def linear_logistic_regression(res, x_train, y_train, x_test, y_test):
# Create model
model = LogisticRegression()
# Fit model
model.fit(x_train, y_train)
# Predict the response for test dataset (proba output)
y_pred = model.predict(x_test)
# Categorize the output
y_pred = np.where(y_pred > 0.5, 1, 0)
accuracy = accuracy_score(y_test, y_pred)
add_row(res, ["logisticRegression", accuracy])
return res
def save(self, input, prediction, target, to_disk=False):
rgb = input[0, :3, :, :]
input_depth = input[0, 3:4, :, :]
input_conf = input[0, 4:5, :, :]
in_gt_depth = target[0, :1, :, :]
out_depth1 = prediction[0][0, :1, :, :]
if prediction[1] is not None:
out_conf1 = prediction[1][0, :1, :, :]
else:
out_conf1 = None
if prediction[2] is not None:
out_depth2 = prediction[2][0, :1, :, :]
else:
out_depth2 = None
row = utils.merge_into_row_with_gt2(rgb, input_depth, input_conf,
in_gt_depth, out_depth1, out_conf1,
out_depth2)
if (self.image is not None):
self.image = utils.add_row(self.image, row)
else:
self.image = row
if to_disk:
utils.save_image(self.image, self.filename)
def decision_tree_accuracy(res, x_train, y_train, x_test, y_test):
# Create Decision Tree classifer object
tree = DecisionTreeClassifier()
# Train Decision Tree Classifer
tree = tree.fit(x_train, y_train)
# Predict the response for test dataset
y_pred = tree.predict(x_test)
accuracy = accuracy_score(y_test, y_pred)
add_row(res, ["decisionTree", accuracy])
col_names = [
'percentile1', 'percentile2', 'percentile3', 'percentile4',
'percentile5', 'persistence1', 'persistence2', 'persistence3',
'persistence4', 'persistence5', 'tree1', 'tree2', 'tree3'
]
print(dict(zip(col_names, tree.feature_importances_)))
return res
def random_forest_accuracy(res,
x_train,
y_train,
x_test,
y_test,
n_estimators=28):
# Create Decision Tree classifer object
model_rf = RandomForestClassifier(n_estimators=n_estimators,
random_state=0)
# Fit model
model_rf.fit(x_train, y_train)
# Predict the response for test dataset
y_pred = model_rf.predict(x_test)
accuracy = accuracy_score(y_test, y_pred)
add_row(res, ["randomForest", accuracy])
print("Tree depths: ",
[estimator.tree_.max_depth for estimator in model_rf.estimators_])
return res
def draw_images(idxs: Iterable[int]) -> np.ndarray:
im_merge = None
for i in idxs:
plt.figure()
x_rgbd, y = val_dataset_rgbd[i]
x_rgb, y = val_dataset_rgb[i]
x_rgb = torch.unsqueeze(x_rgb, 0)
x_rgbd = torch.unsqueeze(x_rgbd, 0)
y = torch.unsqueeze(y, 0)
x_rgbd, x_rgb, y = x_rgbd.cuda(), x_rgb.cuda(), y.cuda()
y_hat_depth = depth_model(x_rgbd # type: ignore
if depth_model_is_rgbd else x_rgb)
y_hat_rgb = rgb_model(x_rgbd # type: ignore
if rgb_model_is_rgbd else x_rgb)
images = [x_rgbd, y, y_hat_depth, y_hat_rgb]
squares = None if "single-pixel" in args.depth_type else [
val_dataset_rgbd.square
] * len(images)
row = merge_ims_into_row(images, square=squares)
im_merge = row if im_merge is None else add_row(im_merge, row)
return im_merge
def validate(val_loader, model, epoch, logger):
average_meter = AverageMeter()
model.eval() # switch to evaluate mode
end = time.time()
skip = len(val_loader) // 9 # save images every skip iters
for i, (input, target) in enumerate(val_loader):
input, target = input.cuda(), target.cuda()
torch.cuda.synchronize()
data_time = time.time() - end
# compute output
end = time.time()
with torch.no_grad():
pred = model(input)
torch.cuda.synchronize()
gpu_time = time.time() - end
# measure accuracy and record loss
result = Result()
result.evaluate(pred.data, target.data)
average_meter.update(result, gpu_time, data_time, input.size(0))
end = time.time()
# save 8 images for visualization
if args.dataset == 'kitti':
rgb = input[0]
pred = pred[0]
target = target[0]
else:
rgb = input
if i == 0:
img_merge = utils.merge_into_row(rgb, target, pred)
elif (i < 8 * skip) and (i % skip == 0):
row = utils.merge_into_row(rgb, target, pred)
img_merge = utils.add_row(img_merge, row)
elif i == 8 * skip:
filename = output_directory + '/comparison_' + str(epoch) + '.png'
utils.save_image(img_merge, filename)
if (i + 1) % args.print_freq == 0:
print('Test: [{0}/{1}]\t'
't_GPU={gpu_time:.3f}({average.gpu_time:.3f})\n\t'
'RMSE={result.rmse:.2f}({average.rmse:.2f}) '
'RML={result.absrel:.2f}({average.absrel:.2f}) '
'Log10={result.lg10:.3f}({average.lg10:.3f}) '
'Delta1={result.delta1:.3f}({average.delta1:.3f}) '
'Delta2={result.delta2:.3f}({average.delta2:.3f}) '
'Delta3={result.delta3:.3f}({average.delta3:.3f})'.format(
i + 1,
len(val_loader),
gpu_time=gpu_time,
result=result,
average=average_meter.average()))
avg = average_meter.average()
print('\n*\n'
'RMSE={average.rmse:.3f}\n'
'Rel={average.absrel:.3f}\n'
'Log10={average.lg10:.3f}\n'
'Delta1={average.delta1:.3f}\n'
'Delta2={average.delta2:.3f}\n'
'Delta3={average.delta3:.3f}\n'
't_GPU={time:.3f}\n'.format(average=avg, time=avg.gpu_time))
logger.add_scalar('Test/rmse', avg.rmse, epoch)
logger.add_scalar('Test/Rel', avg.absrel, epoch)
logger.add_scalar('Test/log10', avg.lg10, epoch)
logger.add_scalar('Test/Delta1', avg.delta1, epoch)
logger.add_scalar('Test/Delta2', avg.delta2, epoch)
logger.add_scalar('Test/Delta3', avg.delta3, epoch)
return avg, img_merge
def validate(val_loader, model, epoch, batch_epoch, write_to_file=True):
average_meter = AverageMeter()
model.eval() # switch to evaluate mode
end = time.time()
for i, (Y, Y_1_2, Y_1_4, Y_1_8, LR, LR_8, HR,
name) in enumerate(val_loader):
Y = Y.cuda()
Y_1_2 = Y_1_2.cuda()
Y_1_4 = Y_1_4.cuda()
Y_1_8 = Y_1_8.cuda()
LR_8 = LR_8.cuda()
LR = LR.cuda()
HR = HR.cuda()
torch.cuda.synchronize()
data_time = time.time() - end
# compute output
end = time.time()
with torch.no_grad():
# print("I am for validation in main 342")
if args.arch == 'VDSR_16':
pred_HR = model(LR)
elif args.arch == 'VDSR_16_2':
pred_HR = model(Y, LR)
elif args.arch == 'VDSR':
pred_HR, residule = model(LR_8, Y)
elif args.arch == 'ResNet_bicubic':
pred_HR, residule = model(LR_8, Y)
elif args.arch == 'resnet50_15_6' or 'resnet50_15_11' or 'resnet50_15_12':
pred_HR = model(Y_1_2, LR)
elif args.arch == 'resnet50_15_2' or 'resnet50_15_3' or 'resnet50_15_5' or 'resnet50_15_8' or 'resnet50_15_9':
pred_HR, residule = model(Y, LR, LR_8)
else:
if config.use_different_size_Y == 1:
pred_HR, pred_thermal0 = model(Y, Y_1_2, Y_1_4, Y_1_8, LR)
else:
pred_HR, pred_thermal = model(Y, LR)
torch.cuda.synchronize()
gpu_time = time.time() - end
# measure accuracy and record loss
result = Result()
result.evaluate(pred_HR, HR)
average_meter.update(result, gpu_time, data_time,
