def _load_batch_pair_pose(self, dataset):
data_provider = slim.dataset_data_provider.DatasetDataProvider(dataset, common_queue_capacity=32, common_queue_min=8)
image_raw_0, image_raw_1, label, pose_0, pose_1, mask_0, mask_1 = data_provider.get([
'image_raw_0', 'image_raw_1', 'label', 'pose_sparse_r4_0', 'pose_sparse_r4_1', 'pose_mask_r4_0', 'pose_mask_r4_1'])
print("trainer－－_load_batch_pair_pose：")
print(pose_0)
pose_0 = sparse_ops.sparse_tensor_to_dense(pose_0, default_value=0, validate_indices=False)
pose_1 = sparse_ops.sparse_tensor_to_dense(pose_1, default_value=0, validate_indices=False)
image_raw_0 = tf.reshape(image_raw_0, [128, 64, 3])
image_raw_1 = tf.reshape(image_raw_1, [128, 64, 3])
pose_0 = tf.cast(tf.reshape(pose_0, [128, 64, self.keypoint_num]), tf.float32) # 数据类型转换
pose_1 = tf.cast(tf.reshape(pose_1, [128, 64, self.keypoint_num]), tf.float32) #
mask_0 = tf.cast(tf.reshape(mask_0, [128, 64, 1]), tf.float32)
mask_1 = tf.cast(tf.reshape(mask_1, [128, 64, 1]), tf.float32)
images_0, images_1, poses_0, poses_1, masks_0, masks_1 = tf.train.batch([image_raw_0, image_raw_1, pose_0, pose_1, mask_0, mask_1],
batch_size=self.batch_size, num_threads=self.num_threads, capacity=self.capacityCoff * self.batch_size)
images_0 = utils_wgan.process_image(tf.to_float(images_0), 127.5, 127.5)
images_1 = utils_wgan.process_image(tf.to_float(images_1), 127.5, 127.5)
poses_0 = poses_0*2-1
poses_1 = poses_1*2-1
return images_0, images_1, poses_0, poses_1, masks_0, masks_1
def test(self):
print("测试")
test_result_dir = os.path.join(self.model_dir, 'test_result')
test_result_dir_x = os.path.join(test_result_dir, 'x')
test_result_dir_x_target = os.path.join(test_result_dir, 'x_target')
test_result_dir_G = os.path.join(test_result_dir, 'G')
test_result_dir_pose = os.path.join(test_result_dir, 'pose')
test_result_dir_pose_target = os.path.join(test_result_dir, 'pose_target')
test_result_dir_mask = os.path.join(test_result_dir, 'mask')
test_result_dir_mask_target = os.path.join(test_result_dir, 'mask_target')
if not os.path.exists(test_result_dir):
os.makedirs(test_result_dir)
if not os.path.exists(test_result_dir_x):
os.makedirs(test_result_dir_x)
if not os.path.exists(test_result_dir_x_target):
os.makedirs(test_result_dir_x_target)
if not os.path.exists(test_result_dir_G):
os.makedirs(test_result_dir_G)
if not os.path.exists(test_result_dir_pose):
os.makedirs(test_result_dir_pose)
if not os.path.exists(test_result_dir_pose_target):
os.makedirs(test_result_dir_pose_target)
if not os.path.exists(test_result_dir_mask):
os.makedirs(test_result_dir_mask)
if not os.path.exists(test_result_dir_mask_target):
os.makedirs(test_result_dir_mask_target)
for i in xrange(400):
x_fixed, x_target_fixed, pose_fixed, pose_target_fixed, mask_fixed, mask_target_fixed = self.get_image_from_loader()
x = utils_wgan.process_image(x_fixed, 127.5, 127.5)
x_target = utils_wgan.process_image(x_target_fixed, 127.5, 127.5)
if 0==i:
x_fake = self.generate(x, x_target, pose_target_fixed, test_result_dir, idx=self.start_step, save=True)
