def test():
with tf.Graph().as_default(), tf.device('/gpu:0'): # Use GPU 0
# Training parameters
# Count the number of training & eval data
num_data = utils.count_text_lines(args.test_filenames_file)
print('===> Train: There are totally %d test files' % (num_data))
steps_per_epoch = np.ceil(num_data / args.batch_size).astype(np.int32)
num_total_steps = args.max_epoches * steps_per_epoch
# Load data
data_loader = Dataloader(test_dataloader_params,
shuffle=False) # no shuffle
# Debug test train_dataloader
# test_synthetic_dataloader(data_loader, True)
I1_batch = data_loader.I1_batch
I2_batch = data_loader.I2_batch
I1_aug_batch = data_loader.I1_aug_batch
I2_aug_batch = data_loader.I2_aug_batch
I_batch = data_loader.I_batch
I_prime_batch = data_loader.I_prime_batch
full_I_batch = data_loader.full_I_batch
full_I_prime_batch = data_loader.full_I_prime_batch
pts1_batch = data_loader.pts1_batch
gt_batch = data_loader.gt_batch
patch_indices_batch = data_loader.patch_indices_batch
# Train on multiple GPU:
h_losses = []
# Create a session
gpu_options = tf.GPUOptions(
allow_growth=True
) # Does not pre-allocate large, increase if needed
config = tf.ConfigProto(
allow_soft_placement=True, gpu_options=gpu_options
) # soft_placement allows to work on CPUs if GPUs are not available
sess = tf.Session(config=config)
# Initialize
sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
# Threads coordinator
coordinator = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coordinator)
num_samples = 0
total_num_fail = 0
h_losses = []
total_time = 0
# Start test
for step in range(num_total_steps):
full_I_value, full_I_prime_value, I2_value, I1_value, I1_aug_value, I2_aug_value, I_value, I_prime_value, pts_1_value, full_gt_corr_value = sess.run(
[
full_I_batch, full_I_prime_batch, I2_batch, I1_batch,
I1_aug_batch, I2_aug_batch, I_batch, I_prime_batch,
pts1_batch, gt_batch
])
for i in range(args.batch_size):
num_samples += 1
down_ratio = 2
I_sample = utils.denorm_img(full_I_value[i]).astype(np.uint8)
I_prime_sample = utils.denorm_img(
full_I_prime_value[i]).astype(np.uint8)
corr1_sample = full_gt_corr_value[i, 0:8].reshape([
4, 2
]) / down_ratio # (gt is for 480x640. Here, use 240x320)
corr2_sample = full_gt_corr_value[i, 8:16].reshape(
[4, 2]) / down_ratio
# Use RANSAC_homography/ Direct method to find the homography (delta 4 points)
sample_start_time = timeit.default_timer()
if args.method == 'direct':
pred_h4p, _, not_found = direct_h.find_homography(
I_sample,
I_prime_sample,
corr1_sample,
corr2_sample,
visual=args.visual,
method=args.method,
num_iterations=args.num_iterations,
return_h_inv=False)
# RANSAC Methods
else:
pred_h4p, _, not_found = ransac_h.find_homography(
I_sample,
I_prime_sample,
corr1_sample,
corr2_sample,
visual=args.visual,
method=args.method,
min_match_count=args.num_features,
return_h_inv=False)
sample_run_time = timeit.default_timer() - sample_start_time
total_time += sample_run_time
# Set maximum value for every value of delta h4p
pred_h4p[np.where(pred_h4p >= 80)] = 80
pred_h4p[np.where(pred_h4p <= -80)] = -80
pred_corr2_sample = pred_h4p[0] + corr1_sample
h_loss_value = np.sqrt(
np.mean(np.square(pred_corr2_sample - corr2_sample)))
# Evaluate the result
# There are two cases of failure
if not_found: # Cannot find homography
total_num_fail += 1
print('===> Fail case 1: Not found homography')
else:
# H_loss if homography is identity matrix
h_loss_identity = np.sqrt(
np.mean(np.square(corr1_sample - corr2_sample)))
if h_loss_identity < h_loss_value:
print('===> Fail case 2: error > identity')
total_num_fail += 1
h_loss_value = h_loss_identity
h_losses.append(h_loss_value)
_ = utils.progress_bar(
step * args.batch_size + i,
num_total_steps * args.batch_size,
' Test| image %d, h_loss %.3f, h_loss_average %.3f, fail %d/%d, time %.4f'
% (i, h_loss_value, np.mean(h_losses), total_num_fail,
