def create_split():
'''
Create split following the original partition
'''
split_list = io.load_str_list(ca_root + 'Eval/list_eval_partition.txt')[2:]
split = {'train': [], 'val': [], 'test': []}
samples = io.load_json(design_root + 'Label/ca_samples.json')
img2id = {
s['img_path_org'][s['img_path_org'].find('img')::]: s_id
for s_id, s in samples.iteritems()
}
for s in split_list:
img_path, status = s.split()
s_id = img2id[img_path]
split[status].append(s_id)
io.mkdir_if_missing(design_root + 'Split')
io.save_json(split, design_root + 'Split/ca_split.json')
print('create split')
for status in ['train', 'val', 'test']:
print('%s: %d' % (status, len(split[status])))
split_trainval = {
'train': split['train'] + split['val'],
'test': split['test']
}
io.save_json(split_trainval, design_root + 'Split/ca_split_trainval.json')
def create_cloth_edge_map():
'''
create edge map that only contains cloth edge (inside the cloth mask)
'''
# config
mask_dilate = 5
seg_dir = design_root + 'Img/seg_ca_syn_256/'
edge_dir = design_root + 'Img/edge_ca_256/'
output_dir = design_root + 'Img/edge_ca_256_cloth/'
io.mkdir_if_missing(output_dir)
split = io.load_json(design_root +
'Split/ca_gan_split_trainval_upper.json')
id_list = split['train'] + split['test']
for i, s_id in enumerate(id_list):
print('%d/%d' % (i, len(id_list)))
seg_map = image.imread(seg_dir + s_id + '.bmp', 'grayscale')
edge_map = image.imread(edge_dir + s_id + '.jpg', 'grayscale')
assert seg_map.shape == edge_map.shape
mask = ((seg_map == 3) | (seg_map == 4)).astype(np.uint8)
mask = cv2.dilate(mask, kernel=np.ones((mask_dilate, mask_dilate)))
edge_map_cloth = edge_map * mask
image.imwrite(edge_map_cloth, output_dir + s_id + '.jpg')
def visualize_samples():
num_sample = 10
dir_out = 'temp/attr_example'
io.mkdir_if_missing(dir_out)
samples = io.load_json(design_root + 'Label/ca_samples.json')
attr_label = io.load_data(design_root + 'Label/ca_attr_label.pkl')
attr_entry = io.load_json(design_root + 'Label/attr_entry.json')
id_set = set(samples.keys())
for i, att in enumerate(attr_entry):
print('attribute %d / %d: %s' % (i, len(attr_entry), att['entry']))
dir_att = os.path.join(dir_out, att['entry'])
io.mkdir_if_missing(dir_att)
pos_id_list = [
s_id for s_id, label in attr_label.iteritems() if label[i] == 1
]
np.random.shuffle(pos_id_list)
for s_id in pos_id_list[0:num_sample]:
fn_src = samples[s_id]['img_path']
fn_tar = os.path.join(dir_att, 'pos_' + s_id + '.jpg')
shutil.copyfile(fn_src, fn_tar)
neg_id_list = list(id_set - set(pos_id_list))
np.random.shuffle(neg_id_list)
for s_id in neg_id_list[0:num_sample]:
fn_src = samples[s_id]['img_path']
fn_tar = os.path.join(dir_att, 'neg_' + s_id + '.jpg')
shutil.copyfile(fn_src, fn_tar)
def create_silhouette():
# DeepFashion
#smpl_pred_dir = 'datasets/DF_Pose/3d/hmr_dfm_v2/pred/'
#output_dir = 'datasets/DF_Pose/Img/silhouette24/'
#image_split = io.load_json('datasets/DF_Pose/Label/image_split_dfm.json')
# Market-1501
smpl_pred_dir = 'datasets/market1501/3d/hmr/pred/'
output_dir = 'datasets/market1501/Images/silhouette24/'
image_split = io.load_json('datasets/market1501/Label/image_split.json')
faces = np.load('scripts/3d/smpl_faces.npy')
vert2part = io.load_json('scripts/3d/smpl_vert_to_bodypart.json')
def _func(face_id):
if face_id == 4294967295:
return 0
else:
verts = faces[face_id]
part_id = vert2part[verts[0]] + 1
return part_id
_vfunc = np.vectorize(_func)
io.mkdir_if_missing(output_dir)
id_list = image_split['train'] + image_split['test']
for sid in tqdm.tqdm(id_list):
pred = io.load_data(smpl_pred_dir + '%s.pkl' % sid)
vis = pred['visibility']
silh = _vfunc(vis).astype(np.uint8)
silh = cv2.medianBlur(silh, 5)
imageio.imwrite(output_dir + '%s.bmp' % sid, silh)
def visualize_image_matrix(self,
imgs,
imgs_title=None,
label='default',
vis_dir='vis'):
'''
Input:
imgs (tensor): image matrix, tensor of size n_row*n_col*C*H*W
imgs_title (tensor): title images, tensor of size n*C*H*W (must have n==n_row==n_col)
label (str): output filename
'''
vis_dir = os.path.join('checkpoints', self.opt.id, vis_dir)
io.mkdir_if_missing(vis_dir)
n_row, n_col, c, h, w = imgs.size()
if imgs_title is not None:
assert imgs_title.size(0) == n_row == n_col