Y.size(0)) #Y.size(0) batch_size
end = time.time()
# save 8 images for visualization,对验证集合生产图片
skip = config.skip
if i == 0:
img_merge = utils.merge_into_row_with_YT(Y, LR, pred_HR, HR)
elif (i < 8 * skip) and (i % skip == 0):
row = utils.merge_into_row_with_YT(Y, LR, pred_HR, HR)
img_merge = utils.add_row(img_merge, row)
elif i == 8 * skip: #储存最终的图片
filename = output_directory + '/Compair_data_epoch_' + str(
epoch) + '_batch_eopch_' + str(batch_epoch + 1) + '.png'
utils.save_image(img_merge, filename)
print("生成第" + str(batch_epoch + 1) + "图片")
if (i + 1) % args.print_freq == 0:
print('Test: [{0}/{1}]\t'
't_GPU={gpu_time:.3f}({average.gpu_time:.3f})\n\t'
'RMSE={result.rmse:.2f}({average.rmse:.2f}) '
'MAE={result.mae:.2f}({average.mae:.2f}) '
'Delta1={result.delta1:.3f}({average.delta1:.3f}) '
'REL={result.absrel:.3f}({average.absrel:.3f}) '
'Lg10={result.lg10:.3f}({average.lg10:.3f}) '.format(
i + 1,
len(val_loader),
gpu_time=gpu_time,
result=result,
average=average_meter.average()))
avg = average_meter.average()
print('\n*\n'
'RMSE={average.rmse:.3f}\n'
'MAE={average.mae:.3f}\n'
'Delta1={average.delta1:.3f}\n'
'REL={average.absrel:.3f}\n'
'Lg10={average.lg10:.3f}\n'
't_GPU={time:.3f}\n'.format(average=avg, time=avg.gpu_time))
if write_to_file:
with open(test_csv, 'a') as csvfile:
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writerow({
'dataset epoch': epoch,
'batch epoch': batch_num + 1,
'psnr': 10 * math.log(1 / (avg.mse), 10),
'mse': avg.mse,
'rmse': avg.rmse,
'absrel': avg.absrel,
'lg10': avg.lg10,
'mae': avg.mae,
'delta1': avg.delta1,
'delta2': avg.delta2,
'delta3': avg.delta3,
'data_time': avg.data_time,
'gpu_time': avg.gpu_time
})
return avg, img_merge
def validate(val_loader, model, epoch, write_to_file=True):
average_meter = AverageMeter()
model.eval() # switch to evaluate mode
end = time.time()
for i, (input, target) in enumerate(val_loader):
input, target = input.cuda(), target.cuda()
torch.cuda.synchronize()
data_time = time.time() - end
# compute output
end = time.time()
##############################################################
## Start of PnP-Depth modification ##
##############################################################
# Original inference
with torch.no_grad():
ori_pred = model.pnp_forward_front(model.pnp_forward_rear(
input)) # equivalent to `ori_pred = model(input)`
# Inference with PnP
sparse_target = input[:, -1:] # NOTE: written for rgbd input
criterion = criteria.MaskedL1Loss().cuda(
) # NOTE: criterion function defined here only for clarity
pnp_iters = 5 # number of iterations
pnp_alpha = 0.01 # update/learning rate
pnp_z = model.pnp_forward_front(input)
for pnp_i in range(pnp_iters):
if pnp_i != 0:
pnp_z = pnp_z - pnp_alpha * torch.sign(pnp_z_grad) # iFGM
pnp_z = Variable(pnp_z, requires_grad=True)
pred = model.pnp_forward_rear(pnp_z)
if pnp_i < pnp_iters - 1:
pnp_loss = criterion(pred, sparse_target)
pnp_z_grad = Grad([pnp_loss], [pnp_z], create_graph=True)[0]
##############################################################
## End of PnP-Depth modification ##
##############################################################
torch.cuda.synchronize()
gpu_time = time.time() - end
# measure accuracy and record loss
result = Result()
result.evaluate(pred.data, target.data)
average_meter.update(result, gpu_time, data_time, input.size(0))
end = time.time()
# save 8 images for visualization
skip = 50
if args.modality == 'd':
img_merge = None
else:
if args.modality == 'rgb':
rgb = input
elif args.modality == 'rgbd':
rgb = input[:, :3, :, :]
depth = input[:, 3:, :, :]
if i == 0:
if args.modality == 'rgbd':
img_merge = utils.merge_into_row_with_gt(
rgb, depth, target, pred)
else:
img_merge = utils.merge_into_row(rgb, target, pred)
elif (i < 8 * skip) and (i % skip == 0):
if args.modality == 'rgbd':
row = utils.merge_into_row_with_gt(rgb, depth, target,
pred)
else:
row = utils.merge_into_row(rgb, target, pred)
img_merge = utils.add_row(img_merge, row)
elif i == 8 * skip:
filename = output_directory + '/comparison_' + str(
epoch) + '.png'
utils.save_image(img_merge, filename)
if (i + 1) % args.print_freq == 0:
print('Test: [{0}/{1}]\t'
't_GPU={gpu_time:.3f}({average.gpu_time:.3f})\n\t'
'RMSE={result.rmse:.2f}({average.rmse:.2f}) '
'MAE={result.mae:.2f}({average.mae:.2f}) '
'Delta1={result.delta1:.3f}({average.delta1:.3f}) '
'REL={result.absrel:.3f}({average.absrel:.3f}) '
'Lg10={result.lg10:.3f}({average.lg10:.3f}) '.format(
i + 1,
len(val_loader),
gpu_time=gpu_time,
result=result,
average=average_meter.average()))
avg = average_meter.average()
print('\n*\n'
'RMSE={average.rmse:.3f}\n'
'MAE={average.mae:.3f}\n'
'Delta1={average.delta1:.3f}\n'
'REL={average.absrel:.3f}\n'
'Lg10={average.lg10:.3f}\n'
't_GPU={time:.3f}\n'.format(average=avg, time=avg.gpu_time))
if write_to_file:
with open(test_csv, 'a') as csvfile:
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writerow({
'mse': avg.mse,
'rmse': avg.rmse,
'absrel': avg.absrel,
'lg10': avg.lg10,
'mae': avg.mae,
'delta1': avg.delta1,
'delta2': avg.delta2,
'delta3': avg.delta3,
'data_time': avg.data_time,
'gpu_time': avg.gpu_time
})
return avg, img_merge
def validate(val_loader, model, write_to_file=True):
average_meter = AverageMeter()
model.eval() # switch to evaluate mode
end = time.time()
print_freq = 10
for i, (input, target) in enumerate(val_loader):
input, target = input.cuda(), target.cuda()
torch.cuda.synchronize()
data_time = time.time() - end
# compute output
end = time.time()
with torch.no_grad():
pred = model(input)
torch.cuda.synchronize()
gpu_time = time.time() - end
# measure accuracy and record loss
result = Result()
result.evaluate(pred.data, target.data)
average_meter.update(result, gpu_time, data_time, input.size(0))
end = time.time()
# save 8 images for visualization
skip = 10
rgb = input
if i == 0:
import matplotlib.pyplot as plt
plt.imsave('pred.png', np.squeeze(pred.cpu().numpy()))
img_merge = utils.merge_into_row(rgb, target, pred)
elif (i < 8 * skip) and (i % skip == 0):
row = utils.merge_into_row(rgb, target, pred)
img_merge = utils.add_row(img_merge, row)
if (i + 1) % print_freq == 0:
print('Test: [{0}/{1}]\t'
't_GPU={gpu_time:.3f}({average.gpu_time:.3f})\n\t'
'RMSE={result.rmse:.2f}({average.rmse:.2f}) '
'MAE={result.mae:.2f}({average.mae:.2f}) '
'Delta1={result.delta1:.3f}({average.delta1:.3f}) '
'REL={result.absrel:.3f}({average.absrel:.3f}) '
'Lg10={result.lg10:.3f}({average.lg10:.3f}) '.format(
i + 1,
len(val_loader),
gpu_time=gpu_time,