num_samples, sample_run_time))
# Save visualization
if args.save_visual:
# Query full images
img1_with_4pts = I_sample.astype(np.uint8)
img2_with_4pts = I_prime_sample.astype(np.uint8)
# Draw prediction
cv2.polylines(img2_with_4pts,
np.int32([pred_corr2_sample]), 1,
(5, 225, 225), 3)
point_color = (0, 255, 255)
line_color_set = [(255, 102, 255), (51, 153, 255),
(102, 255, 255), (255, 255, 0),
(102, 102, 244), (150, 202, 178),
(153, 240, 142), (102, 0, 51),
(51, 51, 0)]
# Draw 4 points (ground truth)
full_stack_images = utils.draw_matches(
img1_with_4pts,
corr1_sample,
img2_with_4pts,
corr2_sample,
'tmp.jpg',
color_set=line_color_set,
show=False)
# Save image
visual_file_name = os.path.join(
args.results_dir,
str(step * args.batch_size + i) + '_loss_' +
str(h_loss_value) + '.jpg')
#cv2.putText(full_stack_images, 'RMSE %.2f'%h_loss,(800, 100), cv2.FONT_HERSHEY_SIMPLEX, 1,(0,0,255),2)
cv2.imwrite(visual_file_name, full_stack_images)
print('Wrote file %s', visual_file_name)
result_dict = {
'method': args.method,
'h_losses': h_losses,
'h_loss_mu': np.mean(h_losses),
'h_loss_std': np.std(h_losses)
}
import cPickle as pickle
result_file_dir = os.path.join(args.results_dir, 'h_losses.pkl')
with open(result_file_dir, 'wb') as f:
pickle.dump(result_dict, f)
print('===> Successfully write results to %s' % result_file_dir)
print('==========================================================')
mean_h_loss, std_h_loss = np.mean(np.array(h_losses)), np.std(
np.array(h_losses))
print('===> H_loss:', mean_h_loss, '+/-', std_h_loss)
print('Running time:', total_time / num_samples)
fail_percent = total_num_fail * 1.0 / (num_samples)
print('Failure %.3f' % (fail_percent))
output_line = [
num_samples, mean_h_loss, std_h_loss, fail_percent,
total_time / num_samples
]
print('output_line:', output_line)
with open(os.path.join(args.log_dir, 'results.txt'), 'w') as f:
np.savetxt(f, [output_line], delimiter=' ', fmt='%.5f')
print('===> Wrote results to file %s' %
os.path.join(args.log_dir, 'results.txt'))
tops_list = utils.find_percentile(h_losses)
print('===> Percentile Values: (20, 50, 80, 100):')
print(tops_list)
print('======> End! ====================================')
if args.visual:
plt.ion()
train_dataloader_params = dataloader_params(data_path=args.data_path,
filenames_file=args.filenames_file,
pts1_file=args.pts1_file,
gt_file=args.gt_file,
mode=args.mode,
batch_size=args.batch_size,
img_h=args.img_h,
img_w=args.img_w,
patch_size=args.patch_size,
augment_list=args.augment_list,
do_augment=args.do_augment)
num_test_data = utils.count_text_lines(args.test_filenames_file)
# num_train_data = utils.count_text_lines(args.filenames_file)
# print('===> There are totally %d train files'%(num_train_data))
print('===> There are totally %d test files' % (num_test_data))
test_batch_size = np.min([num_test_data, args.batch_size])
test_dataloader_params = extended_dataloader_params(
data_path=args.data_path,
filenames_file=args.test_filenames_file,
pts1_file=args.test_pts1_file,
gt_file=args.test_gt_file,
mode='test',
batch_size=test_batch_size,
img_h=args.img_h,
img_w=args.img_w,
patch_size=args.patch_size,
def __init__(self):
# Overrides the current default graph for the lifetime of the context
with tf.device('/gpu:0'): # Use GPU 0
# Count the number of eval data
num_data = utils.count_text_lines(args.test_filenames_file)
print('===> Test: There are totally %d Test files' % (num_data))
steps_per_epoch = np.ceil(num_data / args.batch_size).astype(
np.int32)
self.num_total_steps = 3 * steps_per_epoch # Test 3 epoches
# Load data
data_loader = Dataloader(test_dataloader_params,
shuffle=True) # No shuffle
I1_batch = data_loader.I1_batch
I2_batch = data_loader.I2_batch
I1_aug_batch = data_loader.I1_aug_batch
I2_aug_batch = data_loader.I2_aug_batch
I_batch = data_loader.I_batch
I_prime_batch = data_loader.I_prime_batch
