def main(args, config, sample_index):
cuda = cnn_utils.check_cuda(config)
model = cnn_utils.load_model_and_weights(args, config)
if cuda:
model = model.cuda()
model.eval()
# Create output directory
base_dir = os.path.join(config['PATH']['output_dir'], 'warped')
if not os.path.isdir(base_dir):
pathlib.Path(base_dir).mkdir(parents=True, exist_ok=True)
save_dir = get_sub_dir_for_saving(base_dir)
start_time = time.time()
file_path = os.path.join(config['PATH']['hdf5_dir'],
config['PATH']['hdf5_name'])
with h5py.File(file_path, mode='r', libver='latest') as hdf5_file:
depth_grp = hdf5_file['val']['disparity']
SNUM = sample_index
depth_images = torch.squeeze(
torch.tensor(depth_grp['images'][SNUM], dtype=torch.float32))
colour_grp = hdf5_file['val']['colour']
colour_images = torch.tensor(colour_grp['images'][SNUM],
dtype=torch.float32)
sample = {
'depth': depth_images,
'colour': colour_images,
'grid_size': depth_images.shape[0]
}
warped = data_transform.center_normalise(sample)
im_input = warped['inputs'].unsqueeze_(0)
if cuda:
im_input = im_input.cuda()
output = model(im_input)
time_taken = time.time() - start_time
print("Time taken was {:4f}s".format(time_taken))
grid_size = 64
psnr_accumulator = (0, 0, 0)
ssim_accumulator = (0, 0, 0)
print("Saving output to", save_dir)
output = torch.squeeze(denormalise_lf(output))
cpu_output = np.around(output.cpu().detach().numpy()).astype(np.uint8)
if (not args.no_eval) or args.get_diff:
ground_truth = np.around(
denormalise_lf(colour_images).numpy()).astype(np.uint8)
grid_len = int(math.sqrt(grid_size))
for i in range(grid_size):
row, col = i // grid_len, i % grid_len
file_name = 'Colour{}{}.png'.format(row, col)
save_location = os.path.join(save_dir, file_name)
if i == 0:
print("Saving images of size ", cpu_output[i].shape)
image_warping.save_array_as_image(cpu_output[i], save_location)
if args.get_diff:
colour = ground_truth[i]
diff = image_warping.get_diff_image(colour, cpu_output[i])
#diff = get_diff_image_floatint(res, colour)
file_name = 'Diff{}{}.png'.format(row, col)
save_location = os.path.join(save_dir, file_name)
image_warping.save_array_as_image(diff, save_location)
if not args.no_eval:
img = ground_truth[i]
file_name = 'GT_Colour{}{}.png'.format(row, col)
save_location = os.path.join(save_dir, file_name)
image_warping.save_array_as_image(img, save_location)
psnr = evaluate.my_psnr(cpu_output[i], img)
ssim = evaluate.ssim(cpu_output[i], img)
psnr_accumulator = welford.update(psnr_accumulator, psnr)
ssim_accumulator = welford.update(ssim_accumulator, ssim)
psnr_mean, psnr_var, _ = welford.finalize(psnr_accumulator)
ssim_mean, ssim_var, _ = welford.finalize(ssim_accumulator)
print("For cnn, psnr average {:5f}, stddev {:5f}".format(
psnr_mean, math.sqrt(psnr_var)))
print("For cnn, ssim average {:5f}, stddev {:5f}".format(
ssim_mean, math.sqrt(ssim_var)))
def process(self):
"""Perform the model warping and output an image grid"""
if self.getPropertyByIdentifier("off").value:
print("Image warping is currently turned off")
return 1
start_time = time.time()
if self.getPropertyByIdentifier("display_input").value:
im_data = []
for name in INPORT_LIST:
im_data.append(self.getInport(name).getData())
out_image = Image(OUT_SIZE, DTYPE)
out = resize(
im_data[0].colorLayers[0].data.transpose(1, 0, 2),
OUT_SIZE_LIST)
with warnings.catch_warnings():
warnings.simplefilter("ignore")
inter_out = img_as_ubyte(out)
out_image.colorLayers[0].data = inter_out
self.getOutport("outport").setData(out_image)
return 1
if model is None:
print("No model for synthesis")
return -1
cam = inviwopy.app.network.EntryExitPoints.camera
im_data = []
for name in INPORT_LIST:
