def test_net(cfg,
epoch_idx=-1,
output_dir=None,
test_data_loader=None,
test_writer=None,
encoder=None,
decoder=None,
merger=None):
# Load taxonomies of dataset
taxonomies = []
with open(cfg.DATASETS[cfg.DATASET.TEST_DATASET.upper()].TAXONOMY_FILE_PATH, encoding='utf-8') as file:
taxonomies = json.loads(file.read())
taxonomies = {t['taxonomy_id']: t for t in taxonomies}
# # Set up data loader
if test_data_loader is None:
# Set up data augmentation
IMG_SIZE = cfg.CONST.IMG_H, cfg.CONST.IMG_W
CROP_SIZE = cfg.CONST.CROP_IMG_H, cfg.CONST.CROP_IMG_W
test_transforms = utils.data_transforms.Compose([
utils.data_transforms.CenterCrop(IMG_SIZE, CROP_SIZE),
utils.data_transforms.RandomBackground(cfg.TEST.RANDOM_BG_COLOR_RANGE),
utils.data_transforms.Normalize(mean=cfg.DATASET.MEAN, std=cfg.DATASET.STD),
utils.data_transforms.ToTensor(),
])
dataset_loader = utils.data_loaders.DATASET_LOADER_MAPPING[cfg.DATASET.TEST_DATASET](cfg)
test_data_loader = paddle.io.DataLoader(dataset=dataset_loader.get_dataset(
utils.data_loaders.DatasetType.TEST, cfg.CONST.N_VIEWS_RENDERING, test_transforms),
batch_size=1,
# num_workers=1,
shuffle=False)
mode = 'test'
else:
mode = 'val'
# paddle.io.Dataset not support 'str' input
dataset_taxonomy = None
rendering_image_path_template = cfg.DATASETS.SHAPENET.RENDERING_PATH
volume_path_template = cfg.DATASETS.SHAPENET.VOXEL_PATH
# Load all taxonomies of the dataset
with open('./datasets/ShapeNet.json', encoding='utf-8') as file:
dataset_taxonomy = json.loads(file.read())
# print("[INFO]TEST-- open TAXONOMY_FILE_PATH succeess")
all_test_taxonomy_id_and_sample_name = []
# Load data for each category
for taxonomy in dataset_taxonomy:
taxonomy_folder_name = taxonomy['taxonomy_id']
# print('[INFO] %set -- Collecting files of Taxonomy[ID=%s, Name=%s]' %
# (mode, taxonomy['taxonomy_id'], taxonomy['taxonomy_name']))
samples = taxonomy[mode]
for sample in samples:
all_test_taxonomy_id_and_sample_name.append([taxonomy_folder_name, sample])
# print(len(all_test_taxonomy_id_and_sample_name))
# print(all_test_taxonomy_id_and_sample_name)
print('[INFO] Collected files of %set' % (mode))
# Set up networks
if decoder is None or encoder is None:
encoder = Encoder(cfg)
decoder = Decoder(cfg)
merger = Merger(cfg)
# if torch.cuda.is_available():
# encoder = paddle.DataParallel(encoder)
# decoder = paddle.DataParallel(decoder)
# merger = paddle.DataParallel(merger)
print('[INFO] %s Loading weights from %s ...' % (dt.now(), cfg.CONST.WEIGHTS))
encoder_state_dict = paddle.load(os.path.join(cfg.CONST.WEIGHTS, "encoder.pdparams"))
# encoder_solver_state_dict = paddle.load(os.path.join(cfg.CONST.WEIGHTS, "encoder_solver.pdopt"))
encoder.set_state_dict(encoder_state_dict)
# encoder_solver.set_state_dict(encoder_solver_state_dict)
decoder_state_dict = paddle.load(os.path.join(cfg.CONST.WEIGHTS, "decoder.pdparams"))