result=result,
average=average_meter.average()))
avg = average_meter.average()
print('\n*\n'
'RMSE={average.rmse:.3f}\n'
'MAE={average.mae:.3f}\n'
'Delta1={average.delta1:.3f}\n'
'REL={average.absrel:.3f}\n'
'Lg10={average.lg10:.3f}\n'
't_GPU={time:.3f}\n'.format(average=avg, time=avg.gpu_time))
if write_to_file:
with open(test_csv, 'a') as csvfile:
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writerow({
'mse': avg.mse,
'rmse': avg.rmse,
'absrel': avg.absrel,
'lg10': avg.lg10,
'mae': avg.mae,
'delta1': avg.delta1,
'delta2': avg.delta2,
'delta3': avg.delta3,
'data_time': avg.data_time,
'gpu_time': avg.gpu_time
})
return avg, img_merge
def validation(device,
data_loader,
model,
ord_loss,
output_dir,
epoch,
logger,
PRINT_FREQ,
BETA,
GAMMA,
ORD_NUM=80.0):
avg80 = AverageMeter()
avg50 = AverageMeter()
model.eval()
end = time.time()
skip = 1
img_list = []
evalbar = tqdm(total=len(data_loader))
for i, (_input, _sparse_depth, _dense_depth) in enumerate(data_loader):
_input, _sparse_depth, _dense_depth = _input.to(
device), _sparse_depth.to(device), _dense_depth.to(device)
torch.cuda.synchronize()
data_time = time.time() - end
# compute output
end = time.time()
with torch.no_grad():
_pred_prob, _pred_label = model(_input)
loss = ord_loss(_pred_prob, _dense_depth)
torch.cuda.synchronize()
gpu_time = time.time() - end
pred_depth = utils.label2depth_sid(_pred_label,
K=ORD_NUM,
alpha=1.0,
beta=BETA,
gamma=GAMMA)
abs_rel, sq_rel, rmse, rmse_log, a1, a2, a3 = compute_errors(
_sparse_depth, pred_depth.to(device))
# measure accuracy and record loss
result80 = Result()
result80.evaluate(pred_depth, _sparse_depth.data, cap=80)
result50 = Result()
result50.evaluate(pred_depth, _sparse_depth.data, cap=50)
avg80.update(result80, gpu_time, data_time, _input.size(0))
avg50.update(result50, gpu_time, data_time, _input.size(0))
end = time.time()
# save images for visualization
if i == 0:
img_merge = utils.merge_into_row(_input, _dense_depth, pred_depth)
elif (i < 8 * skip) and (i % skip == 0):
row = utils.merge_into_row(_input, _dense_depth, pred_depth)
img_merge = utils.add_row(img_merge, row)
elif i == 8 * skip:
filename = os.path.join(output_dir,
'eval_{}.png'.format(int(epoch)))
print('save validation figures at {}'.format(filename))
utils.save_image(img_merge, filename)
if (i + 1) % PRINT_FREQ == 0:
print('Test: [{0}/{1}]\t'
't_GPU={gpu_time:.3f}({average.gpu_time:.3f})\n\t'
'RMSE={result.rmse:.2f}({average.rmse:.2f}) '
'AbsRel={result.absrel:.2f}({average.absrel:.2f}) '
'SqRel={result.sqrel:.2f}({average.sqrel:.2f}) '
'Log10={result.lg10:.3f}({average.lg10:.3f}) '
'RMSE_log={result.rmse_log:.3f}({average.rmse_log:.3f}) '
'Delta1={result.delta1:.3f}({average.delta1:.3f}) '
'Delta2={result.delta2:.3f}({average.delta2:.3f}) '
'Delta3={result.delta3:.3f}({average.delta3:.3f})'.format(
i + 1,
len(val_loader),
gpu_time=gpu_time,
result=result80,
average=avg80.average()))
# update progress bar and show loss
evalbar.set_postfix(
ORD_LOSS=
'{:.2f},RMSE/log= {:.2f}/{:.2f},delta={:.2f}/{:.2f}/{:.2f},AbsRel/SqRe;={:.2f}/{:.2f}'
.format(loss, rmse, rmse_log, a1, a2, a3, abs_rel, sq_rel))
evalbar.update(1)
i = i + 1
print('\n**** CAP=80 ****\n'
'RMSE={average.rmse:.3f}\n'
'RMSE_log={average.rmse_log:.3f}\n'
'AbsRel={average.absrel:.3f}\n'
'SqRel={average.sqrel:.3f}\n'
'Log10={average.lg10:.3f}\n'
'Delta1={average.delta1:.3f}\n'
'Delta2={average.delta2:.3f}\n'
'Delta3={average.delta3:.3f}\n'
'iRMSE={average.irmse:.3f}\n'
'iMAE={average.imae:.3f}\n'
't_GPU={average.gpu_time:.3f}\n'.format(average=avg80.average()))
print('\n**** CAP=50 ****\n'
'RMSE={average.rmse:.3f}\n'
'RMSE_log={average.rmse_log:.3f}\n'
'AbsRel={average.absrel:.3f}\n'
'SqRel={average.sqrel:.3f}\n'
'Log10={average.lg10:.3f}\n'
'Delta1={average.delta1:.3f}\n'
'Delta2={average.delta2:.3f}\n'
'Delta3={average.delta3:.3f}\n'
'iRMSE={average.irmse:.3f}\n'
'iMAE={average.imae:.3f}\n'
't_GPU={average.gpu_time:.3f}\n'.format(average=avg50.average()))
logger.add_scalar('VAL_CAP80/RMSE', avg80.average().rmse, epoch)
logger.add_scalar('VAL_CAP80/RMSE_log', avg80.average().rmse_log, epoch)
logger.add_scalar('VAL_CAP80/AbsRel', avg80.average().absrel, epoch)
logger.add_scalar('VAL_CAP80/SqRel', avg80.average().sqrel, epoch)
logger.add_scalar('VAL_CAP80/Delta1', avg80.average().delta1, epoch)
logger.add_scalar('VAL_CAP80/Delta2', avg80.average().delta2, epoch)
logger.add_scalar('VAL_CAP80/Delta3', avg80.average().delta3, epoch)
logger.add_scalar('VAL_CAP50/RMSE', avg50.average().rmse, epoch)
logger.add_scalar('VAL_CAP50/RMSE_log', avg50.average().rmse_log, epoch)
logger.add_scalar('VAL_CAP50/AbsRel', avg50.average().absrel, epoch)
logger.add_scalar('VAL_CAP50/SqRel', avg50.average().sqrel, epoch)
logger.add_scalar('VAL_CAP50/Delta1', avg50.average().delta1, epoch)
logger.add_scalar('VAL_CAP50/Delta2', avg50.average().delta2, epoch)
logger.add_scalar('VAL_CAP50/Delta3', avg50.average().delta3, epoch)
rgb_input = model.rgb_image
depth_input = model.sparse_depth
rgb_sparse = model.sparse_rgb
depth_target = model.depth_image
depth_est = model.depth_est
### These part save image in vis/ folder
if i % num == 0:
img_merge = utils.merge_into_row_with_pred_visualize(
rgb_input, depth_input, rgb_sparse, depth_target,
depth_est)
elif i % num < num - 1:
row = utils.merge_into_row_with_pred_visualize(
rgb_input, depth_input, rgb_sparse, depth_target,
depth_est)
img_merge = utils.add_row(img_merge, row)
elif i % num == num - 1:
filename = 'vis/' + str(i) + '.png'
utils.save_image(img_merge, filename)
i += 1
print('test epoch {0:}, iters: {1:}/{2:} '.format(
epoch, epoch_iter,
len(test_dataset) * test_opt.batch_size),
end='\r')
print('RMSE={result.rmse:.4f}({average.rmse:.4f}) '
'MSE={result.mse:.4f}({average.mse:.4f}) '
'MAE={result.mae:.4f}({average.mae:.4f}) '
'Delta1={result.delta1:.4f}({average.delta1:.4f}) '
'Delta2={result.delta2:.4f}({average.delta2:.4f}) '
def validate(val_loader, model, epoch, write_to_file=True, logger=None):
average_meter = AverageMeter()
if args.arch in multistage_group:
average_meter_stage1 = AverageMeter()
# Include daynight info and rain condition
avg_meter_day = AverageMeter()
avg_meter_night = AverageMeter()
# day, night, sun, rain combinations
avg_meter_day_sun = AverageMeter()
avg_meter_day_rain = AverageMeter()
avg_meter_night_sun = AverageMeter()
avg_meter_night_rain = AverageMeter()
# sun and rain
avg_meter_sun = AverageMeter()
avg_meter_rain = AverageMeter()
model.eval() # switch to evaluate mode
end = time.time()