else:
x_fake = self.generate(x, x_target, pose_target_fixed, test_result_dir, idx=self.start_step, save=False)
p = (np.amax(pose_fixed, axis=-1, keepdims=False)+1.0)*127.5
pt = (np.amax(pose_target_fixed, axis=-1, keepdims=False)+1.0)*127.5
for j in xrange(self.batch_size):
idx = i*self.batch_size+j
im = Image.fromarray(x_fixed[j,:].astype(np.uint8))
im.save('%s/%05d.png'%(test_result_dir_x, idx))
im = Image.fromarray(x_target_fixed[j,:].astype(np.uint8))
im.save('%s/%05d.png'%(test_result_dir_x_target, idx))
im = Image.fromarray(x_fake[j,:].astype(np.uint8))
im.save('%s/%05d.png'%(test_result_dir_G, idx))
im = Image.fromarray(p[j,:].astype(np.uint8))
im.save('%s/%05d.png'%(test_result_dir_pose, idx))
im = Image.fromarray(pt[j,:].astype(np.uint8))
im.save('%s/%05d.png'%(test_result_dir_pose_target, idx))
im = Image.fromarray(mask_fixed[j,:].squeeze().astype(np.uint8))
im.save('%s/%05d.png'%(test_result_dir_mask, idx))
im = Image.fromarray(mask_target_fixed[j,:].squeeze().astype(np.uint8))
im.save('%s/%05d.png'%(test_result_dir_mask_target, idx))
if 0==i:
save_image(x_fixed, '{}/x_fixed.png'.format(test_result_dir))
save_image(x_target_fixed, '{}/x_target_fixed.png'.format(test_result_dir))
save_image(mask_fixed, '{}/mask_fixed.png'.format(test_result_dir))
save_image(mask_target_fixed, '{}/mask_target_fixed.png'.format(test_result_dir))
save_image((np.amax(pose_fixed, axis=-1, keepdims=True)+1.0)*127.5, '{}/pose_fixed.png'.format(test_result_dir))
save_image((np.amax(pose_target_fixed, axis=-1, keepdims=True)+1.0)*127.5, '{}/pose_target_fixed.png'.format(test_result_dir))
def test(self):
test_result_dir = os.path.join(self.model_dir, 'test_result')
test_result_dir_x = os.path.join(test_result_dir, 'x')
test_result_dir_x_target = os.path.join(test_result_dir, 'x_target')
test_result_dir_G = os.path.join(test_result_dir, 'G')
test_result_dir_pose = os.path.join(test_result_dir, 'pose')
test_result_dir_pose_target = os.path.join(test_result_dir, 'pose_target')
test_result_dir_mask = os.path.join(test_result_dir, 'mask')
test_result_dir_mask_target = os.path.join(test_result_dir, 'mask_target')
if not os.path.exists(test_result_dir):
os.makedirs(test_result_dir)
if not os.path.exists(test_result_dir_x):
os.makedirs(test_result_dir_x)
if not os.path.exists(test_result_dir_x_target):
os.makedirs(test_result_dir_x_target)
if not os.path.exists(test_result_dir_G):
os.makedirs(test_result_dir_G)
if not os.path.exists(test_result_dir_pose):
os.makedirs(test_result_dir_pose)
if not os.path.exists(test_result_dir_pose_target):
os.makedirs(test_result_dir_pose_target)
if not os.path.exists(test_result_dir_mask):
os.makedirs(test_result_dir_mask)
if not os.path.exists(test_result_dir_mask_target):
os.makedirs(test_result_dir_mask_target)
for i in xrange(400):
x_fixed, x_target_fixed, pose_fixed, pose_target_fixed, mask_fixed, mask_target_fixed = self.get_image_from_loader()
x = utils_wgan.process_image(x_fixed, 127.5, 127.5)
x_target = utils_wgan.process_image(x_target_fixed, 127.5, 127.5)