# decoder_solver_state_dict = paddle.load(os.path.join(cfg.CONST.WEIGHTS, "decoder_solver.pdopt"))
decoder.set_state_dict(decoder_state_dict)
# decoder_solver.set_state_dict(decoder_solver_state_dict)
if cfg.NETWORK.USE_MERGER:
merger_state_dict = paddle.load(os.path.join(cfg.CONST.WEIGHTS, "merger.pdparams"))
# merger_solver_state_dict = paddle.load(os.path.join(cfg.CONST.WEIGHTS, "merger_solver.pdopt"))
merger.set_state_dict(merger_state_dict)
# merger_solver.set_state_dict(merger_solver_state_dict)
# Set up loss functions
bce_loss = paddle.nn.BCELoss()
# Testing loop
n_samples = len(test_data_loader)
test_iou = dict()
encoder_losses = utils.network_utils.AverageMeter()
# Switch models to evaluation mode
encoder.eval()
decoder.eval()
merger.eval()
for sample_idx, (rendering_images, ground_truth_volume) in enumerate(test_data_loader):
taxonomy_id = all_test_taxonomy_id_and_sample_name[sample_idx][0]
sample_name = all_test_taxonomy_id_and_sample_name[sample_idx][1]
# print("all_test_taxonomy_id_and_sample_name")
# print(taxonomy_id)
# print(sample_name)
with paddle.no_grad():
# Get data from data loader
# rendering_images = utils.network_utils.var_or_cuda(rendering_images)
# ground_truth_volume = utils.network_utils.var_or_cuda(ground_truth_volume)
# Test the encoder, decoder and merger
image_features = encoder(rendering_images)
raw_features, generated_volume = decoder(image_features)
if cfg.NETWORK.USE_MERGER and epoch_idx >= cfg.TRAIN.EPOCH_START_USE_MERGER:
generated_volume = merger(raw_features, generated_volume)
else:
generated_volume = paddle.mean(generated_volume, axis=1)
encoder_loss = bce_loss(generated_volume, ground_truth_volume) * 10
# Append loss and accuracy to average metrics
encoder_losses.update(encoder_loss)
# IoU per sample
sample_iou = []
for th in cfg.TEST.VOXEL_THRESH:
# _volume = torch.ge(generated_volume, th).float()
# intersection = torch.sum(_volume.mul(ground_truth_volume)).float()
# union = torch.sum(torch.ge(_volume.add(ground_truth_volume), 1)).float()
# print("#################")
_volume = paddle.greater_equal(generated_volume, paddle.to_tensor(th)).astype("float32")
# print(_volume)
# print("@@@@@@@")
# print(ground_truth_volume)
intersection = paddle.sum(paddle.multiply(_volume, ground_truth_volume))
# print(paddle.greater_equal(paddle.add(_volume, ground_truth_volume).astype("float32"), paddle.to_tensor(1., dtype='float32')).astype("float32"))
union = paddle.sum(paddle.greater_equal(paddle.add(_volume, ground_truth_volume).astype("float32"), paddle.to_tensor(1., dtype='float32')).astype("float32"))
# print(union)
sample_iou.append((intersection / union))
# IoU per taxonomy
if taxonomy_id not in test_iou:
test_iou[taxonomy_id] = {'n_samples': 0, 'iou': []}
test_iou[taxonomy_id]['n_samples'] += 1
test_iou[taxonomy_id]['iou'].append(sample_iou)
# Append generated volumes to TensorBoard
if output_dir and sample_idx < 1:
img_dir = output_dir % 'images'
# Volume Visualization
gv = generated_volume.cpu().numpy()