# insert title images at the head of each row
imgs = torch.cat((imgs_title.view(n_row, 1, c, h, w), imgs), 1)
# add a title row
img_blank = torch.zeros([1] + list(imgs_title.size()[1::]))
imgs_title = torch.cat((img_blank, imgs_title), 0)
imgs = torch.cat((imgs_title.view(1, n_col + 1, c, h, w), imgs), 0)
n_col += 1
n_row += 1
imgs = imgs.view(n_row * n_col, c, h, w)
fn_img = os.path.join(vis_dir, label + '.jpg')
torchvision.utils.save_image(imgs, fn_img, nrow=n_col, normalize=True)
def keypoint_guided_tps():
num_sample = 64
pair_list = io.load_json(
'datasets/DF_Pose/Label/pair_split.json')['test'][0:num_sample]
pose_label = io.load_data('datasets/DF_Pose/Label/pose_label.pkl')
image_dir = 'datasets/DF_Pose/Img/img_df/'
seg_dir = 'datasets/DF_Pose/Img/seg-lip_df_revised/'
output_dir = 'temp/patch_matching/output/tps_keypoint/'
io.mkdir_if_missing(output_dir)
tps = cv2.createThinPlateSplineShapeTransformer()
for i, (id_1, id_2) in enumerate(tqdm.tqdm(pair_list)):
kp_1 = np.array(pose_label[id_1][1:14],
dtype=np.float64).reshape(1, -1, 2)
kp_2 = np.array(pose_label[id_2][1:14],
dtype=np.float64).reshape(1, -1, 2)
kp_matches = []
for j in range(kp_1.shape[1]):
if (kp_1[0, j] >= 0).all() and (kp_2[0, j] >= 0).all():
kp_matches.append(cv2.DMatch(j, j, 0))
if len(kp_matches) == 0:
continue
tps.estimateTransformation(kp_2, kp_1, kp_matches)
img_1 = cv2.imread(image_dir + id_1 + '.jpg')
img_2 = cv2.imread(image_dir + id_2 + '.jpg')
img_w = tps.warpImage(img_1)
seg = cv2.imread(seg_dir + id_2 + '.bmp', cv2.IMREAD_GRAYSCALE)
mask = ((seg == 3) | (seg == 7)).astype(img_w.dtype)[:, :, np.newaxis]
img_out = img_w * mask + img_2 * (1 - mask)
cv2.imwrite(output_dir + '%d_%s_%s.jpg' % (i, id_1, id_2), img_out)
cv2.imwrite(output_dir + 'w%d_%s_%s.jpg' % (i, id_1, id_2), img_w)
def test_affine_augmentation():
img = image.imread(
'datasets/DeepFashion/Fashion_design/Img/img_ca_256/ca_9.jpg')
assert img is not None
output_dir = 'temp/affine_augmentation'
io.mkdir_if_missing(output_dir)
# config
scale = [0.05, 0.1, 0.15]
num_per_scale = 10
w, h = img.shape[1], img.shape[0]
keypoint_src = np.array([[0, 0], [w, 0], [0, h]], dtype=np.float32)
for s in scale:
for i in range(num_per_scale):
offset = (np.random.rand(3, 2) * 2 - 1) * np.array([w, h]) * s
offset = offset.astype(np.float32)
keypoint_dst = keypoint_src + offset
m = cv2.getAffineTransform(keypoint_src, keypoint_dst)
img_trans = cv2.warpAffine(img,
m,
dsize=(w, h),
flags=cv2.INTER_LINEAR,
borderMode=cv2.BORDER_REPLICATE)
img_trans = img_trans * 0.8 + img * 0.2
image.imwrite(
img_trans, os.path.join(output_dir,
'affine_%f_%d.jpg' % (s, i)))
def create_color_map():
#### test
img = image.imread(
'datasets/DeepFashion/Fashion_design/Img/img_ca_256/ca_9.jpg')
assert img is not None
output_dir = 'temp/color_map_generation_test'
io.mkdir_if_missing(output_dir)
# color map by gaussian blur
kernel_size = 21
for sigma in [1, 2, 5, 10, 20]:
img_blur = cv2.GaussianBlur(img, (kernel_size, kernel_size), sigma)
image.imwrite(
img_blur,
os.path.join(output_dir,
'gaussian_%d_%f.jpg' % (kernel_size, sigma)))
# color map by downsampling
for scale in [2, 4, 8, 16, 32]:
w, h = img.shape[1], img.shape[0]
dw, dh = w // scale, h // scale
img_blur = cv2.resize(cv2.resize(img, (dw, dh),
interpolation=cv2.INTER_LINEAR),
(w, h),
interpolation=cv2.INTER_LINEAR)
image.imwrite(img_blur,
os.path.join(output_dir, 'downsample_%d.jpg') % scale)
def visualize_seg_map():
num_sample = 1000
output_dir = 'temp/seg_map'
io.mkdir_if_missing(output_dir)
samples = io.load_json(design_root + 'Label/ca_samples.json')
split = io.load_json(design_root + 'Split/ca_gan_split_trainval.json')
id_list = split['train'] + split['test']
id_list = [s_id for s_id in id_list if samples[s_id]['cloth_type'] == 3]
seg_dir_list = [
design_root + 'Img/seg_ca_256/', design_root + 'Img/seg_ca_syn_256/'
]
for i, s_id in enumerate(id_list[0:num_sample]):
s = samples[s_id]
img = image.imread(s['img_path'])
imgs = [img]
for seg_dir in seg_dir_list:
seg = image.imread(seg_dir + s_id + '.bmp') * 20
mask = img * (seg > 0).astype(np.float)
imgs += [seg, mask]
img = image.stitch(imgs, 0)
image.imwrite(img, os.path.join(output_dir, s_id + '.jpg'))
print(i)
def revise_coat_label():
'''
Reivese the segment label of coat(7) and upperbody(3).