if 0==i:
x_fake = self.generate(x, x_target, pose_target_fixed, test_result_dir, idx=self.start_step, save=True)
else:
x_fake = self.generate(x, x_target, pose_target_fixed, test_result_dir, idx=self.start_step, save=False)
p = (np.amax(pose_fixed, axis=-1, keepdims=False)+1.0)*127.5
pt = (np.amax(pose_target_fixed, axis=-1, keepdims=False)+1.0)*127.5
for j in xrange(self.batch_size):
idx = i*self.batch_size+j
im = Image.fromarray(x_fixed[j,:].astype(np.uint8))
im.save('%s/%05d.png'%(test_result_dir_x, idx))
im = Image.fromarray(x_target_fixed[j,:].astype(np.uint8))
im.save('%s/%05d.png'%(test_result_dir_x_target, idx))
im = Image.fromarray(x_fake[j,:].astype(np.uint8))
im.save('%s/%05d.png'%(test_result_dir_G, idx))
im = Image.fromarray(p[j,:].astype(np.uint8))
im.save('%s/%05d.png'%(test_result_dir_pose, idx))
im = Image.fromarray(pt[j,:].astype(np.uint8))
im.save('%s/%05d.png'%(test_result_dir_pose_target, idx))
im = Image.fromarray(mask_fixed[j,:].squeeze().astype(np.uint8))
im.save('%s/%05d.png'%(test_result_dir_mask, idx))
im = Image.fromarray(mask_target_fixed[j,:].squeeze().astype(np.uint8))
im.save('%s/%05d.png'%(test_result_dir_mask_target, idx))
if 0==i:
save_image(x_fixed, '{}/x_fixed.png'.format(test_result_dir))
save_image(x_target_fixed, '{}/x_target_fixed.png'.format(test_result_dir))
save_image(mask_fixed, '{}/mask_fixed.png'.format(test_result_dir))
save_image(mask_target_fixed, '{}/mask_target_fixed.png'.format(test_result_dir))
save_image((np.amax(pose_fixed, axis=-1, keepdims=True)+1.0)*127.5, '{}/pose_fixed.png'.format(test_result_dir))
save_image((np.amax(pose_target_fixed, axis=-1, keepdims=True)+1.0)*127.5, '{}/pose_target_fixed.png'.format(test_result_dir))
def train(self):
x_fixed, x_target_fixed, pose_fixed, pose_target_fixed, mask_fixed, mask_target_fixed = self.get_image_from_loader()
save_image(x_fixed, '{}/x_fixed.png'.format(self.model_dir))
save_image(x_target_fixed, '{}/x_target_fixed.png'.format(self.model_dir))
save_image((np.amax(pose_fixed, axis=-1, keepdims=True)+1.0)*127.5, '{}/pose_fixed.png'.format(self.model_dir))
save_image((np.amax(pose_target_fixed, axis=-1, keepdims=True)+1.0)*127.5, '{}/pose_target_fixed.png'.format(self.model_dir))
save_image(mask_fixed, '{}/mask_fixed.png'.format(self.model_dir))
save_image(mask_target_fixed, '{}/mask_target_fixed.png'.format(self.model_dir))
for step in trange(self.start_step, self.max_step):
if step < 22000:
self.sess.run(self.g_optim1)
else:
# Train generator
if step > 0:
self.sess.run(self.g_optim2)
# Train critic
if (self.wgan_gp.MODE == 'dcgan') or (self.wgan_gp.MODE == 'lsgan'):
disc_ITERS = 1
else:
disc_ITERS = self.wgan_gp.CRITIC_ITERS
for i in range(disc_ITERS):
self.sess.run(self.d_optim)
if self.wgan_gp.MODE == 'wgan':
self.sess.run(self.clip_disc_weights)
fetch_dict = {}
if step % self.log_step == self.log_step-1:
fetch_dict.update({
"summary": self.summary_op
})
# "k_t": self.k_t,
result = self.sess.run(fetch_dict)
if step % self.log_step == self.log_step-1:
self.summary_writer.add_summary(result['summary'], step)