rendering_views = utils.binvox_visualization.get_volume_views(gv, os.path.join(img_dir, 'Reconstructed'),
epoch_idx)
test_writer.add_image(tag='Reconstructed', img=rendering_views, step=epoch_idx)
gtv = ground_truth_volume.cpu().numpy()
rendering_views = utils.binvox_visualization.get_volume_views(gtv, os.path.join(img_dir, 'GroundTruth'),
epoch_idx)
test_writer.add_image(tag='GroundTruth', img=rendering_views, step=epoch_idx)
# Print sample loss and IoU
print('[INFO] %s Test[%d/%d] Taxonomy = %s Sample = %s EDLoss = %.4f IoU = %s' %
(dt.now(), sample_idx + 1, n_samples, taxonomy_id, sample_name, encoder_loss,
['%.4f' % si for si in sample_iou]))
# Output testing results
mean_iou = []
for taxonomy_id in test_iou:
test_iou[taxonomy_id]['iou'] = np.mean(test_iou[taxonomy_id]['iou'], axis=0)
mean_iou.append(test_iou[taxonomy_id]['iou'] * test_iou[taxonomy_id]['n_samples'])
mean_iou = np.sum(mean_iou, axis=0) / n_samples
# Print header
print('============================ TEST RESULTS ============================')
print('Taxonomy', end='\t')
print('#Sample', end='\t')
print('Baseline', end='\t')
for th in cfg.TEST.VOXEL_THRESH:
print('t=%.2f' % th, end='\t')
print()
# Print body
for taxonomy_id in test_iou:
print('%s' % taxonomies[taxonomy_id]['taxonomy_name'].ljust(8), end='\t')
print('%d' % test_iou[taxonomy_id]['n_samples'], end='\t')
if 'baseline' in taxonomies[taxonomy_id]:
print('%.4f' % taxonomies[taxonomy_id]['baseline']['%d-view' % cfg.CONST.N_VIEWS_RENDERING], end='\t\t')
else:
print('N/a', end='\t\t')
for ti in test_iou[taxonomy_id]['iou']:
print('%.4f' % ti, end='\t')
print()
# Print mean IoU for each threshold
print('Overall ', end='\t\t\t\t')
for mi in mean_iou:
print('%.4f' % mi, end='\t')
print('\n')
# Add testing results to TensorBoard
max_iou = np.max(mean_iou)
if test_writer is not None:
test_writer.add_scalar(tag='EncoderDecoder/EpochLoss', value=encoder_losses.avg, step=epoch_idx)
test_writer.add_scalar(tag='EncoderDecoder/IoU', value=max_iou, step=epoch_idx)
return max_iou
def train_net(cfg):
# Set up data augmentation
IMG_SIZE = cfg.CONST.IMG_H, cfg.CONST.IMG_W
CROP_SIZE = cfg.CONST.CROP_IMG_H, cfg.CONST.CROP_IMG_W
train_transforms = utils.data_transforms.Compose([
utils.data_transforms.RandomCrop(IMG_SIZE, CROP_SIZE),
utils.data_transforms.RandomBackground(
cfg.TRAIN.RANDOM_BG_COLOR_RANGE),
utils.data_transforms.ColorJitter(cfg.TRAIN.BRIGHTNESS,
cfg.TRAIN.CONTRAST,
cfg.TRAIN.SATURATION),
utils.data_transforms.RandomNoise(cfg.TRAIN.NOISE_STD),
utils.data_transforms.Normalize(mean=cfg.DATASET.MEAN,
std=cfg.DATASET.STD),
utils.data_transforms.RandomFlip(),
utils.data_transforms.RandomPermuteRGB(),
utils.data_transforms.ToTensor(),
])
val_transforms = utils.data_transforms.Compose([
utils.data_transforms.CenterCrop(IMG_SIZE, CROP_SIZE),
utils.data_transforms.RandomBackground(cfg.TEST.RANDOM_BG_COLOR_RANGE),