im_data.append(self.getInport(name).getData())
for im in im_data:
if not (im_data[0].dimensions == im.dimensions):
print("Operation is incompatible with images of different size")
print("Size 1: ", im_data[0].dimensions)
print("Size 2: ", im.dimensions)
return -1
out_image = Image(OUT_SIZE, DTYPE)
sample_image = Image(SAMPLE_SIZE, DTYPE)
im_colour = []
for idx, name in enumerate(INPORT_LIST):
im_colour.append(im_data[idx].colorLayers[0].data[:, :, :3].transpose(1, 0, 2))
im_depth = []
near = cam.nearPlane
far = cam.farPlane
baseline = 0.5
focal_length = cam.projectionMatrix[0][0]
fov = cam.fov.value
for idx, name in enumerate(INPORT_LIST):
im_depth.append(
conversions.depth_to_pixel_disp(
im_data[idx].depth.data.transpose(1, 0),
near=near, far=far, baseline=baseline,
focal_length=focal_length,
fov=fov,
image_pixel_size=float(im_data[0].dimensions[0]))
)
sample = {
'depth': torch.tensor(im_depth[0], dtype=torch.float32).unsqueeze_(0),
'colour': torch.tensor(im_colour[0], dtype=torch.float32).unsqueeze_(0),
'grid_size': GRID_SIZE}
warped = data_transform.transform_inviwo_to_warped(sample)
desired_shape = warped['shape']
im_input = warped['inputs'].unsqueeze_(0)
if cuda:
im_input = im_input.cuda()
model.eval()
output = model(im_input)
output += im_input
output = torch.clamp(output, 0.0, 1.0)
end_time = time.time() - start_time
print("Grid light field rendered in {:4f}".format(end_time))
out_unstack = data_transform.undo_remap(
output[0], desired_shape, dtype=torch.float32)
out_colour = cnn_utils.transform_lf_to_torch(
out_unstack
)
output_grid = vutils.make_grid(
out_colour, nrow=8, range=(0, 1), normalize=False,
padding=2, pad_value=1.0)
output_grid = resize(
output_grid.cpu().detach().numpy().transpose(1, 2, 0),
OUT_SIZE_LIST)
with warnings.catch_warnings():
warnings.simplefilter("ignore")
inter_out = img_as_ubyte(output_grid)
#inter_out = denormalise_lf(output_grid)
#inter_out = inter_out.cpu().detach().numpy().astype(np.uint8).transpose(1, 2, 0)
# Add an alpha channel here
shape = tuple(OUT_SIZE_LIST) + (4,)
final_out = np.full(shape, 255, np.uint8)
final_out[:, :, :3] = inter_out
shape = tuple(SAMPLE_SIZE_LIST) + (4,)
sample_out = np.full(shape, 255, np.uint8)
sample_out[:, :, :3] = np.around(
data_transform.denormalise_lf(
out_unstack).cpu().detach().numpy()
).astype(np.uint8)[self.getPropertyByIdentifier("sample_num").value]
# Inviwo expects a uint8 here
out_image.colorLayers[0].data = final_out
sample_image.colorLayers[0].data = sample_out
self.getOutport("outport").setData(out_image)
self.getOutport("sample").setData(sample_image)
end_time = time.time() - start_time
print("Overall render time was {:4f}".format(end_time))
def do_one_demo(args, config, hdf5_file, model, sample_num, cuda):
depth_grp = hdf5_file['val']['disparity']
# Create output directory
if not args.no_save:
base_dir = os.path.join(config['PATH']['output_dir'], 'warped')
if not os.path.isdir(base_dir):
pathlib.Path(base_dir).mkdir(parents=True, exist_ok=True)
save_dir = get_sub_dir_for_saving(base_dir)
model.eval()
SNUM = sample_num
start_time = time.time()
print("Working on image", SNUM)
depth_images = torch.squeeze(
torch.tensor(depth_grp['images'][SNUM], dtype=torch.float32))
colour_grp = hdf5_file['val']['colour']
colour_images = torch.tensor(colour_grp['images'][SNUM],
dtype=torch.float32)
sample = {
'depth': depth_images,
'colour': colour_images,
'grid_size': depth_images.shape[0]
}
warped = data_transform.transform_to_warped(sample)
warped = data_transform.stack(warped, 65)
im_input = warped['inputs'].unsqueeze_(0)
if cuda:
im_input = im_input.cuda()
output = model(im_input)
im_input = im_input[:, :-3]
output += im_input