pts1_batch = data_loader.pts1_batch
gt_batch = data_loader.gt_batch
patch_indices_batch = data_loader.patch_indices_batch
# Split on multiple GPU
I1_splits = tf.split(I1_batch, args.num_gpus, 0)
I2_splits = tf.split(I2_batch, args.num_gpus, 0)
I1_aug_splits = tf.split(I1_aug_batch, args.num_gpus, 0)
I2_aug_splits = tf.split(I2_aug_batch, args.num_gpus, 0)
I_splits = tf.split(I_batch, args.num_gpus, 0)
I_prime_splits = tf.split(I_prime_batch, args.num_gpus, 0)
pts1_splits = tf.split(pts1_batch, args.num_gpus, 0)
gt_splits = tf.split(gt_batch, args.num_gpus, 0)
patch_indices_splits = tf.split(patch_indices_batch, args.num_gpus,
0)
# Train on multiple GPU:
reuse_variables = None
h_losses = []
rec_losses = []
ssim_losses = []
l1_losses = []
l1_smooth_losses = []
num_fails = []
model_params = homography_model_params(
mode='test',
batch_size=int(args.batch_size / args.num_gpus),
patch_size=args.patch_size,
img_h=args.img_h,
img_w=args.img_w,
loss_type=args.loss_type,
use_batch_norm=args.use_batch_norm,
augment_list=args.augment_list,
leftright_consistent_weight=args.leftright_consistent_weight)
# Deal with sharable variables
with tf.variable_scope(tf.get_variable_scope()):
for i in range(args.num_gpus):
with tf.device('/gpu:%d' % i):
model = HomographyModel(
model_params,
I1_splits[i],
I2_splits[i],
I1_aug_splits[i],
I2_aug_splits[i],
I_splits[i],
I_prime_splits[i],
pts1_splits[i],
gt_splits[i],
patch_indices_splits[i],
reuse_variables=reuse_variables,
model_index=i)
# Debug test splits
#test_synthetic_dataloader(data_loader, True, I1_splits[i], I2_splits[i], I_splits[i], I_prime_splits[i], pts1_splits[i], gt_splits[i], patch_indices_splits[i])
reuse_variables = True
# In testing, use bounded_h_loss (under successful condition)
h_loss = model.bounded_h_loss
rec_loss = model.rec_loss
ssim_loss = model.ssim_loss
l1_loss = model.l1_loss
l1_smooth_loss = model.l1_smooth_loss
num_fail = model.num_fail
self.pred_I2 = model.pred_I2
self.I2 = model.I2
self.H_mat = model.H_mat
self.I1 = model.I1
self.I1_aug = model.I1_aug
self.I2_aug = model.I2_aug
self.I = model.I
self.I_prime = model.I_prime
self.pts1 = model.pts_1
self.gt = model.gt
self.pred_h4p = model.pred_h4p
h_losses.append(h_loss)
rec_losses.append(rec_loss)
ssim_losses.append(ssim_loss)
l1_losses.append(l1_loss)
l1_smooth_losses.append(l1_smooth_loss)
num_fails.append(num_fail)
self.total_h_loss = tf.reduce_mean(h_losses)
self.total_num_fail = tf.reduce_sum(num_fails)
self.total_rec_loss = tf.reduce_mean(rec_losses)
self.total_ssim_loss = tf.reduce_mean(ssim_losses)
self.total_l1_loss = tf.reduce_mean(l1_losses)
self.total_l1_smooth_loss = tf.reduce_mean(l1_smooth_losses)
with tf.name_scope('Losses'):
tf.summary.scalar('Total_h_loss', self.total_h_loss)
tf.summary.scalar('Total_rec_loss', self.total_rec_loss)
tf.summary.scalar('Total_ssim_loss', self.total_ssim_loss)
tf.summary.scalar('Total_l1_loss', self.total_l1_loss)
tf.summary.scalar('Total_l1_smooth_loss',
self.total_l1_smooth_loss)
self.summary_opt = tf.summary.merge_all()
def train():
# Overrides the current default graph for the lifetime of the context
with tf.Graph().as_default(), tf.device('/gpu:0'): # Use GPU 0
global_step = tf.Variable(0, trainable=False)
# Training parameters
# Count the number of training & eval data
num_data = utils.count_text_lines(args.filenames_file)
print('===> Train: There are totally %d training files' % (num_data))
num_total_steps = 150000
# Optimizer. Use exponential decay: decayed_lr = lr* decay_rate^ (global_steps/ decay_steps)
decay_rate = 0.96
decay_steps = (math.log(decay_rate) * num_total_steps) / math.log(
args.min_lr * 1.0 / args.lr)
print('args lr:', args.lr, args.min_lr)
print('===> Decay steps:', decay_steps)
learning_rate = tf.train.exponential_decay(args.lr,
global_step,
int(decay_steps),
decay_rate,
staircase=True)