'''
import cv2
img_dir = 'datasets/DF_Pose/Img/img_df/'
seg_dir = 'datasets/DF_Pose/Img/seg-lip_df/'
output_dir = 'datasets/DF_Pose/Img/seg-lip_df_revised/'
split = io.load_json('datasets/DF_Pose/Label/split.json')
id_list = split['train'] + split['test']
pid_to_sids = defaultdict(lambda: [])
for sid in id_list:
pid = sid[0:5]
pid_to_sids[pid].append(sid)
print('find %d person ids' % len(pid_to_sids))
n_revised = 0
io.mkdir_if_missing(output_dir)
for i, (pid, sids) in enumerate(pid_to_sids.items()):
seg_0 = cv2.imread(seg_dir + pid + '_1.bmp',
cv2.IMREAD_GRAYSCALE) # try to load frontal image
if (seg_0 is not None) and (7 in seg_0) and (3 in seg_0):
n_revised += 1
img_0 = cv2.imread(img_dir + pid + '_1.jpg')
mask_u = (seg_0 == 3).astype(np.uint8)
mask_c = (seg_0 == 7).astype(np.uint8)
hist_u = cv2.calcHist([img_0], [0, 1, 2], mask_u, [8] * 3,
[0, 256] * 3)
hist_c = cv2.calcHist([img_0], [0, 1, 2], mask_c, [8] * 3,
[0, 256] * 3)
for sid in sids:
if sid == pid + '_1':
shutil.copyfile(seg_dir + sid + '.bmp',
output_dir + sid + '.bmp')
else:
seg_i = cv2.imread(seg_dir + sid + '.bmp',
cv2.IMREAD_GRAYSCALE)
img_i = cv2.imread(img_dir + sid + '.jpg')
mask_u_i = (seg_i == 3).astype(np.uint8)
mask_c_i = (seg_i == 7).astype(np.uint8)
for mask_i in [mask_u_i, mask_c_i]:
if mask_i.any():
hist_i = cv2.calcHist([img_i], [0, 1, 2], mask_i,
[8] * 3, [0, 256] * 3)
if cv2.compareHist(
hist_i, hist_u,
cv2.HISTCMP_CORREL) < cv2.compareHist(
hist_i, hist_c, cv2.HISTCMP_CORREL):
seg_i[mask_i] = 3
else:
seg_i[mask_i] = 7
cv2.imwrite(output_dir + sid + '.bmp', seg_i)
else:
for sid in sids:
shutil.copyfile(seg_dir + sid + '.bmp',
output_dir + sid + '.bmp')
print('%d / %d (%d revised)' % (i, len(pid_to_sids), n_revised))
def visualize_results(self, visuals, filename):
io.mkdir_if_missing(os.path.dirname(filename))
imgs, vis_item_list = merge_visual(visuals)
torchvision.utils.save_image(imgs,
filename,
nrow=len(visuals),
normalize=True)
fn_list = os.path.join(os.path.dirname(filename), 'vis_item_list.txt')
io.save_str_list(vis_item_list, fn_list)
def visualize_image(self, epoch, subset, visuals):
opt = self.opt
vis_dir = os.path.join('checkpoints', opt.id, 'vis')
io.mkdir_if_missing(vis_dir)
print('[%s] visualizing %s images' % (opt.id, subset))
# post-process
if 'seg_map' in visuals:
visuals['seg_map'] = self._seg_map_to_img(visuals['seg_map'])
if 'landmark_heatmap' in visuals:
visuals['landmark_heatmap'] = visuals['landmark_heatmap'].max(
dim=1, keepdim=True)[0].expand_as(visuals['img_real'])
if 'edge_map' in visuals:
visuals['edge_map'] = visuals['edge_map'].expand_as(
visuals['img_real'])
if 'seg_mask_aug' in visuals:
visuals['seg_mask_aug'] = visuals['seg_mask_aug'][:, 1::].sum(
dim=1, keepdim=True).expand_as(visuals['img_real'])
if 'edge_map_aug' in visuals:
visuals['edge_map_aug'] = visuals['edge_map_aug'].expand_as(
