def graph_conv_cheby(self, x, cl, L, lmax, Fout, K):
# parameters
# B = batch size
# V = nb vertices
# Fin = nb input features
# Fout = nb output features
# K = Chebyshev order & support size
B, V, Fin = x.size()
B, V, Fin = int(B), int(V), int(Fin)
# rescale Laplacian
lmax = lmax_L(L)
L = rescale_L(L, lmax)
# convert scipy sparse matric L to pytorch
L = L.tocoo()
indices = np.column_stack((L.row, L.col)).T
indices = indices.astype(np.int64)
indices = torch.from_numpy(indices)
indices = indices.type(torch.LongTensor)
L_data = L.data.astype(np.float32)
L_data = torch.from_numpy(L_data)
L_data = L_data.type(torch.FloatTensor)
L = torch.sparse.FloatTensor(indices, L_data, torch.Size(L.shape))
L = Variable(L, requires_grad=False)
if torch.cuda.is_available():
L = L.cuda()
# transform to Chebyshev basis
x0 = x.permute(1, 2, 0).contiguous() # V x Fin x B
x0 = x0.view([V, Fin * B]) # V x Fin*B
x = x0.unsqueeze(0) # 1 x V x Fin*B
def concat(x, x_):
x_ = x_.unsqueeze(0) # 1 x V x Fin*B
return torch.cat((x, x_), 0) # K x V x Fin*B
if K > 1:
x1 = my_sparse_mm()(L, x0) # V x Fin*B
x = torch.cat((x, x1.unsqueeze(0)), 0) # 2 x V x Fin*B
for k in range(2, K):
x2 = 2 * my_sparse_mm()(L, x1) - x0
x = torch.cat((x, x2.unsqueeze(0)), 0) # M x Fin*B
x0, x1 = x1, x2
x = x.view([K, V, Fin, B]) # K x V x Fin x B
x = x.permute(3, 1, 2, 0).contiguous() # B x V x Fin x K
x = x.view([B * V, Fin * K]) # B*V x Fin*K
# Compose linearly Fin features to get Fout features
x = cl(x) # B*V x Fout
x = x.view([B, V, Fout]) # B x V x Fout
return x
def graph_conv_cheby(self, x, cl, L, Fout, K):
# parameters
# B = batch size
# V = nb vertices
# Fin = nb input features
# Fout = nb output features
# K = Chebyshev order & support size
B, V, Fin = x.size()
B, V, Fin = int(B), int(V), int(Fin)
# rescale Laplacian
lmax = lmax_L(L)
L = rescale_L(L, lmax)
# convert scipy sparse matric L to pytorch
L = sparse_mx_to_torch_sparse_tensor(L)
if torch.cuda.is_available():
L = L.cuda()
# transform to Chebyshev basis
x0 = x.permute(1, 2, 0).contiguous() # V x Fin x B
x0 = x0.view([V, Fin * B]) # V x Fin*B
x = x0.unsqueeze(0) # 1 x V x Fin*B
def concat(x, x_):
x_ = x_.unsqueeze(0) # 1 x V x Fin*B
return torch.cat((x, x_), 0) # K x V x Fin*B
if K > 1:
x1 = my_sparse_mm()(L, x0) # V x Fin*B
x = torch.cat((x, x1.unsqueeze(0)), 0) # 2 x V x Fin*B
for k in range(2, K):
x2 = 2 * my_sparse_mm()(L, x1) - x0
x = torch.cat((x, x2.unsqueeze(0)),
0) # M x Fin*B --> K x V x Fin*B
x0, x1 = x1, x2
x = x.view([K, V, Fin, B]) # K x V x Fin x B
x = x.permute(3, 1, 2, 0).contiguous() # B x V x Fin x K
x = x.view([B * V, Fin * K]) # B*V x Fin*K
# Compose linearly Fin features to get Fout features
x = cl(x) # B*V x Fout
x = x.view([B, V, Fout]) # B x V x Fout
return x
def prepare(self):
# split train and test
self.training_events = self.dataset[:self.n_training_events]
self.test_events = self.dataset[self.n_training_events:]
# set up model
self.model = Graph_ConvNet(self.options)
self.grid_side = self.options['grid_side']
self.number_edges = self.options['number_edges']
self.metric = self.options['metric']
# create graph of Euclidean grid
self.Grid = grid_graph(self.grid_side, self.number_edges, self.metric)
# Compute coarsened graphs
self.L, self.perm = coarsen(self.Grid, self.options['coarsening'])
lmax = []
for i in range(self.options['coarsening']):
lmax.append(lmax_L(self.L[i]))
self.options['D'] = max(perm) + 1
self.options['FC1Fin'] = self.options['CL2_F'] * \
(self.options['D'] // 16)
def build_coarse_graphs(mesh_face, joint_num, skeleton, flip_pairs, levels=9):
joint_adj = build_adj(joint_num, skeleton, flip_pairs)
# Build graph
mesh_adj = build_graph(mesh_face, mesh_face.max() + 1)
graph_Adj, graph_L, graph_perm = coarsen(mesh_adj, levels=levels)
input_Adj = sp.csr_matrix(joint_adj)
input_Adj.eliminate_zeros()
input_L = laplacian(input_Adj, normalized=True)
graph_L[-1] = input_L
graph_Adj[-1] = input_Adj
# Compute max eigenvalue of graph Laplacians, rescale Laplacian
graph_lmax = []
renewed_lmax = []
for i in range(levels):
graph_lmax.append(lmax_L(graph_L[i]))
graph_L[i] = rescale_L(graph_L[i], graph_lmax[i])
# renewed_lmax.append(lmax_L(graph_L[i]))
return graph_Adj, graph_L, graph_perm, perm_index_reverse(graph_perm[0])
t_start = time.time()
grid_side = 28
number_edges = 4
metric = 'euclidean'
A = grid_graph(grid_side, number_edges,
metric) # create graph of Euclidean grid
# Compute coarsened graphs
coarsening_levels = 4
L, perm = coarsen(A, coarsening_levels)
# Compute max eigenvalue of graph Laplacians
lmax = []
for i in range(coarsening_levels):
lmax.append(lmax_L(L[i]))
print('lmax: ' + str([lmax[i] for i in range(coarsening_levels)]))
# Reindex nodes to satisfy a binary tree structure
train_data = perm_data(train_data, perm)
val_data = perm_data(val_data, perm)
test_data = perm_data(test_data, perm)
print(train_data.shape)
print(val_data.shape)
print(test_data.shape)
print('Execution time: {:.2f}s'.format(time.time() - t_start))
del perm