# Due to slim.batch_norm docs:
# Note: when training, the moving_mean and moving_variance need to be updated.
# By default the update ops are placed in `tf.GraphKeys.UPDATE_OPS`, so they
# need to be added as a dependency to the `train_op`. For example:
# ```python
# update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
# with tf.control_dependencies(update_ops):
# train_op = optimizer.minimize(loss)
# ```
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
with tf.control_dependencies(update_ops):
opt_step = tf.train.AdamOptimizer(learning_rate)
# Load data
data_loader = Dataloader(train_dataloader_params,
shuffle=True) # shuffle
I1_batch = data_loader.I1_batch
I2_batch = data_loader.I2_batch
I1_aug_batch = data_loader.I1_aug_batch
I2_aug_batch = data_loader.I2_aug_batch
I_batch = data_loader.I_batch
I_prime_batch = data_loader.I_prime_batch
pts1_batch = data_loader.pts1_batch
gt_batch = data_loader.gt_batch
patch_indices_batch = data_loader.patch_indices_batch
# Split on multiple GPU
I1_splits = tf.split(I1_batch, args.num_gpus, 0)
I2_splits = tf.split(I2_batch, args.num_gpus, 0)
I1_aug_splits = tf.split(I1_aug_batch, args.num_gpus, 0)
I2_aug_splits = tf.split(I2_aug_batch, args.num_gpus, 0)
I_splits = tf.split(I_batch, args.num_gpus, 0)
I_prime_splits = tf.split(I_prime_batch, args.num_gpus, 0)
pts1_splits = tf.split(pts1_batch, args.num_gpus, 0)
gt_splits = tf.split(gt_batch, args.num_gpus, 0)
patch_indices_splits = tf.split(patch_indices_batch, args.num_gpus, 0)
# Train on multiple GPU:
multi_grads = []
reuse_variables = None
h_losses = []
rec_losses = []
ssim_losses = []
l1_losses = []
l1_smooth_losses = []
ncc_losses = []
model_params = homography_model_params(
mode=args.mode,
batch_size=int(args.batch_size / args.num_gpus),
patch_size=args.patch_size,
img_h=args.img_h,
img_w=args.img_w,
loss_type=args.loss_type,
use_batch_norm=args.use_batch_norm,
augment_list=args.augment_list,
leftright_consistent_weight=args.leftright_consistent_weight)
# Deal with sharable variables
with tf.variable_scope(tf.get_variable_scope()):
for i in range(args.num_gpus):
with tf.device('/gpu:%d' % i):
model = HomographyModel(model_params,
I1_splits[i],
I2_splits[i],
I1_aug_splits[i],
I2_aug_splits[i],
I_splits[i],
I_prime_splits[i],
pts1_splits[i],
gt_splits[i],
patch_indices_splits[i],
reuse_variables=reuse_variables,
model_index=i)
h_loss = model.h_loss
rec_loss = model.rec_loss
ssim_loss = model.ssim_loss
l1_loss = model.l1_loss
l1_smooth_loss = model.l1_smooth_loss
ncc_loss = model.ncc_loss
pred_I2 = model.pred_I2
I2 = model.I2
H_mat = model.H_mat
I1 = model.I1
I = model.I
I1_aug = model.I1_aug
I2_aug = model.I2_aug
h_losses.append(h_loss)
rec_losses.append(rec_loss)
ssim_losses.append(ssim_loss)
l1_losses.append(l1_loss)
l1_smooth_losses.append(l1_smooth_loss)
ncc_losses.append(ncc_loss)
reuse_variables = True
if args.loss_type == 'h_loss':
grads = opt_step.compute_gradients(h_loss)
elif args.loss_type == 'rec_loss':
grads = opt_step.compute_gradients(rec_loss)
elif args.loss_type == 'ssim_loss':
grads = opt_step.compute_gradients(ssim_loss)
elif args.loss_type == 'l1_loss':
grads = opt_step.compute_gradients(l1_loss)
elif args.loss_type == 'l1_smooth_loss':
grads = opt_step.compute_gradients(l1_smooth_loss)
elif args.loss_type == 'ncc_loss':
grads = opt_step.compute_gradients(ncc_loss)
else:
print('===> Loss type does not exist!')