self.summary_writer.flush()
if step % (self.log_step * 3) == (self.log_step * 3)-1:
# if self.data_format == 'NCHW':
# x = x_fixed.transpose([0, 3, 1, 2])
# else:
# x = x_fixed
x = utils_wgan.process_image(x_fixed, 127.5, 127.5)
x_target = utils_wgan.process_image(x_target_fixed, 127.5, 127.5)
self.generate(x, x_target, pose_target_fixed, self.model_dir, idx=step)
if step % self.lr_update_step == self.lr_update_step - 1:
self.sess.run([self.g_lr_update, self.d_lr_update])
if step % (self.log_step * 30) == (self.log_step * 30)-1:
self.saver.save(self.sess, os.path.join(self.model_dir, 'model.ckpt'), global_step=step)
def _load_batch_pair_pose(self, dataset):
data_provider = slim.dataset_data_provider.DatasetDataProvider(
dataset, common_queue_capacity=32, common_queue_min=8)
image_raw_0, image_raw_1, label, pose_0, pose_1, mask_0, mask_1 = data_provider.get(
[
'image_raw_0', 'image_raw_1', 'label', 'pose_sparse_r4_0',
'pose_sparse_r4_1', 'pose_mask_r4_0', 'pose_mask_r4_1'
])
print("trainer－－_load_batch_pair_pose：")
print(pose_0)
pose_0 = sparse_ops.sparse_tensor_to_dense(pose_0,
default_value=0,
validate_indices=False)
pose_1 = sparse_ops.sparse_tensor_to_dense(pose_1,
default_value=0,
validate_indices=False)
image_raw_0 = tf.reshape(image_raw_0, [128, 64, 3])
image_raw_1 = tf.reshape(image_raw_1, [128, 64, 3])
pose_0 = tf.cast(tf.reshape(pose_0, [128, 64, self.keypoint_num]),
tf.float32) # 数据类型转换
pose_1 = tf.cast(tf.reshape(pose_1, [128, 64, self.keypoint_num]),
tf.float32) #
mask_0 = tf.cast(tf.reshape(mask_0, [128, 64, 1]), tf.float32)
mask_1 = tf.cast(tf.reshape(mask_1, [128, 64, 1]), tf.float32)
images_0, images_1, poses_0, poses_1, masks_0, masks_1 = tf.train.batch(
[image_raw_0, image_raw_1, pose_0, pose_1, mask_0, mask_1],
batch_size=self.batch_size,
num_threads=self.num_threads,
capacity=self.capacityCoff * self.batch_size)
images_0 = utils_wgan.process_image(tf.to_float(images_0), 127.5,
127.5)
images_1 = utils_wgan.process_image(tf.to_float(images_1), 127.5,
127.5)
poses_0 = poses_0 * 2 - 1
poses_1 = poses_1 * 2 - 1
return images_0, images_1, poses_0, poses_1, masks_0, masks_1
def generate_hunter(self, x_input, pose_input, path=None, save=True):
#x_input_ = cv2.resize(x_input, (64, 128))
x_input_ = cv2.resize(x_input, (256, 256))
x_input_ = np.expand_dims(x_input_, axis=0)
#pdb.set_trace()
#pose_input_ = np.transpose(pose_input, axes=(1, 2, 0))
#pose_input_ = cv2.resize(pose_input_, (64, 128))
#p_save = pose_input_.sum(axis=2)
#p_save = Image.fromarray(p_save.astype(np.uint8))
#p_save.save('hhh.png')
pose_target_fixed = np.expand_dims(pose_input, axis=0)
x_fixed = utils_wgan.process_image(x_input_, 127.5, 127.5)
G = self.sess.run(self.G, {
self.x: x_fixed,
self.pose_target: pose_target_fixed
})
#pdb.set_trace()
if path is None and save:
current_path = '/media/cheng/marvel/Pose-Guided-Person-Image-Generation/test/'
path = os.path.join(current_path, 'test.png')
im = Image.fromarray(G[0, :].astype(np.uint8))
im.save(path)
print("fake image generated.")