# Save something to draw??
if logger is None:
import h5py
output_path = os.path.join(output_directory, "results.h5")
h5_writer = h5py.File(output_path, "w", libver="latest", swmr=True)
for i, data in enumerate(val_loader):
# Add compatibility for nuscenes
if args.data != "nuscenes":
inputs, target = data[0].cuda(), data[1].cuda()
else:
inputs, target = data["inputs"].cuda(), data["labels"].cuda()
torch.cuda.synchronize()
data_time = time.time() - end
# Compute output
end = time.time()
with torch.no_grad():
if args.arch in multistage_group:
pred_ = model(inputs)
pred1 = pred_["stage1"]
pred = pred_["stage2"]
else:
pred = model(inputs)
pred_ = None
torch.cuda.synchronize()
gpu_time = time.time() - end
# Record for qualitative results
if (logger is None) and (i % 5 == 0):
pred_np = {}
if pred_ is None:
pred_np = pred.cpu().numpy()
else:
for key in pred_.keys():
pred_np[key] = pred_[key][0, ...].cpu().numpy()
res = {
"inputs": data["inputs"][0, ...].cpu().numpy(),
"lidar_depth": data["lidar_depth"][0, ...].cpu().numpy(),
"radar_depth": data["radar_depth"][0, ...].cpu().numpy(),
"pred": pred_np
}
file_key = "%05d"%(i)
f_group = h5_writer.create_group(file_key)
# Store data
for key, output_data in res.items():
if isinstance(output_data, dict):
for key, data_ in output_data.items():
if key in res.keys():
key = key + "*"
f_group.create_dataset(key, data=data_, compression="gzip")
elif output_data is None:
pass
else:
f_group.create_dataset(key, data=output_data, compression="gzip")
# Measure accuracy and record loss
result = Result()
result.evaluate(pred.data, target.data)
average_meter.update(result, gpu_time, data_time, inputs.size(0))
if args.arch in multistage_group:
result_stage1 = Result()
result_stage1.evaluate(pred1.data, target.data)
average_meter_stage1.update(result_stage1, gpu_time, data_time, inputs.size(0))
end = time.time()
# Record the day, night, rain info
assert inputs.size(0) == 1
daynight_info = data["daynight_info"][0]
if ("day" in daynight_info) and ("rain" in daynight_info):
avg_meter_day_rain.update(result, gpu_time, data_time, inputs.size(0))
avg_meter_day.update(result, gpu_time, data_time, inputs.size(0))
avg_meter_rain.update(result, gpu_time, data_time, inputs.size(0))
elif "day" in daynight_info:
avg_meter_day_sun.update(result, gpu_time, data_time, inputs.size(0))
avg_meter_day.update(result, gpu_time, data_time, inputs.size(0))
avg_meter_sun.update(result, gpu_time, data_time, inputs.size(0))
if ("night" in daynight_info) and ("rain" in daynight_info):
avg_meter_night_rain.update(result, gpu_time, data_time, inputs.size(0))
avg_meter_night.update(result, gpu_time, data_time, inputs.size(0))
avg_meter_rain.update(result, gpu_time, data_time, inputs.size(0))
elif "night" in daynight_info:
avg_meter_night_sun.update(result, gpu_time, data_time, inputs.size(0))
avg_meter_night.update(result, gpu_time, data_time, inputs.size(0))
avg_meter_sun.update(result, gpu_time, data_time, inputs.size(0))
# save 8 images for visualization
skip = 50
if args.modality == 'd':
img_merge = None
else:
if args.modality == 'rgb':
rgb = inputs
elif args.modality == 'rgbd':
rgb = inputs[:,:3,:,:]
depth = inputs[:,3:,:,:]
if i == 0:
if args.modality == 'rgbd':
img_merge = utils.merge_into_row_with_gt(rgb, depth, target, pred)
else:
img_merge = utils.merge_into_row(rgb, target, pred)
elif (i < 8*skip) and (i % skip == 0):
if args.modality == 'rgbd':
row = utils.merge_into_row_with_gt(rgb, depth, target, pred)
else:
row = utils.merge_into_row(rgb, target, pred)
img_merge = utils.add_row(img_merge, row)
elif i == 8*skip:
filename = output_directory + '/comparison_' + str(epoch) + '.png'
utils.save_image(img_merge, filename)
if (i+1) % args.print_freq == 0:
print('Test: [{0}/{1}]\t'
't_GPU={gpu_time:.3f}({average.gpu_time:.3f})\n\t'
'RMSE={result.rmse:.2f}({average.rmse:.2f}) '
'MAE={result.mae:.2f}({average.mae:.2f}) '
'Delta1={result.delta1:.3f}({average.delta1:.3f}) '
'REL={result.absrel:.3f}({average.absrel:.3f}) '
'Lg10={result.lg10:.3f}({average.lg10:.3f}) '.format(
i+1, len(val_loader), gpu_time=gpu_time, result=result, average=average_meter.average()))
# Save the result to pkl file
if logger is None:
h5_writer.close()
avg = average_meter.average()
if args.arch in multistage_group:
avg_stage1 = average_meter_stage1.average()
if logger is not None:
record_test_scalar_summary(avg_stage1, epoch, logger, "Test_stage1")
print('\n*\n'
'RMSE={average.rmse:.3f}\n'
'Rel={average.absrel:.3f}\n'
'Log10={average.lg10:.3f}\n'
'Delta1={average.delta1:.3f}\n'
'Delta2={average.delta2:.3f}\n'
'Delta3={average.delta3:.3f}\n'
't_GPU={time:.3f}\n'.format(
average=avg, time=avg.gpu_time))
if logger is not None:
# Record summaries
record_test_scalar_summary(avg, epoch, logger, "Test")
print('\n*\n'
'RMSE={average.rmse:.3f}\n'
'MAE={average.mae:.3f}\n'
'Delta1={average.delta1:.3f}\n'
'REL={average.absrel:.3f}\n'
'Lg10={average.lg10:.3f}\n'
't_GPU={time:.3f}\n'.format(
average=avg, time=avg.gpu_time))
if write_to_file:
with open(test_csv, 'a') as csvfile:
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writerow({'mse': avg.mse, 'rmse': avg.rmse, 'absrel': avg.absrel, 'lg10': avg.lg10,
'mae': avg.mae, 'delta1': avg.delta1, 'delta2': avg.delta2, 'delta3': avg.delta3,
'data_time': avg.data_time, 'gpu_time': avg.gpu_time})
return avg, img_merge
def validate(val_loader, model, epoch, write_to_file=True):
average_meter = AverageMeter()
model.eval() # switch to evaluate mode
end = time.time()
eval_file = output_directory + '/evaluation.csv'
f = open(eval_file, "w+")
f.write("Max_Error,Depth,RMSE,GPU_TIME,Number_Of_Frame\r\n")
for i, (input, target) in enumerate(val_loader):
input, target = input.cuda(), target.cuda()
# torch.cuda.synchronize()
data_time = time.time() - end
# compute output
end = time.time()
with torch.no_grad():
pred = model(input)
# torch.cuda.synchronize()
gpu_time = time.time() - end
abs_err = (target.data - pred.data).abs().cpu()
max_err_ind = np.unravel_index(np.argmax(abs_err, axis=None),
abs_err.shape)
max_err_depth = target.data[max_err_ind]
max_err = abs_err[max_err_ind]
# measure accuracy and record loss
result = Result()
result.evaluate(pred.data, target.data)