visuals['img_real'])
if 'color_map' in visuals and visuals['color_map'].size(1) == 6:
visuals['color_map'] = visuals['color_map'][:, 0:3] + visuals[
'color_map'][:, 3:6]
if 'color_map_aug' in visuals and visuals['color_map_aug'].size(
1) == 6:
visuals['color_map_aug'] = visuals[
'color_map_aug'][:, 0:3] + visuals['color_map_aug'][:, 3:6]
# display
num_vis = min(opt.max_n_vis, visuals['img_real'].size(0))
item_list = [
'img_real',
'img_real_raw',
'img_fake',
'img_fake_raw',
'seg_map',
'edge_map',
'color_map',
'landmark_heatmap',
'seg_mask_aug',
'edge_map_aug',
'color_map_aug',
]
imgs = [
visuals[item_name] for item_name in item_list
if item_name in visuals
]
imgs = torch.stack(imgs, dim=1)[0:num_vis]
imgs = imgs.view(
imgs.size(0) * imgs.size(1), imgs.size(2), imgs.size(3),
imgs.size(4))
nrow = int(imgs.size(0) / num_vis)
fn_img = os.path.join(vis_dir, '%s_epoch%d.jpg' % (subset, epoch))
torchvision.utils.save_image(imgs, fn_img, nrow=nrow, normalize=True)
def resize_and_pad():
'''
resize the image that its longer side equals to new_size. Then pad the image to have the size [new_size, new_size]
create new pose label at the same time
'''
# config
new_size = 256
img_root = zalando_root + 'Img/img_zalando/'
output_dir = zalando_root + 'Img/img_zalando_%d/' % new_size
split = io.load_json(zalando_root + 'Split/zalando_split.json')
pose_label = io.load_data(zalando_root + 'Label/zalando_pose_label.pkl')
io.mkdir_if_missing(output_dir)
id_list = split['train'] + split['test']
# id_list = id_list[0:10]
new_pose_label = {}
for i, s_id in enumerate(id_list):
print('%d / %d' % (i, len(id_list)))
# resize image
img = cv2.imread(img_root + s_id + '_0.jpg')
w, h = img.shape[1], img.shape[0]
if w < h:
top = 0
bottom = 0
left = (h-w)//2
right = h-w-left
ratio = new_size/h
else:
top = (w-h)//2
bottom = w-h-top
left = 0
right = 0
ratio = new_size/w
img = cv2.copyMakeBorder(img, top, bottom, left, right, borderType=cv2.BORDER_REPLICATE)
img = cv2.resize(img, dsize=(new_size, new_size), interpolation=cv2.INTER_LINEAR)
cv2.imwrite(output_dir + s_id + '_0.jpg', img)
# resize clothing image
img1 = cv2.imread(img_root + s_id + '_1.jpg')
if not (img1.shape[0] == h and img1.shape[1] == w):
img1 = cv2.resize(img1, dsize=(w,h))
img1 = cv2.copyMakeBorder(img1, top, bottom, left, right, borderType=cv2.BORDER_REPLICATE)
img1 = cv2.resize(img1, dsize=(new_size, new_size), interpolation=cv2.INTER_LINEAR)
cv2.imwrite(output_dir + s_id + '_1.jpg', img1)
# modify pose label
pose = pose_label[s_id]
new_pose = [[(p[0]+left)*ratio, (p[1]+top)*ratio] if p != [-1,-1] else [-1,-1] for p in pose]
new_pose_label[s_id] = new_pose
io.save_data(new_pose_label, zalando_root + 'Label/zalando_pose_label_%d.pkl' % new_size)
def save(self, fn=None):
if self.opt is None:
raise Exception("parse options before saving!")