return G
def test(self):
test_result_dir = os.path.join(self.model_dir, 'test_result')
test_result_dir_x = os.path.join(test_result_dir, 'x')
test_result_dir_x_target = os.path.join(test_result_dir, 'x_target')
test_result_dir_G = os.path.join(test_result_dir, 'G')
test_result_dir_pose = os.path.join(test_result_dir, 'pose')
test_result_dir_pose_target = os.path.join(test_result_dir, 'pose_target')
test_result_dir_mask = os.path.join(test_result_dir, 'mask')
test_result_dir_mask_target = os.path.join(test_result_dir, 'mask_target')
if not os.path.exists(test_result_dir):
os.makedirs(test_result_dir)
if not os.path.exists(test_result_dir_x):
os.makedirs(test_result_dir_x)
if not os.path.exists(test_result_dir_x_target):
os.makedirs(test_result_dir_x_target)
if not os.path.exists(test_result_dir_G):
os.makedirs(test_result_dir_G)
if not os.path.exists(test_result_dir_pose):
os.makedirs(test_result_dir_pose)
if not os.path.exists(test_result_dir_pose_target):
os.makedirs(test_result_dir_pose_target)
if not os.path.exists(test_result_dir_mask):
os.makedirs(test_result_dir_mask)
if not os.path.exists(test_result_dir_mask_target):
os.makedirs(test_result_dir_mask_target)
with open("data/DF_test_data/p_pairs_test.p", 'rb') as f:
p_pairs = pickle.load(f)
c = 0
for i in range(400):
if c == len(p_pairs):
break
x_fixed, x_target_fixed, pose_fixed, pose_target_fixed, mask_fixed, mask_target_fixed = self.get_image_from_loader()
x = utils_wgan.process_image(x_fixed, 127.5, 127.5)
x_target = utils_wgan.process_image(x_target_fixed, 127.5, 127.5)
if 0==i:
x_fake = self.generate(x, x_target, pose_target_fixed, test_result_dir, idx=self.start_step, save=True)
else:
x_fake = self.generate(x, x_target, pose_target_fixed, test_result_dir, idx=self.start_step, save=False)
p = (np.amax(pose_fixed, axis=-1, keepdims=False)+1.0)*127.5
pt = (np.amax(pose_target_fixed, axis=-1, keepdims=False)+1.0)*127.5
for j in range(self.batch_size):
idx = i*self.batch_size+j
# fasionMENShirtsPolosid0000372503_1front.jpg_fasionMENShirtsPolosid0000372503_3back.jpg.png
img_name = p_pairs[c][0] + '_' + p_pairs[c][1]
im = Image.fromarray(x_fixed[j,:].astype(np.uint8))
im.save('%s/%s.png'%(test_result_dir_x, img_name))
im = Image.fromarray(x_target_fixed[j,:].astype(np.uint8))
im.save('%s/%s.png'%(test_result_dir_x_target, img_name))
im = Image.fromarray(x_fake[j,:].astype(np.uint8))
im.save('%s/%s.png'%(test_result_dir_G, img_name))
im = Image.fromarray(p[j,:].astype(np.uint8))
im.save('%s/%s.png'%(test_result_dir_pose, img_name))
im = Image.fromarray(pt[j,:].astype(np.uint8))
im.save('%s/%s.png'%(test_result_dir_pose_target, img_name))
im = Image.fromarray(mask_fixed[j,:].squeeze().astype(np.uint8))
im.save('%s/%s.png'%(test_result_dir_mask, img_name))
im = Image.fromarray(mask_target_fixed[j,:].squeeze().astype(np.uint8))
im.save('%s/%s.png'%(test_result_dir_mask_target, img_name))