average_meter.update(result, gpu_time, data_time, input.size(0))
end = time.time()
f.write(
f'{max_err},{max_err_depth},{result.rmse:.2f},{gpu_time},{i+1}\r\n'
)
# save 8 images for visualization
skip = 50
if args.modality == 'rgb':
rgb = input
if i == 0:
img_merge = utils.merge_into_row_with_gt(rgb, target, pred,
(target - pred).abs())
elif (i < 8 * skip) and (i % skip == 0):
row = utils.merge_into_row_with_gt(rgb, target, pred,
(target - pred).abs())
img_merge = utils.add_row(img_merge, row)
elif i == 8 * skip:
filename = output_directory + '/comparison_' + str(epoch) + '.png'
utils.save_image(img_merge, filename)
if (i + 1) % args.print_freq == 0:
print('Test: [{0}/{1}]\t'
't_GPU={gpu_time:.3f}({average.gpu_time:.3f})\n\t'
'RMSE={result.rmse:.2f}({average.rmse:.2f}) '
'MAE={result.mae:.2f}({average.mae:.2f}) '
'Delta1={result.delta1:.3f}({average.delta1:.3f}) '
'REL={result.absrel:.3f}({average.absrel:.3f}) '
'Lg10={result.lg10:.3f}({average.lg10:.3f}) '.format(
i + 1,
len(val_loader),
gpu_time=gpu_time,
result=result,
average=average_meter.average()))
f.close()
avg = average_meter.average()
print('\n*\n'
'RMSE={average.rmse:.3f}\n'
'MAE={average.mae:.3f}\n'
'Delta1={average.delta1:.3f}\n'
'REL={average.absrel:.3f}\n'
'Lg10={average.lg10:.3f}\n'
't_GPU={time:.3f}\n'.format(average=avg, time=avg.gpu_time))
if write_to_file:
with open(test_csv, 'a') as csvfile:
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writerow({
'mse': avg.mse,
'rmse': avg.rmse,
'absrel': avg.absrel,
'lg10': avg.lg10,
'mae': avg.mae,
'delta1': avg.delta1,
'delta2': avg.delta2,
'delta3': avg.delta3,
'data_time': avg.data_time,
'gpu_time': avg.gpu_time
})
return avg, img_merge
def validate(val_loader, model, epoch, write_to_file=True):
average_meter = AverageMeter()
# switch to evaluate mode
model.eval()
end = time.time()
for i, (input, target) in enumerate(val_loader):
input, target = input.cuda(), target.cuda(
) # 从后面看，这里的target应该是深度图的ground truth
input_var = torch.autograd.Variable(input)
target_var = torch.autograd.Variable(target)
torch.cuda.synchronize()
data_time = time.time() - end
# compute output
end = time.time()
depth_pred = model(input_var)
torch.cuda.synchronize()
gpu_time = time.time() - end
# measure accuracy and record loss
result = Result()
output1 = torch.index_select(depth_pred.data, 1,
torch.cuda.LongTensor([0]))
result.evaluate(output1, target)
average_meter.update(result, gpu_time, data_time, input.size(0))
end = time.time()
# save 8 images for visualization
skip = 50
if args.modality == 'd':
img_merge = None
else:
if args.modality == 'rgb':
rgb = input
elif args.modality == 'rgbd':
rgb = input[:, :3, :, :]
if i == 0:
img_merge = utils.merge_into_row(rgb, target, depth_pred)
# 隔50个图片抽一张作为可视化结果
elif (i < 8 * skip) and (i % skip == 0): # and等同于C++中的&&
row = utils.merge_into_row(rgb, target, depth_pred)
img_merge = utils.add_row(img_merge, row) # 添加一行
elif i == 8 * skip: # 只保存8张图片，保存够8张后输出
filename = output_directory + '/comparison_' + str(
epoch) + '.png' # str()：将()中的对象转换为字符串
utils.save_image(img_merge,
filename) # 建议：把这种常用的功能写到特定的脚本文件中，再像这样调用
if (i + 1) % args.print_freq == 0:
print('Test: [{0}/{1}]\t'
't_GPU={gpu_time:.3f}({average.gpu_time:.3f})\t'
'RMSE={result.rmse:.2f}({average.rmse:.2f}) '
'MAE={result.mae:.2f}({average.mae:.2f}) '
'Delta1={result.delta1:.3f}({average.delta1:.3f}) '
'REL={result.absrel:.3f}({average.absrel:.3f}) '
'Lg10={result.lg10:.3f}({average.lg10:.3f}) '.format(
i + 1,
len(val_loader),
gpu_time=gpu_time,
result=result,
average=average_meter.average()))
avg = average_meter.average()
print('\n*\n'
'RMSE={average.rmse:.3f}\n'
'MAE={average.mae:.3f}\n'
'Delta1={average.delta1:.3f}\n'
'REL={average.absrel:.3f}\n'
'Lg10={average.lg10:.3f}\n'
't_GPU={time:.3f}\n'.format(average=avg, time=avg.gpu_time))
if write_to_file:
with open(test_csv, 'a') as csvfile:
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writerow({
'mse': avg.mse,
'rmse': avg.rmse,
'absrel': avg.absrel,
'lg10': avg.lg10,
'mae': avg.mae,
'delta1': avg.delta1,
'delta2': avg.delta2,
'delta3': avg.delta3,
'data_time': avg.data_time,
'gpu_time': avg.gpu_time
})
return avg, img_merge
def validate_coarse(val_loader, model, epoch):
average_meter = AverageMeter()
model.eval() # switch to evaluate mode
end = time.time()
for i, (input, target) in enumerate(val_loader):
input, target = input.cuda(), target.cuda()
torch.cuda.synchronize()
data_time = time.time() - end
# compute output
end = time.time()
with torch.no_grad():
pred = model(input)
torch.cuda.synchronize()
gpu_time = time.time() - end
# measure accuracy and record loss
result = Result()
result.evaluate(pred.data, target.data)
average_meter.update(result, gpu_time, data_time, input.size(0))
end = time.time()
# save 8 images for visualization
skip = 50
if args.modality == 'd':
img_merge = None
else:
rgb = input
upsmaple_size = (rgb.size()[2], rgb.size()[3])
upsmaple = torch.nn.Upsample(size=upsmaple_size,
mode='bilinear',
align_corners=True)
target = upsmaple(target)
pred = upsmaple(pred)
if i == 0:
img_merge = utils.merge_into_row(rgb, target, pred)
elif (i < 8 * skip) and (i % skip == 0):
row = utils.merge_into_row(rgb, target, pred)
img_merge = utils.add_row(img_merge, row)
elif i == 8 * skip:
filename = output_directory + '/coarse_comparison_' + str(
epoch) + '.png'
utils.save_image(img_merge, filename)
if (i + 1) % args.print_freq == 0:
print('Test: [{0}/{1}]\t'
't_GPU={gpu_time:.3f}({average.gpu_time:.3f})\n\t'
'RMSE={result.rmse:.2f}({average.rmse:.2f}) '
'MAE={result.mae:.2f}({average.mae:.2f}) '
'Delta1={result.delta1:.3f}({average.delta1:.3f}) '
'REL={result.absrel:.3f}({average.absrel:.3f}) '
'Lg10={result.lg10:.3f}({average.lg10:.3f}) '.format(
i + 1,
len(val_loader),
gpu_time=gpu_time,
result=result,
average=average_meter.average()))
avg = average_meter.average()
print('\n*\n'
'RMSE={average.rmse:.3f}\n'
'MAE={average.mae:.3f}\n'
'Delta1={average.delta1:.3f}\n'
'REL={average.absrel:.3f}\n'
'Lg10={average.lg10:.3f}\n'
't_GPU={time:.3f}\n'.format(average=avg, time=avg.gpu_time))
return avg, img_merge
def validate(val_loader, model, epoch, write_to_file=True):
average_meter = AverageMeter()
model.eval() # switch to evaluate mode
end = time.time()
for i, (input, target) in enumerate(val_loader):
