def load_data(collection, n=100):
#2d indexes FTW
max_x = 180
max_y = 180
for j, d in load_data_file(n):
d['rand'] = [random.randint(-max_x, max_x), random.randint(-max_y, max_y)]
collection.insert( d )
collection.create_index( [('rand', '2d')])
def load_data(collection, n=100):
#let's skip some elements
skiplist = [10, 12, 231 , 2 , 4]
for i,d in load_data_file(n):
d['i'] = i
if i in skiplist:
continue
collection.insert( d )
def load_data(collection, n=100):
#let's skip some elements
skiplist = [10, 12, 231, 2, 4]
for i, d in load_data_file(n):
d['i'] = i
if i in skiplist:
continue
collection.insert(d)
def test_graph_cut():
adj = load_data_file("test_data.txt")
pca = PCA(256)
data = pca.fit_transform(adj.numpy())
data = torch.Tensor(data).cuda()
adj = adj.cuda()
model = GAP(4, data, 128)
parameter = torch.load("simple_test.pth")
model.load_state_dict(parameter)
model.cuda()
def load_data(collection, n=100):
#2d indexes FTW
max_x = 180
max_y = 180
for j, d in load_data_file(n):
d['rand'] = [
random.randint(-max_x, max_x),
random.randint(-max_y, max_y)
]
collection.insert(d)
collection.create_index([('rand', '2d')])
def __init__(self, path):
# Load data
self.path = path
self.collections = data.load_data_file(path)
# Initialize the menu
self.widget = urwid.Padding([], left = 2, right = 2)
self.top = urwid.Overlay(self.widget,
urwid.SolidFill(u'\N{MEDIUM SHADE}'),
align = 'center', width = ('relative', 60),
valign = 'middle', height = ('relative', 60),
min_width = 20, min_height = 9)
# Enter the main menu
self.main()
def load_data(collection, n=100):
#fixed number of marks
max_i = 10
for j, d in load_data_file(n):
d['i'] = random.randint(0, max_i)
collection.insert(d)
from data import load_data_file from torch_sparse import SparseTensor import torch from torch_geometric.nn import SAGEConv adj = load_data_file() adj_sparse = SparseTensor.from_torch_sparse_coo_tensor(adj) x = torch.randn((5, 10)) sage_conv = SAGEConv(10, 9, True) out = sage_conv(x, adj_sparse) print(out) print(type(out))
def load_data(collection, n=100):
#for each element we will insert the `i` value
for i,d in load_data_file(n):
d['i'] = i
collection.insert( d )