c += 1
if 0==i:
save_image(x_fixed, '{}/x_fixed.png'.format(test_result_dir))
save_image(x_target_fixed, '{}/x_target_fixed.png'.format(test_result_dir))
save_image(mask_fixed, '{}/mask_fixed.png'.format(test_result_dir))
save_image(mask_target_fixed, '{}/mask_target_fixed.png'.format(test_result_dir))
save_image((np.amax(pose_fixed, axis=-1, keepdims=True)+1.0)*127.5, '{}/pose_fixed.png'.format(test_result_dir))
save_image((np.amax(pose_target_fixed, axis=-1, keepdims=True)+1.0)*127.5, '{}/pose_target_fixed.png'.format(test_result_dir))
def train(self):
print("训练")
x_fixed, x_target_fixed, pose_fixed, pose_target_fixed, mask_fixed, mask_target_fixed = \
self.get_image_from_loader()
# 以下是灰度图
# print("x_fixed:", x_fixed.shape)
# print("x_target_fixed:", x_target_fixed.shape)
# print("mask_fixed:", mask_fixed.shape)
# print("mask_target_fixed:", mask_target_fixed.shape)
# print("pose_fixed[0][40][40]:", np.array(pose_fixed[0][40][40]))
# print("pose_target_fixed:", pose_target_fixed.shape)
save_image(x_fixed, '{}/.png'.format(self.model_dir))
save_image(x_target_fixed, '{}/x_target_fixed.png'.format(self.model_dir))
save_image((np.amax(pose_fixed, axis=-1, keepdims=True)+1.0)*127.5, '{}/pose_fixed.png'.format(self.model_dir))
save_image((np.amax(pose_target_fixed, axis=-1, keepdims=True)+1.0)*127.5, '{}/pose_target_fixed.png'.format(self.model_dir))
save_image(mask_fixed, '{}/mask_fixed.png'.format(self.model_dir))
save_image(mask_target_fixed, '{}/mask_target_fixed.png'.format(self.model_dir))
for step in trange(self.start_step, self.max_step):
if step < 22000:
self.sess.run(self.g_optim1)
else:
# Train generator
if step > 0:
self.sess.run(self.g_optim2)
# Train critic
if (self.wgan_gp.MODE == 'dcgan') or (self.wgan_gp.MODE == 'lsgan'):
disc_ITERS = 1
else:
disc_ITERS = self.wgan_gp.CRITIC_ITERS
for i in xrange(disc_ITERS):
self.sess.run(self.d_optim)
if self.wgan_gp.MODE == 'wgan':
self.sess.run(self.clip_disc_weights)
fetch_dict = {}
if step % self.log_step == self.log_step-1:
fetch_dict.update({"summary": self.summary_op}) # "k_t": self.k_t,
result = self.sess.run(fetch_dict)
if step % self.log_step == self.log_step-1:
self.summary_writer.add_summary(result['summary'], step)
self.summary_writer.flush()
if step % (self.log_step * 3) == (self.log_step * 3)-1:
# if self.data_format == 'NCHW':
# x = x_fixed.transpose([0, 3, 1, 2])
# else:
# x = x_fixed
x = utils_wgan.process_image(x_fixed, 127.5, 127.5)
x_target = utils_wgan.process_image(x_target_fixed, 127.5, 127.5)
self.generate(x, x_target, pose_target_fixed, self.model_dir, idx=step)
if step % self.lr_update_step == self.lr_update_step - 1:
self.sess.run([self.g_lr_update, self.d_lr_update])
if step % (self.log_step * 30) == (self.log_step * 30)-1:
self.saver.save(self.sess, os.path.join(self.model_dir, 'model.ckpt'), global_step=step)