# io.imshow(np.squeeze(input[:,3:,:,:].cpu().numpy()), interpolation='nearest')
# io.show()
#print(input.size())
input, target = input.cuda(), target.cuda()
torch.cuda.synchronize()
data_time = time.time() - end
# compute output
end = time.time()
with torch.no_grad():
pred = model(input)
torch.cuda.synchronize()
gpu_time = time.time() - end
# measure accuracy and record loss
result = Result()
result.evaluate(pred.data, target.data)
average_meter.update(result, gpu_time, data_time, input.size(0))
end = time.time()
if visualize:
if args.modality == 'd':
fig = plt.figure()
fig.suptitle(
'Error Percentage ' + str(round(result.absrel * 100, 2)) +
' GPU TIME ' + str(round(gpu_time, 2)) + ' FPS ' +
str(round(60.0 / (gpu_time + data_time), 2)),
fontsize=16)
plt.subplot(131)
plt.title("SPARSE (Input)")
plt.axis('off')
plt.imshow(np.squeeze(input.cpu().numpy()),
interpolation='nearest')
plt.subplot(132)
plt.title("TARGET (Ground Truth)")
plt.axis('off')
plt.imshow(np.squeeze(target.cpu().numpy()),
interpolation='nearest')
plt.colorbar(fraction=0.1, pad=0.04)
plt.subplot(133)
plt.title("PREDICTED")
plt.axis('off')
plt.imshow(np.squeeze(pred.cpu().numpy()),
interpolation='nearest')
plt.colorbar(fraction=0.1, pad=0.04)
# plt.waitforbuttonpress(timeout=2)
# plt.close()
plt.waitforbuttonpress()
plt.close()
if args.modality == 'rgbd':
# sparse = np.squeeze(input[:, 3:, :, :].cpu().numpy())
# print(sparse.shape)
# sleep(3)
fig = plt.figure()
fig.suptitle(
'Error Percentage ' + str(round(result.absrel * 100, 2)) +
' GPU TIME ' + str(round(gpu_time, 2)) + ' FPS ' +
str(round(60.0 / (gpu_time + data_time), 2)),
fontsize=16)
rgb1 = 255 * np.transpose(
np.squeeze(input[:, :3, :, :].cpu().numpy()),
(1, 2, 0)) # H, W, C
rgb1 = Image.fromarray(rgb1.astype('uint8'))
plt.subplot(221)
plt.title("RGB (Input)")
plt.axis('off')
plt.imshow(rgb1)
plt.subplot(222)
plt.title("SPARSE (Input)")
plt.axis('off')
plt.imshow(np.squeeze(input[:, 3:, :, :].cpu().numpy()),
interpolation='nearest')
plt.subplot(223)
plt.title("TARGET (Ground Truth)")
plt.axis('off')
plt.imshow(np.squeeze(target.cpu().numpy()),
interpolation='nearest')
plt.colorbar(fraction=0.1, pad=0.04)
plt.subplot(224)
plt.title("PREDICTED")
plt.axis('off')
plt.imshow(np.squeeze(pred.cpu().numpy()),
interpolation='nearest')
plt.colorbar(fraction=0.1, pad=0.04)
# plt.waitforbuttonpress(timeout=2)
# plt.close()
plt.waitforbuttonpress()
plt.close()
#
# save 8 images for visualization
skip = 50
if args.modality == 'd':
img_merge = None
else:
if args.modality == 'rgb':
rgb = input
elif args.modality == 'rgbd':
rgb = input[:, :3, :, :]
depth = input[:, 3:, :, :]
if i == 0:
if args.modality == 'rgbd':
img_merge = utils.merge_into_row_with_gt(
rgb, depth, target, pred)
else:
img_merge = utils.merge_into_row(rgb, target, pred)
elif (i < 8 * skip) and (i % skip == 0):
if args.modality == 'rgbd':
row = utils.merge_into_row_with_gt(rgb, depth, target,
pred)
else:
row = utils.merge_into_row(rgb, target, pred)
img_merge = utils.add_row(img_merge, row)
elif i == 8 * skip:
filename = output_directory + '/comparison_' + str(
epoch) + '.png'
utils.save_image(img_merge, filename)
if (i + 1) % args.print_freq == 0:
print('Test: [{0}/{1}]\t'
't_GPU={gpu_time:.3f}({average.gpu_time:.3f})\n\t'
'RMSE={result.rmse:.2f}({average.rmse:.2f}) '
'MAE={result.mae:.2f}({average.mae:.2f}) '
'Delta1={result.delta1:.3f}({average.delta1:.3f}) '
'REL={result.absrel:.3f}({average.absrel:.3f}) '
'Lg10={result.lg10:.3f}({average.lg10:.3f}) '.format(
i + 1,
len(val_loader),
gpu_time=gpu_time,
result=result,
average=average_meter.average()))
avg = average_meter.average()
print('\n*\n'
'RMSE={average.rmse:.3f}\n'
'MAE={average.mae:.3f}\n'
'Delta1={average.delta1:.3f}\n'
'REL={average.absrel:.3f}\n'
'Lg10={average.lg10:.3f}\n'
't_GPU={time:.3f}\n'.format(average=avg, time=avg.gpu_time))
if write_to_file:
with open(test_csv, 'a') as csvfile:
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writerow({
'mse': avg.mse,
'rmse': avg.rmse,
'absrel': avg.absrel,
'lg10': avg.lg10,
'mae': avg.mae,
'delta1': avg.delta1,
'delta2': avg.delta2,
'delta3': avg.delta3,
'data_time': avg.data_time,
'gpu_time': avg.gpu_time
})
return avg, img_merge
def validate(val_loader, model, epoch):
average_meter = AverageMeter()
model.eval() # switch to evaluate mode
end = time.time()
skip = len(val_loader) // 8 # save images every skip iters
count_b = 0
count = 0
x = random.randint(0, len(val_loader))
for i, (input, target, label, mask) in enumerate(val_loader):
input, target = input.cuda(), target.cuda()
input = torch.squeeze(input, 0)
mask = mask.cuda()
torch.cuda.synchronize()
data_time = time.time() - end
# compute output
end = time.time()
with torch.no_grad():
pred, pred_mask, c1, c2, c3 = model(input)
# pred,c1,c2,c3 = model(input)
b, c, h, w = pred.size()
# temp0 = torch.zeros_like(pred_mask)
# temp1 = torch.ones_like(pred_mask)
# pred_mask2 = torch.where(pred_mask>0.5,temp1,temp0)
#pred[:,1,:,:] = pred[:,1,:,:] * pred_mask2
temp0_2 = torch.zeros_like(c1)
temp1_2 = torch.ones_like(c1)
c1_2 = torch.where(c1 > 0.5, temp1_2, temp0_2)
c2_2 = torch.where(c2 > 0.5, temp1_2, temp0_2)
c3_2 = torch.where(c3 > 0.5, temp1_2, temp0_2)
torch.cuda.synchronize()
gpu_time = time.time() - end
target = torch.squeeze(target, 1)
# measure accuracy and record loss
c1_2 = c1_2.cpu().numpy()
c2_2 = c2_2.cpu().numpy()
c3_2 = c3_2.cpu().numpy()
l = label.numpy()
for k in range(l.shape[0]):
if c1_2[k] == 0 and c2_2[k] == 0 and c3_2[k] == 0 and l[k] == -1:
count_b += 1
if c1_2[k] == 1 and c2_2[k] == 0 and c3_2[k] == 0 and l[k] == 0:
count_b += 1
if c1_2[k] == 0 and c2_2[k] == 1 and c3_2[k] == 0 and l[k] == 1:
count_b += 1
if c1_2[k] == 0 and c2_2[k] == 0 and c3_2[k] == 1 and l[k] == 2:
count_b += 1
count += l.shape[0]
result = Result()
result.evaluate(pred, target, label)
average_meter.update(result, gpu_time, data_time, input.size(0))
end = time.time()
# save 8 images for visualization
rgb = input
# print(rgb.size(),target.size(),pred.size())
# exit(0)
# if i == x:
# img_merge = utils.merge_into_row(rgb, target, pred, pred_mask2,label)
# filename = output_directory + '/comparison_' + str(epoch) + '.png'
# utils.save_image(img_merge, filename)
if i == 0:
