
return F.log_softmax(self.fc2(x), dim=1)
def forward(self, data):
inputs = data.x
x = self.kp_conv0(data.points[self.layer_ind],
data.points[self.layer_ind],
data.list_neigh[self.layer_ind], inputs)
x = self.activate_feature(x, self.bn0)
if (not self.is_strided):
x = self.kp_conv1(data.points[self.layer_ind],
data.points[self.layer_ind],
data.list_neigh[self.layer_ind], x)
x = self.activate_feature(x, self.bn1)
data.x = x + self.shortcut_op(inputs)
else:
x = self.kp_conv(data.points[self.layer_ind + 1],
data.points[self.layer_ind],
data.list_pool[self.layer_ind], x)
x = self.activate_feature(x, self.bn1)
shortcut = self.shortcut_op(
max_pool(inputs, data.list_pool[self.layer_ind]))
data.x = x + shortcut
return data