def forward(ctx, xyz1, xyz2, eps, iters):
batchsize, n, _ = xyz1.size()
_, m, _ = xyz2.size()
assert(n == m)
assert(xyz1.size()[0] == xyz2.size()[0])
assert(n % 1024 == 0)
assert(batchsize <= 512)
xyz1 = xyz1.contiguous().float().cuda()
xyz2 = xyz2.contiguous().float().cuda()
dist = torch.zeros(batchsize, n, device='cuda').contiguous()
assignment = torch.zeros(batchsize, n, device='cuda', dtype=torch.int32).contiguous() - 1
assignment_inv = torch.zeros(batchsize, m, device='cuda', dtype=torch.int32).contiguous() - 1
price = torch.zeros(batchsize, m, device='cuda').contiguous()
bid = torch.zeros(batchsize, n, device='cuda', dtype=torch.int32).contiguous()
bid_increments = torch.zeros(batchsize, n, device='cuda').contiguous()
max_increments = torch.zeros(batchsize, m, device='cuda').contiguous()
unass_idx = torch.zeros(batchsize * n, device='cuda', dtype=torch.int32).contiguous()
max_idx = torch.zeros(batchsize * m, device='cuda', dtype=torch.int32).contiguous()
unass_cnt = torch.zeros(512, dtype=torch.int32, device='cuda').contiguous()
unass_cnt_sum = torch.zeros(512, dtype=torch.int32, device='cuda').contiguous()
cnt_tmp = torch.zeros(512, dtype=torch.int32, device='cuda').contiguous()
emd.forward(xyz1, xyz2, dist, assignment, price, assignment_inv, bid, bid_increments, max_increments, unass_idx, unass_cnt, unass_cnt_sum, cnt_tmp, max_idx, eps, iters)
ctx.save_for_backward(xyz1, xyz2, assignment)
return dist, assignment
def forward(ctx, xyz1, xyz2):
batchsize, n, _ = xyz1.size()
_, m, _ = xyz2.size()
match = torch.zeros(batchsize, n, m).cuda()
cost = torch.zeros(batchsize, ).cuda()
temp = torch.zeros(batchsize, 2 * (m + n)).cuda()
emd.forward(xyz1, xyz2, match, cost, temp)
ctx.save_for_backward(xyz1, xyz2, match)
return cost