img_merge = utils.merge_into_row(
rgb, target, pred, target,
label) # (rgb, target, pred, pred_mask2,label)
elif (i < 8 * skip) and (i % skip == 0):
row = utils.merge_into_row(rgb, target, pred, target, label)
img_merge = utils.add_row(img_merge, row)
elif i == 8 * skip:
filename = output_directory + '/comparison_' + str(epoch) + '.png'
utils.save_image(img_merge, filename)
if (i + 1) % args.print_freq == 0:
print("acc: %f" % (count_b * 1.0 / count))
print('Test: [{0}/{1}]\t'
't_GPU={gpu_time:.3f}({average.gpu_time:.3f})\n\t'
'MAE={result.mae:.2f}({average.mae:.2f}) '.format(
i + 1,
len(val_loader),
gpu_time=gpu_time,
result=result,
average=average_meter.average()))
avg = average_meter.average()
print("epoch: %d, acc: %f" % (epoch, count_b * 1.0 / count))
print('\n*\n'
'MAE={average.mae:.3f}\n'
't_GPU={time:.3f}\n'.format(average=avg, time=avg.gpu_time))
return avg, img_merge
def main():
args = parser.parse_args()
image_shape = (192, 256)
args.data = os.path.join(os.environ["DATASET_DIR"], "nyudepthv2")
dataset_no_depth = NYUDataset(args.data,
phase='val',
modality="rgbd",
num_samples=0,
square_width=0,
output_shape=image_shape,
depth_type="square")
dataset_square_hq = NYUDataset(args.data,
phase='val',
modality="rgbd",
num_samples=0,
square_width=50,
output_shape=image_shape,
depth_type="square")
dataset_square_lq = NYUDataset(args.data,
phase='val',
modality="rgbd",
num_samples=0,
square_width=50,
output_shape=image_shape,
depth_type="low-quality-square")
dataset_square_random_sample = NYUDataset(args.data,
phase='val',
modality="rgbd",
num_samples=200,
output_shape=image_shape,
depth_type="full")
dataset_single_pixel = NYUDataset(args.data,
phase='val',
modality="rgbd",
num_samples=0,
output_shape=image_shape,
depth_type="single-pixel")
dataset_single_pixel_lq = NYUDataset(args.data,
phase='val',
modality="rgbd",
num_samples=0,
output_shape=image_shape,
depth_type="single-pixel-low-quality")
images = []
image_idx = 223
#Create image with various possible depthmaps, not only from this work
_, y = dataset_no_depth[image_idx]
y = y.cuda().unsqueeze(0)
images.append(y)
for dataset in [
dataset_square_hq, dataset_square_lq, dataset_square_random_sample
]:
x, _ = dataset[image_idx]
x = x.cuda().unsqueeze(0)
images.append(x)
square_shapes = [
None, dataset_square_hq.square, dataset_square_hq.square, None
]
im_merge_depth = merge_ims_into_row(images,
rgbd_action="depth_only",
square=square_shapes)
os.makedirs(args.save_dir)
depth_fn = os.path.join(args.save_dir, "depth.png")
save_image(im_merge_depth, depth_fn)
#Create image with source image
x, y = dataset_no_depth[image_idx]
x, y = x.cuda().unsqueeze(0), y.cuda().unsqueeze(0)
im_merge_original = merge_ims_into_row([x, y], rgbd_action="rgb_only")
original_fn = os.path.join(args.save_dir, "original.png")
save_image(im_merge_original, original_fn)
#Create image with all the depth maps investigated in this work
#First row is hq images
images = []
squares = []
x, _ = dataset_single_pixel[image_idx]
images.append(x.cuda().unsqueeze(0))
squares.append(None)
for square_width in [10, 50, 100]:
dataset_square_hq.square_width = square_width
x, _ = dataset_square_hq[image_idx]
images.append(x.cuda().unsqueeze(0))
squares.append(dataset_square_hq.square)
im_merge_depths_hq = merge_ims_into_row(images,
square=squares,
rgbd_action="depth_only")
#Second row is lq images
images = []
squares = []
x, _ = dataset_single_pixel_lq[image_idx]
images.append(x.cuda().unsqueeze(0))
squares.append(None)
for square_width in [10, 50, 100]:
dataset_square_lq.square_width = square_width
x, _ = dataset_square_lq[image_idx]
images.append(x.cuda().unsqueeze(0))
squares.append(dataset_square_lq.square)
im_merge_depths_lq = merge_ims_into_row(images,
square=squares,
rgbd_action="depth_only")
im_merge_depths = add_row(im_merge_depths_hq, im_merge_depths_lq)
depths_fn = os.path.join(args.save_dir, "depths.png")
save_image(im_merge_depths, depths_fn)
def validate(val_loader, model, epoch, write_to_file=True):
average_meter = AverageMeter()
model.eval() # switch to evaluate mode
end = time.time()
for i, (input, target) in enumerate(val_loader):
input, target = input.cuda(), target.cuda()
# torch.cuda.synchronize()
data_time = time.time() - end
# compute output
end = time.time()
with torch.no_grad():
pred = model(input)
#print("Predicted shape ",pred.shape) #(1,1,224,224)
# torch.cuda.synchronize()
gpu_time = time.time() - end
# measure accuracy and record loss
result = Result()
result.evaluate(pred.data, target.data)
average_meter.update(result, gpu_time, data_time, input.size(0))
end = time.time()
# save 8 images for visualization
skip = 50
if args.modality == 'rgb':
rgb = input
output_dir = "/content/drive/MyDrive/Code/fast-depth/results2/"
filename_gt = output_dir + "gt_" + str(i) + ".jpg"
filename_predicted = output_dir + "predicted_" + str(i) + ".jpg"
gt, predicted = utils.get_depth_map(rgb, target, pred)
print("Predicted shape ", predicted.shape)
import scipy.misc
#scipy.misc.toimage(gt).save(filename_gt)
#scipy.misc.toimage(predicted).save(filename_predicted)
if i == 0:
img_merge = utils.merge_into_row(rgb, target, pred)
elif (i < 8 * skip) and (i % skip == 0):
row = utils.merge_into_row(rgb, target, pred)
img_merge = utils.add_row(img_merge, row)
elif i == 8 * skip:
filename = output_directory + '/comparison_' + str(epoch) + '.png'
utils.save_image(img_merge, filename)
if (i + 1) % args.print_freq == 0:
print('Test: [{0}/{1}]\t'
't_GPU={gpu_time:.3f}({average.gpu_time:.3f})\n\t'
'RMSE={result.rmse:.2f}({average.rmse:.2f}) '
'MAE={result.mae:.2f}({average.mae:.2f}) '
'Delta1={result.delta1:.3f}({average.delta1:.3f}) '
'REL={result.absrel:.3f}({average.absrel:.3f}) '
'Lg10={result.lg10:.3f}({average.lg10:.3f}) '.format(
i + 1,
len(val_loader),
gpu_time=gpu_time,
result=result,
average=average_meter.average()))
avg = average_meter.average()
print('\n*\n'
'RMSE={average.rmse:.3f}\n'
'MAE={average.mae:.3f}\n'
'Delta1={average.delta1:.3f}\n'
'REL={average.absrel:.3f}\n'
'Lg10={average.lg10:.3f}\n'
't_GPU={time:.3f}\n'.format(average=avg, time=avg.gpu_time))
if write_to_file:
with open(test_csv, 'a') as csvfile:
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writerow({
