def run():
cnt = 0
for _ in tqdm.trange(len_test_dataset):
# data for sampling
xa_ipt, a_ipt = sess.run(test_next)
b_ipt = np.copy(a_ipt)
for test_att_name in args.test_att_names:
i = args.att_names.index(test_att_name)
b_ipt[..., i] = 1 - b_ipt[..., i]
b_ipt = data.check_attribute_conflict(b_ipt, test_att_name,
args.att_names)
b__ipt = (b_ipt * 2 - 1).astype(np.float32) # !!!
for test_att_name, test_int in zip(args.test_att_names,
args.test_ints):
i = args.att_names.index(test_att_name)
b__ipt[..., i] = b__ipt[..., i] * test_int
x_opt_list = [xa_ipt]
x_opt = sess.run(x, feed_dict={xa: xa_ipt, b_: b__ipt})
x_opt_list.append(x_opt)
sample = np.transpose(x_opt_list, (1, 2, 0, 3, 4))
sample = np.reshape(sample, (sample.shape[0], -1, sample.shape[2] *
sample.shape[3], sample.shape[4]))
for s in sample:
cnt += 1
im.imwrite(s, '%s/%d.jpg' % (save_dir, cnt))
def run():
cnt = 0
for _ in tqdm.trange(len_test_dataset):
# data for sampling
xa_ipt, a_ipt = sess.run(test_iter.get_next())
b_ipt_list = [a_ipt] # the first is for reconstruction
for i in range(n_atts):
tmp = np.array(a_ipt, copy=True)
tmp[:, i] = 1 - tmp[:, i] # inverse attribute
tmp = data.check_attribute_conflict(tmp, args.att_names[i],
args.att_names)
b_ipt_list.append(tmp)
x_opt_list = [xa_ipt]
for i, b_ipt in enumerate(b_ipt_list):
b__ipt = (b_ipt * 2 - 1).astype(np.float32) # !!!
if i > 0: # i == 0 is for reconstruction
b__ipt[..., i - 1] = b__ipt[..., i - 1] * args.test_int
x_opt = sess.run(x, feed_dict={xa: xa_ipt, b_: b__ipt})
x_opt_list.append(x_opt)
sample = np.transpose(x_opt_list, (1, 2, 0, 3, 4))
sample = np.reshape(sample, (sample.shape[0], -1, sample.shape[2] *
sample.shape[3], sample.shape[4]))
for s in sample:
cnt += 1
im.imwrite(s, '%s/%d.jpg' % (save_dir, cnt))
def run():
cnt = 0
for _ in tqdm.trange(len_test_dataset):
# data for sampling
xa_ipt, a_ipt = sess.run(test_iter.get_next())
b_ipt_list = [a_ipt] # the first is for reconstruction
for i in range(n_atts):
tmp = np.array(a_ipt, copy=True)
tmp[:, i] = 1 - tmp[:, i] # inverse attribute
tmp = data.check_attribute_conflict(tmp, args.att_names[i],
args.att_names)
b_ipt_list.append(tmp)
x_opt_list = [xa_ipt]
e_opt_list = [np.full_like(xa_ipt, -1.0)]
ms_opt_list = []
a__ipt = a_ipt * 2 - 1
for i, b_ipt in enumerate(b_ipt_list):
b__ipt = (b_ipt * 2 - 1).astype(np.float32) # !!!
if i > 0: # i == 0 is for reconstruction
b__ipt[..., i - 1] = b__ipt[..., i - 1] * args.test_int
x_opt, e_opt, ms_opt = sess.run([x, e, ms],
feed_dict={
xa: xa_ipt,
a_: a__ipt,
b_: b__ipt
})
x_opt_list.append(x_opt)
e_opt_list.append(e_opt)
ms_opt_list.append(ms_opt)
if args.with_mask:
# resize all masks to the same size
for ms_opt in ms_opt_list: # attribute axis
for i, m_opt in enumerate(ms_opt): # mask level axis
m_opt_resized = []
for m_j_opt in m_opt: # batch axis
m_opt_resized.append(
im.imresize(m_j_opt * 2 - 1,
(args.crop_size, args.crop_size)))
ms_opt[i] = np.concatenate([np.array(m_opt_resized)] *
3,
axis=-1)
ms_opt_list = [np.full_like(ms_opt_list[0], -1.0)
] + ms_opt_list
ms_opt_list = list(
np.transpose(ms_opt_list, (1, 0, 2, 3, 4, 5)))[::-1]
sample_m = np.transpose([x_opt_list, e_opt_list] + ms_opt_list,
(2, 0, 3, 1, 4, 5))
else:
sample_m = np.transpose([x_opt_list], (2, 0, 3, 1, 4, 5))
sample_m = np.reshape(sample_m,
(sample_m.shape[0], -1, sample_m.shape[3] *
sample_m.shape[4], sample_m.shape[5]))
for s in sample_m:
cnt += 1
im.imwrite(s, '%s/%d.jpg' % (save_dir, cnt))
def run():
cnt = 0
for _ in tqdm.trange(len_test_dataset):
# data for sampling
xa_ipt, a_ipt = sess.run(test_iter.get_next())
b_ipt = np.copy(a_ipt)
for test_att_name in args.test_att_names:
i = args.att_names.index(test_att_name)
b_ipt[..., i] = 1 - b_ipt[..., i]
b_ipt = data.check_attribute_conflict(b_ipt, test_att_name, args.att_names)
a__ipt = a_ipt * 2 - 1
b__ipt = (b_ipt * 2 - 1).astype(np.float32) # !!!