exit(0)
print('====> Use loss type: ', args.loss_type)
time.sleep(2)
multi_grads.append(grads)
# Take average of the grads
grads = utils.get_average_grads(multi_grads)
apply_grad_opt = opt_step.apply_gradients(grads,
global_step=global_step)
total_h_loss = tf.reduce_mean(h_losses)
total_rec_loss = tf.reduce_mean(rec_losses)
total_ssim_loss = tf.reduce_mean(ssim_losses)
total_l1_loss = tf.reduce_mean(l1_losses)
total_l1_smooth_loss = tf.reduce_mean(l1_smooth_losses)
total_ncc_loss = tf.reduce_mean(ncc_losses)
with tf.name_scope('Losses'):
tf.summary.scalar('Learning_rate', learning_rate)
tf.summary.scalar('Total_h_loss', total_h_loss)
tf.summary.scalar('Total_rec_loss', total_rec_loss)
tf.summary.scalar('Total_ssim_loss', total_ssim_loss)
tf.summary.scalar('Total_l1_loss', total_l1_loss)
tf.summary.scalar('Total_l1_smooth_loss', total_l1_smooth_loss)
tf.summary.scalar('Total_ncc_loss', total_ncc_loss)
summary_opt = tf.summary.merge_all()
# Create a session
gpu_options = tf.GPUOptions(
allow_growth=True
) # Does not pre-allocate large, increase if needed
config = tf.ConfigProto(
allow_soft_placement=True, gpu_options=gpu_options
) # soft_placement allows to work on CPUs if GPUs are not available
sess = tf.Session(config=config)
# Saver
log_name = args.loss_type
summary_writer = tf.summary.FileWriter(args.log_dir, sess.graph)
train_saver = tf.train.Saver(max_to_keep=5) # Keep maximum 5 models
# Initialize
sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
# Threads coordinator
coordinator = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coordinator)
# Restore
if args.resume:
train_saver.restore(sess,
tf.train.latest_checkpoint(args.model_dir))
if args.retrain:
sess.run(global_step.assign(0))
# Index of the image want to display
index = 0
h_total_loss_value = 0
rec_total_loss_value = 0
ssim_total_loss_value = 0
l1_total_loss_value = 0
l1_smooth_total_loss_value = 0
ncc_total_loss_value = 0
start_step = global_step.eval(session=sess)
print('===> Start step:', start_step)
# Start training
for step in range(start_step, start_step + num_total_steps):
if args.visual:
_, h_loss_value, rec_loss_value, ssim_loss_value, l1_loss_value, l1_smooth_loss_value, ncc_loss_value, lr_value, H_mat_value, pred_I2_value, I2_value, I1_value, I1_aug_value, I2_aug_value, I_value = sess.run(
[
apply_grad_opt, total_h_loss, total_rec_loss,
total_ssim_loss, total_l1_loss, total_l1_smooth_loss,
total_ncc_loss, learning_rate, H_mat, pred_I2, I2, I1,
I1_aug, I2_aug, I
])
elif args.loss_type == "l1_loss" and not args.visual:
_, h_loss_value, l1_loss_value, l1_smooth_loss_value, lr_value = sess.run(
[
apply_grad_opt, total_h_loss, total_l1_loss,
total_l1_smooth_loss, learning_rate
])
h_total_loss_value += h_loss_value
l1_total_loss_value += l1_loss_value
l1_smooth_total_loss_value += l1_smooth_loss_value
if step % 100 == 0:
total_time = utils.progress_bar(
step, num_total_steps + start_step - 1,
'Train: 1, h_loss %4.3f, l1_loss %.6f, l1_smooth_loss %.6f, lr %.6f'
%
(h_total_loss_value /
(step - start_step + 1), l1_total_loss_value /
(step - start_step + 1), l1_smooth_total_loss_value /
(step - start_step + 1), lr_value))
else:
_, h_loss_value, rec_loss_value, ssim_loss_value, l1_loss_value, l1_smooth_loss_value, ncc_loss_value, lr_value = sess.run(
[
apply_grad_opt, total_h_loss, total_rec_loss,
total_ssim_loss, total_l1_loss, total_l1_smooth_loss,
total_ncc_loss, learning_rate
])
h_total_loss_value += h_loss_value
rec_total_loss_value += rec_loss_value
ssim_total_loss_value += ssim_loss_value
l1_total_loss_value += l1_loss_value
l1_smooth_total_loss_value += l1_smooth_loss_value
ncc_total_loss_value += ncc_loss_value
if step % 100 == 0:
total_time = utils.progress_bar(
step, num_total_steps + start_step - 1,
'Train: 1, h_loss %4.3f, rec_loss %4.3f, ssim_loss %.6f. l1_loss %.6f, l1_smooth_loss %.6f, ncc_loss %.6f, lr %.6f'
%
(h_total_loss_value /
(step - start_step + 1), rec_total_loss_value /
(step - start_step + 1), ssim_total_loss_value /