'mse': avg.mse,
'rmse': avg.rmse,
'absrel': avg.absrel,
'lg10': avg.lg10,
'mae': avg.mae,
'delta1': avg.delta1,
'delta2': avg.delta2,
'delta3': avg.delta3,
'data_time': avg.data_time,
'gpu_time': avg.gpu_time
})
return avg, img_merge
def validate(val_loader, model, epoch, write_to_file=True):
average_meter = AverageMeter()
# switch to evaluate mode
model.eval()
end = time.time()
for i, (input, target) in enumerate(val_loader):
input, target = input.cuda(), target.cuda()
# torch.cuda.synchronize()
data_time = time.time() - end
# compute output
end = time.time()
with torch.no_grad():
pred = model(input)
# torch.cuda.synchronize()
gpu_time = time.time() - end
# measure accuracy and record loss
result = Result()
result.evaluate(pred.data, target.data)
average_meter.update(result, gpu_time, data_time, input.size(0))
end = time.time()
# save 8 images for visualization
skip = 50
if args.modality == 'd':
img_merge = None
else:
if args.modality == 'rgb':
rgb = input
elif args.modality == 'rgbd':
rgb = input[:, :3, :, :]
depth = input[:, 3:, :, :]
if i == 0:
if args.modality == 'rgbd':
img_merge = utils.merge_into_row_with_gt(
rgb, depth, target, pred)
else:
img_merge = utils.merge_into_row(rgb, target, pred)
elif (i < 8 * skip) and (i % skip == 0):
if args.modality == 'rgbd':
row = utils.merge_into_row_with_gt(rgb, depth, target,
pred)
else:
row = utils.merge_into_row(rgb, target, pred)
img_merge = utils.add_row(img_merge, row)
elif i == 8 * skip:
filename = output_directory + '/comparison_' + str(
epoch) + '.png'
utils.save_image(img_merge, filename)
if (i + 1) % args.print_freq == 0:
print('Test: [{0}/{1}]\t'
't_GPU={gpu_time:.3f}({average.gpu_time:.3f})\n\t'
'RMSE={result.rmse:.2f}({average.rmse:.2f}) '
'MAE={result.mae:.2f}({average.mae:.2f})\n\t'
'Delta1={result.delta1:.3f}({average.delta1:.3f}) '
'REL={result.absrel:.3f}({average.absrel:.3f}) '
'Lg10={result.lg10:.3f}({average.lg10:.3f}) '.format(
i + 1,
len(val_loader),
gpu_time=gpu_time,
result=result,
average=average_meter.average()))
avg = average_meter.average()
print('\n*\n'
'RMSE={average.rmse:.3f}\n'
'MAE={average.mae:.3f}\n'
'Delta1={average.delta1:.3f}\n'
'REL={average.absrel:.3f}\n'
'Lg10={average.lg10:.3f}\n'
't_GPU={time:.3f}\n'.format(average=avg, time=avg.gpu_time))
if write_to_file:
with open(test_csv, 'a') as csvfile:
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writerow({
'mse': avg.mse,
'rmse': avg.rmse,
'absrel': avg.absrel,
'lg10': avg.lg10,
'mae': avg.mae,
'delta1': avg.delta1,
'delta2': avg.delta2,
'delta3': avg.delta3,
'data_time': avg.data_time,
'gpu_time': avg.gpu_time
})
return avg, img_merge
def validate(
val_loader,
square_width,
modality,
output_directory,
print_freq,
test_csv,
model: torch.nn.Module,
epoch: int,
write_to_file: bool = True,
) -> typing.Tuple[Result, Result, Result, np.array, typing.List[MaskedResult],
evaluate.Evaluator]:
average_meter = AverageMeter()
inside_average_meter = AverageMeter()
outside_average_meter = AverageMeter()
# switch to evaluate mode
model.eval()
evaluator = evaluate.Evaluator(val_loader.dataset.output_shape,
square_width)
end = time.time()
results = []
for i, (input, target) in enumerate(val_loader):
input, target = input.cuda(), target.cuda()
input_var = torch.autograd.Variable(input)
torch.cuda.synchronize()
data_time = time.time() - end
# compute output
end = time.time()
depth_pred = model(input_var)
torch.cuda.synchronize()
gpu_time = time.time() - end
# measure accuracy and record loss
output1 = torch.index_select(depth_pred.data, 1,
torch.cuda.LongTensor([0]))
evaluator.add_results(output1, target)
#assume all squares are of same size
result = MaskedResult(val_loader.dataset.mask_inside_square)
result.evaluate(output1, target)
results.append(result)
average_meter.update(result.result, gpu_time, data_time, input.size(0))
inside_average_meter.update(result.result_inside, gpu_time, data_time,
input.size(0))
outside_average_meter.update(result.result_outside, gpu_time,
data_time, input.size(0))
end = time.time()
# save 8 images for visualization
skip = 50
if modality == 'd':
img_merge = None
else:
if i == 0:
img_merge = utils.merge_ims_into_row(
[input, target, depth_pred], rgbd_action="both")
elif (i < 8 * skip) and (i % skip == 0):
row = utils.merge_ims_into_row([input, target, depth_pred],
rgbd_action="both")
img_merge = utils.add_row(img_merge, row)
elif i == 8 * skip:
filename = output_directory + '/comparison_' + str(
epoch) + '.png'
utils.save_image(img_merge, filename)
average = average_meter.average()
if (i + 1) % print_freq == 0:
#print('=> output: {}'.format(output_directory))
def print_result(result, result_name):
stdout.write(
f'Validation Epoch: {epoch} [{i + 1}/{len(val_loader)}]\t'
f"{result_name}: "
#f't_Data={data_time:.3f}({average.data_time:.3f}) '
#f't_GPU={gpu_time:.3f}({average.gpu_time:.3f}) '
f'RMSE={result.rmse:.2f}({average.rmse:.2f}) '
f'MAE={result.mae:.2f}({average.mae:.2f}) '
f'Delta1={result.delta1:.3f}({average.delta1:.3f}) '
#f'REL={result.absrel:.3f}({average.absrel:.3f}) '
#f'Lg10={result.lg10:.3f}({average.lg10:.3f}) \n'
'\n')
print_result(result.result, "result")
avg = average_meter.average()
avg_inside = inside_average_meter.average()
avg_outside = outside_average_meter.average()
avg.name = "average"
avg_inside.name = "average inside"
avg_outside.name = "average outside"
gpu_time = average.gpu_time
print(f'\n*\n' + str(avg) + "\n" + str(avg_inside) + "\n" +
str(avg_outside))
if write_to_file:
with open(test_csv, 'a') as csvfile:
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writerow({
'mse': avg.mse,
'rmse': avg.rmse,
'rmse inside': avg_inside.rmse,
'rmse outside': avg_outside.rmse,
'absrel': avg.absrel,
'absrel inside': avg_inside.absrel,
'absrel outside': avg_outside.absrel,
'lg10': avg.lg10,
'mae': avg.mae,
'mae inside': avg_inside.mae,
'mae outside': avg_outside.mae,
'delta1': avg.delta1,
'delta1 inside': avg_inside.delta1,
'delta1 outside': avg_outside.delta1,
'delta2': avg.delta2,
'delta3': avg.delta3,
'gpu_time': avg.gpu_time,
'data_time': avg.data_time
})
evaluator.save_plot(
os.path.join(output_directory, f"evaluation_epoch{epoch}.png"))
return avg, avg_inside, avg_outside, img_merge, results, evaluator