if fn is None:
expr_dir = os.path.join('checkpoints', self.opt.id)
io.mkdir_if_missing(expr_dir)
if self.opt.is_train:
fn = os.path.join(expr_dir, 'train_opt.json')
else:
fn = os.path.join(expr_dir, 'test_opt.json')
io.save_json(vars(self.opt), fn)
def show_patch():
from options.pose_transfer_options import TrainPoseTransferOptions
from data.data_loader import CreateDataLoader
import imageio
import cv2
opt = TrainPoseTransferOptions().parse()
# output_dir = 'temp/visualize_patch/%d/' % opt.patch_size
output_dir = 'temp/visualize_patch/test/'
io.mkdir_if_missing(output_dir)
loader = iter(CreateDataLoader(opt, 'test'))
model = TwoStagePoseTransferModel()
model.initialize(opt)
data = next(loader)
model.set_input(data)
patch_1 = model.get_patch(model.input['img_1'], model.input['joint_c_1'],
opt.patch_size, opt.patch_indices)
patch_2 = model.get_patch(model.input['img_2'], model.input['joint_c_2'],
opt.patch_size, opt.patch_indices)
images = [model.input['img_1'], model.input['img_2']]
patches = [patch_1, patch_2]
joints = [model.input['joint_c_1'], model.input['joint_c_2']]
id_list = model.input['id']
def _tensor_to_numpy(img_t):
img = img_t.cpu().detach().numpy().transpose(1, 2, 0)
img = (img * 127.5 + 127.5).clip(0, 255).astype(np.uint8)
return img
for idx in range(opt.batch_size):
for i in range(2):
fn_i = output_dir + '%d_%d.jpg' % (idx, i)
img = _tensor_to_numpy(images[i][idx])
for j, joint_idx in enumerate(opt.patch_indices):
fn_p = output_dir + '%d_%d_%d.jpg' % (idx, i, joint_idx)
p = _tensor_to_numpy(patches[i][idx, j])
imageio.imwrite(fn_p, p)
x_c, y_c = joints[i][idx, joint_idx]
if x_c > 0 and y_c > 0:
x_1, y_1 = x_c - opt.patch_size // 2, y_c - opt.patch_size // 2
x_2, y_2 = x_c + opt.patch_size // 2, y_c + opt.patch_size // 2
cv2.rectangle(img, (x_1, y_1), (x_2, y_2),
color=(0, 255, 0))
cv2.putText(img,
str(joint_idx).encode('ascii',
'replace'), (x_c, y_c),
cv2.FONT_HERSHEY_SIMPLEX, 0.3, (0, 255, 0))
imageio.imwrite(fn_i, img)
def create_inner_edge_map():
'''
extract the edges inside the clothing regions
'''
# config
kernel_size = 7
threshold = 0
split = io.load_json(design_root + 'Split/ca_gan_split_trainval.json')
id_list = split['train'] + split['test']
edge_root = design_root + 'Img/edge_ca_256'
seg_root = design_root + 'Img/seg_ca_256'
output_dir = design_root + 'Img/edge_ca_256_inner'
io.mkdir_if_missing(output_dir)
kernel = np.zeros((kernel_size, kernel_size), np.uint8)
k = (kernel_size - 1) / 2
for i in range(kernel_size):
for j in range(kernel_size):
if np.abs(i - k) + np.abs(j - k) <= k:
kernel[i, j] = 1
for i, s_id in enumerate(id_list):
edge = image.imread(os.path.join(edge_root, s_id + '.jpg'),
'grayscale')
seg = image.imread(os.path.join(seg_root, s_id + '.bmp'), 'grayscale')
mask_upper = cv2.erode((seg == 3).astype(np.uint8), kernel)
mask_lower = cv2.erode((seg == 4).astype(np.uint8), kernel)
mask = mask_upper | mask_lower
edge_inner = edge * mask
edge_inner = (edge_inner >= threshold).astype(np.uint8) * edge_inner
image.imwrite(edge_inner, os.path.join(output_dir, s_id + '.jpg'))
print('extracting inner edge %d / %d' % (i, len(id_list)))
# create labels
edge_paths = {
s_id: os.path.join(output_dir, s_id + '.jpg')
for s_id in id_list
}
split_debug = io.load_json(design_root + 'Split/debugca_gan_split.json')
edge_paths_debug = {
s_id: p
for s_id, p in edge_paths.iteritems()
if s_id in split_debug['train'] + split_debug['test']
}
io.save_json(edge_paths, design_root + 'Label/ca_edge_inner_paths.json')
io.save_json(edge_paths_debug,
design_root + 'Label/debugca_edge_inner_paths.json')
def extract_feature(opt, save_feat=True):
fn_feat = os.path.join(
os.path.join('checkpoints', opt.id, 'feat',
'%s.pkl' % opt.which_epoch))
if os.path.isfile(fn_feat):
print('loading feature from %s' % fn_feat)
feat_data = io.load_data(fn_feat)
# feat_data['feat_train']
# feat_data['feat_test']
# feat_data['id_list_train']
# feat_data['id_list_test']
else:
# create model
model = AttributeEncoder()
model.initialize(opt)
model.eval()
feat_data = {
'feat_train': [],
'feat_test': [],
'id_list_train': [],
'id_list_test': []
}
for split in ['train', 'test']:
