def track_time(size, dim, k):
device = utils.get_bench_device()
features = np.random.randn(size, dim)
feat = torch.tensor(features, dtype=torch.float, device=device)
# dry run
dgl.knn_graph(feat, k)
# timing
with utils.Timer() as t:
for i in range(10):
dgl.knn_graph(feat, k)
return t.elapsed_secs / 10
def track_time(size, dim, k, algorithm):
device = utils.get_bench_device()
features = np.random.RandomState(42).randn(size, dim)
feat = torch.tensor(features, dtype=torch.float, device=device)
# dry run
for i in range(1):
dgl.knn_graph(feat, k, algorithm=algorithm)
# timing
with utils.Timer() as t:
for i in range(5):
dgl.knn_graph(feat, k, algorithm=algorithm)
return t.elapsed_secs / 5
def track_time(size, dim, k):
device = utils.get_bench_device()
features = np.random.randn(size, dim)
feat = torch.tensor(features, dtype=torch.float, device=device)
# dry run
dgl.knn_graph(feat, k)
# timing
t0 = time.time()
for i in range(10):
dgl.knn_graph(feat, k)
t1 = time.time()
return (t1 - t0) / 10
def get_single_event(self, event_idx):
# ------- building the cluster graph ---------- #
cluster_cell_ID = self.ev_tree['cluster_cell_ID'].array(
entry_start=event_idx, entry_stop=event_idx + 1, library='np')[0]
cluster_cell_E = self.ev_tree['cluster_cell_E'].array(
entry_start=event_idx, entry_stop=event_idx + 1, library='np')[0]
n_clusters = len(cluster_cell_ID)
if (n_clusters == 0):
#print('Empty cluster event')
return {
'gr': [dgl.rand_graph(2, 1)],
'truth_E': torch.tensor([-1.])
}
graph_list = []
# ---- loop over clusters ---- #
for ic in range(n_clusters):
cell_E = np.array(cluster_cell_E[ic])
cell_idx = np.array(cluster_cell_ID[ic])
cluster_cell_pos = np.array(
[self.id_to_position[x] for x in cell_idx])
n_part = len(cluster_cell_pos)
if (n_part < self.k):
knn_g = dgl.knn_graph(torch.tensor(cluster_cell_pos), n_part)
else:
knn_g = dgl.knn_graph(torch.tensor(cluster_cell_pos), self.k)
knn_g.ndata['x'] = torch.tensor(cluster_cell_pos)
knn_g.ndata['en'] = torch.tensor(cell_E)
graph_list.append(knn_g)
# -------- #
cluster_energy_truth = self.ev_tree['cluster_ENG_CALIB_TOT'].array(
entry_start=event_idx, entry_stop=event_idx + 1, library='np')[0]
# ---------------------------------------------------------------- #
return {
'gr': graph_list,
'truth_E': torch.tensor(cluster_energy_truth)
}
def savetotensfile(self):
listtenstosave = []
for each in self.sampcloud:
vertex = []
vertex.append(float(each[0]))
vertex.append(float(each[1]))
vertex.append(float(each[2]))
listtenstosave.append(vertex)
nodepostens = torch.tensor(listtenstosave)
#print(nodepostens)
print(len(nodepostens))
knn_g_edges = dgl.knn_graph(nodepostens, k=20)
print(knn_g_edges)
torch.save(nodepostens.clone(), 'nodepostens.pt')
torch.save(knn_g_edges.clone(), 'knn_g_edges.pt')
self.signalStatus.emit('Tensor files saved')