(step - start_step + 1), l1_total_loss_value /
(step - start_step + 1), l1_smooth_total_loss_value /
(step - start_step + 1), ncc_total_loss_value /
(step - start_step + 1), lr_value))
# Tensorboard
if step % 1000 == 0:
summary_str = sess.run(summary_opt)
summary_writer.add_summary(summary_str, global_step=step)
if step and step % 1000 == 0:
train_saver.save(sess,
args.model_dir + args.model_name,
global_step=step)
if args.visual and step % 1 == 0:
if 'normalize' in args.augment_list:
pred_I2_sample_value = utils.denorm_img(
pred_I2_value[index, :, :, 0]).astype(np.uint8)
I2_sample_value = utils.denorm_img(
I2_value[index, :, :, 0]).astype(np.uint8)
I1_sample_value = utils.denorm_img(
I1_value[index, :, :, 0]).astype(np.uint8)
I1_aug_sample_value = utils.denorm_img(
I1_aug_value[index, :, :, 0]).astype(np.uint8)
I2_aug_sample_value = utils.denorm_img(
I2_aug_value[index, :, :, 0]).astype(np.uint8)
I_sample_value = utils.denorm_img(
I_value[index, ...]).astype(np.uint8)
else:
pred_I2_sample_value = pred_I2_value[index, :, :,
0].astype(np.uint8)
I2_sample_value = I2_value[index, :, :, 0].astype(np.uint8)
I1_sample_value = I1_value[index, :, :, 0].astype(np.uint8)
I1_aug_sample_value = I1_aug_value[index, :, :,
0].astype(np.uint8)
I2_aug_sample_value = I2_aug_value[index, :, :,
0].astype(np.uint8)
I_sample_value = I_value[index, ...].astype(np.uint8)
plt.subplot(3, 1, 1)
plt.imshow(np.concatenate(
[pred_I2_sample_value, I2_sample_value], 1),
cmap='gray')
plt.title('Pred I2 vs I2')
plt.subplot(3, 1, 2)
plt.imshow(np.concatenate(
[I1_aug_sample_value, I2_aug_sample_value], 1),
cmap='gray')
plt.title('I1_aug vs I2_aug')
plt.subplot(3, 1, 3)
plt.imshow(I_sample_value if I_sample_value.shape[2] ==
3 else I_sample_value[:, :, 0])
plt.title('I')
plt.show()
plt.pause(0.05)
# Save the final model
train_saver.save(sess,
args.model_dir + args.model_name,
global_step=step)
def __init__(self):
# Overrides the current default graph for the lifetime of the context
with tf.device('/gpu:0'): # Use GPU 0
# Count the number of eval data
num_data = utils.count_text_lines(args.test_filenames_file)
print('===> Test: There are totally %d Test files' % (num_data))
steps_per_epoch = np.ceil(num_data / args.batch_size).astype(
np.int32)
self.num_total_steps = 2 * steps_per_epoch # Test 2 epoches
# Load data
data_loader = Dataloader(test_dataloader_params,
shuffle=False) # No shuffle
# Debug test train_dataloader
# test_synthetic_dataloader(data_loader, True)
I1_batch = data_loader.I1_batch
I2_batch = data_loader.I2_batch
I1_aug_batch = data_loader.I1_aug_batch
I2_aug_batch = data_loader.I2_aug_batch
I_batch = data_loader.I_batch
I_prime_batch = data_loader.I_prime_batch
full_I_batch = data_loader.full_I_batch
full_I_prime_batch = data_loader.full_I_prime_batch
pts1_batch = data_loader.pts1_batch
gt_batch = data_loader.gt_batch
patch_indices_batch = data_loader.patch_indices_batch
# Split on multiple GPU
I1_splits = tf.split(I1_batch, args.num_gpus, 0)
I2_splits = tf.split(I2_batch, args.num_gpus, 0)
I1_aug_splits = tf.split(I1_aug_batch, args.num_gpus, 0)
I2_aug_splits = tf.split(I2_aug_batch, args.num_gpus, 0)
I_splits = tf.split(I_batch, args.num_gpus, 0)
I_prime_splits = tf.split(I_prime_batch, args.num_gpus, 0)
pts1_splits = tf.split(pts1_batch, args.num_gpus, 0)
gt_splits = tf.split(gt_batch, args.num_gpus, 0)
patch_indices_splits = tf.split(patch_indices_batch, args.num_gpus,
0)
# Train on multiple GPU:
reuse_variables = None
rec_losses = []
ssim_losses = []
l1_losses = []
l1_smooth_losses = []
num_fails = []
model_params = homography_model_params(
mode='test',
batch_size=int(args.batch_size / args.num_gpus),
patch_size=args.patch_size,
img_h=args.img_h,
img_w=args.img_w,
loss_type=args.loss_type,
use_batch_norm=args.use_batch_norm,
augment_list=args.augment_list,
leftright_consistent_weight=args.leftright_consistent_weight)
# Deal with sharable variables
with tf.variable_scope(tf.get_variable_scope()):
for i in range(args.num_gpus):
with tf.device('/gpu:%d' % i):