loader = CreateDataLoader(opt, split=split)
for i, data in enumerate(loader):
model.set_input(data)
model.extract_feat()
feat_data['feat_%s' %
split].append(model.output['feat'].data.cpu().numpy(
)) # size: batch_size * feat_size
feat_data['id_list_%s' %
split] += data['id'] # list of length batch_size
print('\r[%s] extract feature from %s samples %d/%d' %
(opt.id, split, i, len(loader)),
end='')
print('\n')
feat_data['feat_%s' % split] = np.vstack(feat_data['feat_%s' %
split])
if save_feat:
io.mkdir_if_missing(os.path.join('checkpoints', opt.id, 'feat'))
io.save_data(feat_data, fn_feat)
return feat_data
def create_split():
'''
create split file. follow the partition used in VITON paper
'''
train_pairs = io.load_str_list(zalando_root + 'Source/viton_train_pairs.txt')
test_piars = io.load_str_list(zalando_root + 'Source/viton_test_pairs.txt')
split = {}
for subset, pairs in [('train', train_pairs), ('test', test_piars)]:
id_list = [p.split()[0][0:6] for p in pairs]
split[subset] = id_list
split['debug'] = split['train'][0:32]
io.mkdir_if_missing(zalando_root + 'Split')
io.save_json(split, zalando_root + 'Split/zalando_split.json')
def search_image(query_fn_list, gallery_fn_list, output_dir, method='cos'):
num_cand = 20;
cache_image = True
if method == 'cos':
func_similarity = similarity_cos
if cache_image:
img_g_dict = dict()
io.mkdir_if_missing(output_dir)
result = []
for idx,fn_q in enumerate(query_fn_list):
print('searching sample %d/%d' % (idx, len(query_fn_list)))
io.mkdir_if_missing(output_dir+'/%d/'%idx)
img_q = imageio.imread(fn_q)
cand_list = [(None, None, -1)]
for fn_g in tqdm.tqdm(gallery_fn_list):
if cache_image:
if fn_g in img_g_dict:
img_g = img_g_dict[fn_g]
else:
img_g = imageio.imread(fn_g)
img_g_dict[fn_g] = img_g
else:
img_g = imageio.imread(fn_g)
score = func_similarity(img_q, img_g)
i_insert = -1
for i in range(len(cand_list)):
if score > cand_list[i][2]:
i_insert = i
break
if i_insert >= 0:
cand_list.insert(i_insert, (fn_g, img_g, score))
if len(cand_list) > num_cand:
cand_list = cand_list[0:num_cand]
imageio.imwrite(output_dir+'/%d/query.jpg'%idx, img_q)
for i, (fn_g, img_g, score) in enumerate(cand_list):
if fn_g:
imageio.imwrite(output_dir + '/%d/cand_%d.jpg'%(idx, i), img_g)
output_info = [fn_q]
output_info += ['%d %f %s' % (i, score, fn) for i, (fn, _, score) in enumerate(cand_list)]
io.save_str_list(output_info, output_dir + '/%d/result.txt'%idx)
result.append('%d %s %s' % (idx, fn_q, cand_list[0][0]))
io.save_str_list(result, output_dir+'result.txt')
def calc_correspondence_from_smpl():
'''
Compute pixel-wise correspondence between image pair by SMPL model (http://smpl.is.tue.mpg.de/).
The SMPL fit result is predicted by HMR(https://github.com/akanazawa/hmr), with following format:
pred = {
'id': sid,
'theta': theta,
'proc_param': proc_param,
'verts2d': verts2d,
'verts_z': verts_z,
'visibility': visibility, # a map with same size of img, each pixel is its corresponding SMPL face index (or 4294967295 if it's corresponding to no face)
}
See '/data2/ynli/human3d/hmr/run_hmr.py' for more details
'''
# num_pair = 64
# pair_split_fn = 'datasets/DF_Pose/Label/pair_split.json'
# hmr_pred_dir = 'temp/3d_hmr/hmr_df_openpose/pred/'
# output_dir = 'temp/3d_hmr/corr/'
num_pair = -1
pair_split_fn = 'datasets/DF_Pose/Label/pair_split_dfm.json'
hmr_pred_dir = 'datasets/DF_Pose/3d/hmr_dfm/pred/'
output_dir = 'datasets/DF_Pose/3d/hmr_dfm/corr/'
io.mkdir_if_missing(output_dir)
# load pair ids
pairs = io.load_json(pair_split_fn)
pair_list = pairs['test'] + pairs['train']
if num_pair > 0:
pair_list = pair_list[:num_pair]
for id_1, id_2 in tqdm.tqdm(pair_list):
pred_1 = io.load_data(hmr_pred_dir + id_1 + '.pkl')
pred_2 = io.load_data(hmr_pred_dir + id_2 + '.pkl')
corr_2to1, vis_mask_2 = calc_correspondence_from_smpl_internal(
pred_2, pred_1)
flow_util.write_corr(output_dir + '%s_%s.corr' % (id_2, id_1),
corr_2to1, vis_mask_2)
corr_1to2, vis_mask_1 = calc_correspondence_from_smpl_internal(
pred_1, pred_2)
flow_util.write_corr(output_dir + '%s_%s.corr' % (id_1, id_2),
corr_1to2, vis_mask_1)
def pad_image_for_segmentation():
'''