output = torch.clamp(output, 0.0, 1.0)
time_taken = time.time() - start_time
print("Time taken was {:.0f}s".format(time_taken))
grid_size = 64
psnr_accumulator = (0, 0, 0)
ssim_accumulator = (0, 0, 0)
if not args.no_save:
print("Saving output to", save_dir)
no_cnn_dir = os.path.join(save_dir, "no_cnn")
cnn_dir = os.path.join(save_dir, "cnn")
os.mkdir(cnn_dir)
os.mkdir(no_cnn_dir)
output = torch.squeeze(denormalise_lf(output))
output = data_transform.torch_unstack(output)
im_input = im_input.cpu().detach()
cpu_output = np.around(output.cpu().detach().numpy()).astype(np.uint8)
if (not args.no_eval) or args.get_diff:
ground_truth = np.around(denormalise_lf(colour_images).numpy()).astype(
np.uint8)
grid_len = int(math.sqrt(grid_size))
for i in range(grid_size):
row, col = i // grid_len, i % grid_len
if not args.no_save:
file_name = 'Colour{}{}.png'.format(row, col)
save_location = os.path.join(cnn_dir, file_name)
if i == 0:
print("Saving images of size ", cpu_output[i].shape)
image_warping.save_array_as_image(cpu_output[i], save_location)
if args.get_diff and not args.no_save:
colour = ground_truth[i]
diff = image_warping.get_diff_image(colour, cpu_output[i])
#diff = get_diff_image_floatint(res, colour)
file_name = 'Diff{}{}.png'.format(row, col)
save_location = os.path.join(cnn_dir, file_name)
image_warping.save_array_as_image(diff, save_location)
if not args.no_eval:
img = ground_truth[i]
if not args.no_save:
file_name = 'GT_Colour{}{}.png'.format(row, col)
save_location = os.path.join(save_dir, file_name)
image_warping.save_array_as_image(img, save_location)
psnr = evaluate.my_psnr(cpu_output[i], img)
ssim = evaluate.ssim(cpu_output[i], img)
psnr_accumulator = welford.update(psnr_accumulator, psnr)
ssim_accumulator = welford.update(ssim_accumulator, ssim)
psnr_mean, psnr_var, _ = welford.finalize(psnr_accumulator)
ssim_mean, ssim_var, _ = welford.finalize(ssim_accumulator)
print("For cnn, psnr average {:5f}, stddev {:5f}".format(
psnr_mean, math.sqrt(psnr_var)))
print("For cnn, ssim average {:5f}, stddev {:5f}".format(
ssim_mean, math.sqrt(ssim_var)))
psnr1 = psnr_mean
ssim1 = ssim_mean
psnr_accumulator = (0, 0, 0)
ssim_accumulator = (0, 0, 0)
psnr2, ssim2 = 0, 0
if args.no_cnn:
squeeze_input = torch.squeeze(denormalise_lf(im_input))
squeeze_input = data_transform.torch_unstack(squeeze_input)
cpu_input = np.around(squeeze_input.numpy()).astype(np.uint8)
for i in range(grid_size):
row, col = i // grid_len, i % grid_len
if not args.no_save:
file_name = 'Colour{}{}.png'.format(row, col)
save_location = os.path.join(no_cnn_dir, file_name)
if i == 0:
print("Saving images of size ", cpu_input[i].shape)
image_warping.save_array_as_image(cpu_input[i], save_location)
if args.get_diff and not args.no_save:
colour = ground_truth[i]
diff = image_warping.get_diff_image(colour, cpu_output[i])
#diff = get_diff_image_floatint(res, colour)
file_name = 'Diff{}{}.png'.format(row, col)
save_location = os.path.join(no_cnn_dir, file_name)
image_warping.save_array_as_image(diff, save_location)
if not args.no_eval:
img = ground_truth[i]
psnr = evaluate.my_psnr(cpu_input[i], img)
ssim = evaluate.ssim(cpu_input[i], img)
psnr_accumulator = welford.update(psnr_accumulator, psnr)
ssim_accumulator = welford.update(ssim_accumulator, ssim)
psnr_mean, psnr_var, _ = welford.finalize(psnr_accumulator)
ssim_mean, ssim_var, _ = welford.finalize(ssim_accumulator)
print("For no cnn, psnr average {:5f}, stddev {:5f}".format(
psnr_mean, math.sqrt(psnr_var)))
print("For no cnn, ssim average {:5f}, stddev {:5f}".format(
ssim_mean, math.sqrt(ssim_var)))
psnr2, ssim2 = psnr_mean, ssim_mean
return psnr1, ssim1, psnr2, ssim2