# Note that ground truth gt_ here is the correspondences between pairs of images
# and are different from the actual delta movement of fourpoints that we want to find
# This ground truth is used for evaluating the estimated homography on real image data.
model = HomographyModel(
model_params,
I1_splits[i],
I2_splits[i],
I1_aug_splits[i],
I2_aug_splits[i],
I_splits[i],
I_prime_splits[i],
pts1_splits[i],
gt_splits[i],
patch_indices_splits[i],
reuse_variables=reuse_variables,
model_index=i)
# Debug test splits
#test_synthetic_dataloader(data_loader, True, I1_splits[i], I2_splits[i], I_splits[i], I_prime_splits[i], pts1_splits[i], gt_splits[i], patch_indices_splits[i])
reuse_variables = True
rec_loss = model.rec_loss
ssim_loss = model.ssim_loss
l1_loss = model.l1_loss
l1_smooth_loss = model.l1_smooth_loss
if i == 0:
self.pred_I2 = model.pred_I2
self.I = model.I
self.I_prime = model.I_prime
self.I1_aug = model.I1_aug
self.I2_aug = model.I2_aug
self.pred_h4p = model.pred_h4p
self.gt_corr = model.gt
self.pts1 = model.pts_1
else:
self.pred_I2 = tf.concat(
[self.pred_I2, model.pred_I2], axis=0)
self.I = tf.concat([self.I, model.I], axis=0)
self.I_prime = tf.concat(
[self.I_prime, model.I_prime], axis=0)
self.I1_aug = tf.concat(
[self.I1_aug, model.I1_aug], axis=0)
self.I2_aug = tf.concat(
[self.I2_aug, model.I2_aug], axis=0)
self.pred_h4p = tf.concat(
[self.pred_h4p, model.pred_h4p], axis=0)
self.gt_corr = tf.concat([self.gt_corr, model.gt],
axis=0)
self.pts1 = tf.concat([self.pts1, model.pts_1],
axis=0)
rec_losses.append(rec_loss)
ssim_losses.append(ssim_loss)
l1_losses.append(l1_loss)
l1_smooth_losses.append(l1_smooth_loss)
self.total_rec_loss = tf.reduce_mean(rec_losses)
self.total_ssim_loss = tf.reduce_mean(ssim_losses)
self.total_l1_loss = tf.reduce_mean(l1_losses)
self.total_l1_smooth_loss = tf.reduce_mean(l1_smooth_losses)
self.full_I = full_I_batch
self.full_I_prime = full_I_prime_batch
with tf.name_scope('Losses'):
tf.summary.scalar('Total_rec_loss', self.total_rec_loss)
tf.summary.scalar('Total_ssim_loss', self.total_ssim_loss)
tf.summary.scalar('Total_l1_loss', self.total_l1_loss)
tf.summary.scalar('Total_l1_smooth_loss',
self.total_l1_smooth_loss)
self.summary_opt = tf.summary.merge_all()
def test():
with tf.Graph().as_default(), tf.device('/gpu:0'): # Use GPU 0
# Training parameters
# Count the number of training & eval data
num_data = utils.count_text_lines(args.test_filenames_file)
print('===> Train: There are totally %d test files'%(num_data))
steps_per_epoch = np.ceil(num_data/args.batch_size).astype(np.int32)
num_total_steps = args.max_epoches*steps_per_epoch
# Load data
data_loader = Dataloader(test_dataloader_params, shuffle=False) # no shuffle
# Debug test train_dataloader
# test_synthetic_dataloader(data_loader, True)
I1_batch = data_loader.I1_batch
I2_batch = data_loader.I2_batch
I1_aug_batch = data_loader.I1_aug_batch
I2_aug_batch = data_loader.I2_aug_batch
I_batch = data_loader.I_batch
I_prime_batch = data_loader.I_prime_batch
pts1_batch = data_loader.pts1_batch
gt_batch = data_loader.gt_batch
patch_indices_batch = data_loader.patch_indices_batch
# Train on multiple GPU:
h_losses = []
# Create a session
gpu_options = tf.GPUOptions(allow_growth=True) # Does not pre-allocate large, increase if needed