resize and padding image for segmentation (using fashionGAN code)
Todo: add inshop version
'''
sz_tar = 256
output_dir = 'datasets/DeepFashion/Fashion_design/Img/img_ca_pad'
io.mkdir_if_missing(output_dir)
samples = io.load_json(design_root + 'Label/ca_samples.json')
split = io.load_json(design_root + 'Split/ca_gan_split_trainval.json')
id_list = split['train'] + split['test']
# update landmark and bbox
lm_label = io.load_data(design_root + 'Label/ca_landmark_label.pkl')
bbox_label = io.load_data(design_root + 'Label/ca_bbox_label.pkl')
lm_label_pad = {}
bbox_label_pad = {}
io.save_str_list(id_list, os.path.join(output_dir, 'img_ca_pad.txt'))
for i, s_id in enumerate(id_list):
img_org = image.imread(samples[s_id]['img_path_org'])
h, w = img_org.shape[0:2]
if h > w:
img = image.resize(img_org, (-1, sz_tar))
scale = 1. * sz_tar / h
else:
img = image.resize(img_org, (sz_tar, -1))
scale = 1. * sz_tar / w
# img = image.pad_square(img, sz_tar, padding_value = 255, mode = 'lefttop')
# image.imwrite(img, os.path.join(output_dir, s_id + '.jpg'))
bbox_label_pad[s_id] = [c * scale for c in bbox_label[s_id]]
lm_label_pad[s_id] = []
for x, y, v in lm_label[s_id]:
lm_label_pad[s_id].append([x * scale, y * scale, v])
print('padding image %d / %d' % (i, len(id_list)))
io.save_data(lm_label_pad,
design_root + 'Label/ca_landmark_label_pad_%d.pkl' % sz_tar)
io.save_data(bbox_label_pad,
design_root + 'Label/ca_bbox_label_pad_%d.pkl' % sz_tar)
def visualize_image(self, epoch, subset, visuals):
opt = self.opt
vis_dir = os.path.join('checkpoints', opt.id, 'vis')
io.mkdir_if_missing(vis_dir)
print('[%s] visualizing %s images' % (opt.id, subset))
imgs, vis_list = self.merge_visual(visuals,
kword_params={
'shape_with_face':
'shape_with_face' in opt
and opt.shape_with_face
})
fn_img = os.path.join(vis_dir, '%s_epoch%s.jpg' % (subset, epoch))
torchvision.utils.save_image(imgs,
fn_img,
nrow=len(visuals),
normalize=True)
io.save_str_list(vis_list, os.path.join(vis_dir, 'vis_name_list.txt'))
def prepro_image(img_dir, output_dir):
h_out, w_out = [256, 256]
io.mkdir_if_missing(output_dir)
for fn in tqdm.tqdm(os.listdir(img_dir)):
img_org = cv2.imread(img_dir+fn)
h, w = img_org.shape[0:2]
if h/h_out > w/w_out:
w1 = int(w/h*h_out)
img_rsz = cv2.resize(img_org, (w1, h_out))
img_out = np.ones((h_out, w_out, 3), dtype=np.uint8)*255
img_out[:,((w_out-w1)//2):((w_out-w1)//2+w1),:] = img_rsz
else:
h1 = int(h/w*w_out)
img_rsz = cv2.resize(img_org, (w_out, h1))
img_out = np.ones((h_out, w_out, 3), dtype=np.uint8)*255
img_out[((h_out-h1)//2):((h_out-h1)//2+h1),:,:] = img_rsz
cv2.imwrite(output_dir+fn, img_out)
def merge_silhouette():
# for DeepFashion
#image_split = io.load_json('datasets/DF_Pose/Label/image_split_dfm.json')
#input_dir = 'datasets/DF_Pose/Img/silhouette24/'
#output_dir = 'datasets/DF_Pose/Img/silhouette6/'
# for Market-1501
image_split = io.load_json('datasets/market1501/Label/image_split.json')
input_dir = 'datasets/market1501/Images/silhouette24/'
output_dir = 'datasets/market1501/Images/silhouette6/'
id_list = image_split['train'] + image_split['test']
io.mkdir_if_missing(output_dir)
head = {13, 16}
torso = {1, 4, 7, 10}
larm = {14, 17, 19, 21, 23}
rarm = {15, 18, 20, 22, 24}
lleg = {2, 5, 8, 11}
rleg = {3, 6, 9, 12}
def _func_merge(x):
if x == 0:
return 0
elif x in head:
return 1
elif x in torso:
return 2
elif x in larm:
return 3
elif x in rarm:
return 4
elif x in lleg:
return 5
elif x in rleg:
return 6
_vfunc_merge = np.vectorize(_func_merge, otypes=[np.uint8])
for sid in tqdm.tqdm(id_list):
silh = imageio.imread(input_dir + '%s.bmp' % sid)
silhm = _vfunc_merge(silh)
imageio.imwrite(output_dir + '%s.bmp' % sid, silhm)
def create_seg_input():
# samples = io.load_json(root + 'Anno/samples_highres.json')
# in_dir = root + 'Img/img1_highres/'
samples = io.load_json(root + 'Label/samples.json')
in_dir = root + 'Img/img1/'
out_dir = root + 'Img/input/'
io.mkdir_if_missing(out_dir)
for img_id, s in samples.iteritems():
fn_src = in_dir + s['img_path']
fn_tar = out_dir + '%s.jpg' % img_id
shutil.copyfile(fn_src, fn_tar)
print(img_id)
def visualize_seg():
'''
visualize segmentation
'''