for test_att_name, test_int in zip(args.test_att_names, args.test_ints):
i = args.att_names.index(test_att_name)
b__ipt[..., i] = b__ipt[..., i] * test_int
x_opt_list = [xa_ipt]
e_opt_list = [np.full_like(xa_ipt, -1.0)]
ms_opt_list = []
x_opt, e_opt, ms_opt = sess.run([x, e, ms], feed_dict={xa: xa_ipt, a_: a__ipt, b_: b__ipt})
x_opt_list.append(x_opt)
e_opt_list.append(e_opt)
ms_opt_list.append(ms_opt)
if args.with_mask:
# resize all masks to the same size
for ms_opt in ms_opt_list: # attribute axis
for i, m_opt in enumerate(ms_opt): # mask level axis
m_opt_resized = []
for m_j_opt in m_opt: # batch axis
m_opt_resized.append(im.imresize(m_j_opt * 2 - 1, (args.crop_size, args.crop_size)))
ms_opt[i] = np.concatenate([np.array(m_opt_resized)] * 3, axis=-1)
ms_opt_list = [np.full_like(ms_opt_list[0], -1.0)] + ms_opt_list
ms_opt_list = list(np.transpose(ms_opt_list, (1, 0, 2, 3, 4, 5)))[::-1]
sample_m = np.transpose([x_opt_list, e_opt_list] + ms_opt_list, (2, 0, 3, 1, 4, 5))
else:
sample_m = np.transpose([x_opt_list], (2, 0, 3, 1, 4, 5))
sample_m = np.reshape(sample_m, (sample_m.shape[0], -1, sample_m.shape[3] * sample_m.shape[4], sample_m.shape[5]))
for s in sample_m:
cnt += 1
im.imwrite(s, '%s/%d.jpg' % (save_dir, cnt))
for idx, (img_a, att_a) in enumerate(test_dataloader):
if args.num_test is not None and idx == args.num_test:
break
img_a = img_a.cuda() if args.gpu else img_a
att_a = att_a.cuda() if args.gpu else att_a
att_a = att_a.type(torch.float)
att_b_list = [att_a]
if args.by_levels:
for i in range(args.n_attrs):
tmp = att_a.clone()
for j in range(args.n_attrs):
tmp[:, j] = -1
tmp[:, i] = 1
tmp = check_attribute_conflict(tmp, args.attrs[i], args.attrs)
att_b_list.append(tmp)
else:
for i in range(args.n_attrs):
tmp = att_a.clone()
tmp[:, i] = 1 - tmp[:, i]
tmp = check_attribute_conflict(tmp, args.attrs[i], args.attrs)
att_b_list.append(tmp) # a list of lists of attributes (probably).
with torch.no_grad():
samples = [img_a]
for i, att_b in enumerate(att_b_list):
att_b_ = (att_b * 2 - 1) * args.thres_int
if i > 0:
att_b_[..., i - 1] = att_b_[..., i - 1] * args.test_int / args.thres_int
samples.append(attgan.G(img_a, att_b_))
progressbar = Progressbar()
attgan.eval()
for idx, (img_a, att_a) in enumerate(test_dataloader):
if args.num_test is not None and idx == args.num_test:
break
img_a = img_a.cuda() if args.gpu else img_a
att_a = att_a.cuda() if args.gpu else att_a
att_a = att_a.type(torch.float)
att_b = att_a.clone()
for a in args.test_atts:
i = args.attrs.index(a)
att_b[:, i] = 1 - att_b[:, i]
att_b = check_attribute_conflict(att_b, args.attrs[i], args.attrs)
with torch.no_grad():
samples = [img_a]
att_b_ = (att_b * 2 - 1) * args.thres_int
for a, i in zip(args.test_atts, args.test_ints):
att_b_[..., args.attrs.index(a)] = att_b_[
..., args.attrs.index(a)] * i / args.thres_int
samples.append(attgan.G(img_a, att_b_))
samples = torch.cat(samples, dim=3)
if args.custom_img:
out_file = test_dataset.images[idx]
else:
out_file = '{:06d}.jpg'.format(idx + 182638)
vutils.save_image(samples,
join(output_path, out_file),