config = tf.ConfigProto(allow_soft_placement=True, gpu_options=gpu_options) # soft_placement allows to work on CPUs if GPUs are not available
sess = tf.Session(config=config)
# Initialize
sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
# Threads coordinator
coordinator = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coordinator)
num_samples = 0
total_num_fail = 0
h_total_loss_value = 0
h_losses = []
total_time = 0
# Start test
for step in range(num_total_steps):
I2_value, I1_value, I1_aug_value, I2_aug_value, I_value, I_prime_value, pts_1_value, gt_value = sess.run([I2_batch, I1_batch, I1_aug_batch, I2_aug_batch, I_batch, I_prime_batch, pts1_batch, gt_batch])
for i in range(args.batch_size):
num_samples += 1
I_sample = utils.denorm_img(I_value[i]).astype(np.uint8)
I_prime_sample = utils.denorm_img(I_prime_value[i]).astype(np.uint8)
pts_1_sample = pts_1_value[i].reshape([4,2])
gt_sample = gt_value[i].reshape([4,2])
pts_2_sample = pts_1_sample + gt_sample
# Use RANSAC_homography to find the homography (delta 4 points)
sample_start_time = timeit.default_timer()
if args.method == 'direct':
pred_h4p, _, not_found = direct_h.find_homography(I_sample, I_prime_sample, pts_1_sample, pts_2_sample, visual=args.visual, method=args.method, num_iterations=args.num_iterations)
else:
pred_h4p, _, not_found = ransac_h.find_homography(I_sample, I_prime_sample, pts_1_sample, pts_2_sample, visual=args.visual, method=args.method, min_match_count=args.num_features)
sample_run_time = timeit.default_timer() - sample_start_time
total_time += sample_run_time
# Set maximum value for every value of delta h4p
pred_h4p[np.where(pred_h4p >= RHO)] = RHO*2
pred_h4p[np.where(pred_h4p <=- RHO)] = -RHO*2
h_loss_value = np.sqrt(np.mean(np.square(pred_h4p[0] - gt_sample)))
# Evaluate the result
# There are two cases of failure
if not_found: # Cannot find homography
total_num_fail += 1
print('===> Fail case 1: Not found homography')
else:
# H_loss if homography is identity matrix
h_loss_identity = np.sqrt(np.mean(np.square(gt_sample)))
if h_loss_identity < h_loss_value:
print('===> Fail case 2: error > identity')
total_num_fail += 1
h_loss_value = h_loss_identity
h_losses.append(h_loss_value)
h_loss_value = np.sqrt(np.mean(np.square(pred_h4p - gt_sample)))
_ = utils.progress_bar(step*args.batch_size+i, num_total_steps*args.batch_size, ' Test| image %d, h_loss %.3f, h_loss_average %.3f, fail %d/%d, time %.4f'%(i, h_loss_value, np.mean(h_losses), total_num_fail, num_samples, sample_run_time))
print ('==========================================================')
mean_h_loss, std_h_loss = np.mean(np.array(h_losses)), np.std(np.array(h_losses))
print ('===> H_loss:', mean_h_loss, '+/-', std_h_loss)
print ('Running time:', total_time/num_samples)
fail_percent = total_num_fail*1.0/(num_samples)
print ('Failure %.3f'%(fail_percent))
output_line = [num_samples, mean_h_loss, std_h_loss, fail_percent, total_time/num_samples]
print ('output_line:', output_line)
with open(os.path.join(args.log_dir, 'results.txt'), 'w') as f:
np.savetxt(f, [output_line], delimiter= ' ', fmt='%.5f')
print('===> Wrote results to file %s'%os.path.join(args.log_dir, 'results.txt'))
tops_list = utils.find_percentile(h_losses)
print('===> Percentile Values: (30, 60, 100):')
print(tops_list)