num_vis = 100
img_root = zalando_root + 'Img/img_zalando_256/'
seg_root = zalando_root + 'Img/seg_zalando_256/'
output_dir = 'temp/zalando_seg_vis/'
io.mkdir_if_missing(output_dir)
split = io.load_json(zalando_root + 'Split/zalando_split.json')
id_list = split['train'] + split['test']
for s_id in id_list[0:num_vis]:
img = cv2.imread(img_root + s_id + '_0.jpg')
seg = cv2.imread(seg_root + s_id + '_0.bmp')
seg = seg * 20
img = np.concatenate((img, seg), axis = 1)
cv2.imwrite(output_dir + s_id + '.jpg', img)
def parse(self,
ord_str=None,
save_to_file=True,
display=True,
set_gpu=True):
if not self.initialized:
self.initialize()
if ord_str is None:
self.opt = self.parser.parse_args()
else:
ord_list = ord_str.split()
self.opt = self.parser.parse_args(ord_list)
self.auto_set()
if len(self.opt.gpu_ids) > 0 and set_gpu:
os.environ['CUDA_VISIBLE_DEVICES'] = ','.join(
[str(i) for i in self.opt.gpu_ids])
self.opt.gpu_ids = range(len(self.opt.gpu_ids))
torch.cuda.set_device(0)
args = vars(self.opt)
# display options
if display:
print('------------ Options -------------')
for k, v in sorted(args.items()):
print('%s: %s' % (str(k), str(v)))
print('-------------- End ----------------')
# save to disk
if save_to_file:
expr_dir = os.path.join('checkpoints', self.opt.id)
io.mkdir_if_missing(expr_dir)
if self.opt.is_train:
fn_out = os.path.join(expr_dir, 'train_opt.json')
else:
fn_out = os.path.join(expr_dir, 'test_opt.json')
io.save_json(args, fn_out)
return self.opt
def create_cloth_edge_map():
'''
extract edges inside the cloth region
'''
mask_dilate = 5
split = io.load_json(zalando_root + 'Split/zalando_split.json')
id_list = split['train'] + split['test']
edge_dir = zalando_root + 'Img/edge_zalando_256/'
seg_dir = zalando_root + 'Img/seg_zalando_256/'
output_dir = zalando_root + 'Img/edge_zalando_256_cloth/'
io.mkdir_if_missing(output_dir)
for i, s_id in enumerate(id_list):
print('%d/%d' % (i, len(id_list)))
edge = cv2.imread(edge_dir + s_id + '.jpg', cv2.IMREAD_GRAYSCALE)
seg = cv2.imread(seg_dir + s_id + '.bmp', cv2.IMREAD_GRAYSCALE)
assert edge.shape == seg.shape
mask = ((seg==3) | (seg==4)).astype(np.uint8)
mask = cv2.dilate(mask, kernel = np.ones((mask_dilate, mask_dilate)))
edge_cloth = edge * mask
cv2.imwrite(output_dir + s_id + '.jpg', edge_cloth)
def visualize_image_matrix(self,
imgs,
imgs_title_top=None,
imgs_title_left=None,
label='default',
vis_dir='vis'):
'''
Input:
imgs (tensor): image matrix, tensor of size n_row*n_col*C*H*W
imgs_title_top (tensor): top title images, tensor of size n_col*C*H*W
imgs_title_left (tensor): left title images, tensor of size n_row*C*H*W
label (str): output filename
'''
vis_dir = os.path.join('checkpoints', self.opt.id, vis_dir)
io.mkdir_if_missing(vis_dir)
n_row, n_col, c, h, w = imgs.size()
if imgs_title_top is not None:
assert imgs_title_top.size(0) == n_col
imgs = torch.cat((imgs_title_top.view(1, n_col, c, h, w), imgs), 0)
n_row += 1
if imgs_title_left is not None:
assert imgs_title_left.size(0) in {n_row, n_row - 1}
if imgs_title_left.size(0) == n_row - 1:
img_blank = torch.zeros([1] +
list(imgs_title_left.size()[1::]))
imgs_title_left = torch.cat((img_blank, imgs_title_left), 0)
imgs = torch.cat((imgs_title_left.view(n_row, 1, c, h, w), imgs),
1)
n_col += 1
imgs = imgs.view(n_row * n_col, c, h, w)
fn_img = os.path.join(vis_dir, label + '.jpg')
torchvision.utils.save_image(imgs, fn_img, nrow=n_col, normalize=True)
def visualize_pose():
'''
visualize pose label
'''
num_vis = 10
# img_root = zalando_root + 'Img/img_zalando/'
# pose_label = io.load_data(zalando_root + 'Label/zalando_pose_label.pkl')
img_root = zalando_root + 'Img/img_zalando_256/'
pose_label = io.load_data(zalando_root + 'Label/zalando_pose_label_256.pkl')
output_dir = 'temp/zalando_pose_vis/'
io.mkdir_if_missing(output_dir)
for i, (s_id, pose) in enumerate(pose_label.items()[0:num_vis]):
print('%d / %d' % (i, num_vis))
img = cv2.imread(img_root + s_id + '_0.jpg')
assert img is not None
for p in pose:
if p[0] != -1:
c = (int(p[0]), int(p[1]))
cv2.circle(img, center=c, radius=5, color=(0,255,0), thickness=-1)
cv2.imwrite(output_dir + s_id + '.jpg', img)