utils.data_transforms.Normalize(mean=cfg.DATASET.MEAN,
std=cfg.DATASET.STD),
utils.data_transforms.ToTensor(),
])
# Set up data loader
train_dataset_loader = utils.data_loaders.DATASET_LOADER_MAPPING[
cfg.DATASET.TRAIN_DATASET](cfg)
val_dataset_loader = utils.data_loaders.DATASET_LOADER_MAPPING[
cfg.DATASET.TEST_DATASET](cfg)
train_data_loader = paddle.io.DataLoader(
dataset=train_dataset_loader.get_dataset(
utils.data_loaders.DatasetType.TRAIN, cfg.CONST.N_VIEWS_RENDERING,
train_transforms),
batch_size=cfg.CONST.BATCH_SIZE,
#num_workers=0 , # cfg.TRAIN.NUM_WORKER>0时报错，因为dev/shm/太小 https://blog.csdn.net/ctypyb2002/article/details/107914643
#pin_memory=True,
use_shared_memory=False,
shuffle=True,
drop_last=True)
val_data_loader = paddle.io.DataLoader(
dataset=val_dataset_loader.get_dataset(
utils.data_loaders.DatasetType.VAL, cfg.CONST.N_VIEWS_RENDERING,
val_transforms),
batch_size=1,
#num_workers=1,
#pin_memory=True,
shuffle=False)
# Set up networks # paddle.Model prepare fit save
encoder = Encoder(cfg)
decoder = Decoder(cfg)
merger = Merger(cfg)
refiner = Refiner(cfg)
print('[DEBUG] %s Parameters in Encoder: %d.' %
(dt.now(), utils.network_utils.count_parameters(encoder)))
print('[DEBUG] %s Parameters in Decoder: %d.' %
(dt.now(), utils.network_utils.count_parameters(decoder)))
print('[DEBUG] %s Parameters in Merger: %d.' %
(dt.now(), utils.network_utils.count_parameters(merger)))
print('[DEBUG] %s Parameters in Refiner: %d.' %
(dt.now(), utils.network_utils.count_parameters(refiner)))
# # Initialize weights of networks # paddle的参数化不同，参见API
# encoder.apply(utils.network_utils.init_weights)
# decoder.apply(utils.network_utils.init_weights)
# merger.apply(utils.network_utils.init_weights)
# Set up learning rate scheduler to decay learning rates dynamically
encoder_lr_scheduler = paddle.optimizer.lr.MultiStepDecay(
learning_rate=cfg.TRAIN.ENCODER_LEARNING_RATE,
milestones=cfg.TRAIN.ENCODER_LR_MILESTONES,
gamma=cfg.TRAIN.GAMMA,
verbose=True)
decoder_lr_scheduler = paddle.optimizer.lr.MultiStepDecay(
learning_rate=cfg.TRAIN.DECODER_LEARNING_RATE,
milestones=cfg.TRAIN.DECODER_LR_MILESTONES,
gamma=cfg.TRAIN.GAMMA,
verbose=True)
merger_lr_scheduler = paddle.optimizer.lr.MultiStepDecay(
learning_rate=cfg.TRAIN.MERGER_LEARNING_RATE,
milestones=cfg.TRAIN.MERGER_LR_MILESTONES,
gamma=cfg.TRAIN.GAMMA,
verbose=True)
refiner_lr_scheduler = paddle.optimizer.lr.MultiStepDecay(
learning_rate=cfg.TRAIN.REFINER_LEARNING_RATE,
milestones=cfg.TRAIN.REFINER_LR_MILESTONES,
gamma=cfg.TRAIN.GAMMA,
verbose=True)
# Set up solver
# if cfg.TRAIN.POLICY == 'adam':
encoder_solver = paddle.optimizer.Adam(learning_rate=encoder_lr_scheduler,
parameters=encoder.parameters())
decoder_solver = paddle.optimizer.Adam(learning_rate=decoder_lr_scheduler,
parameters=decoder.parameters())
merger_solver = paddle.optimizer.Adam(learning_rate=merger_lr_scheduler,
parameters=merger.parameters())
refiner_solver = paddle.optimizer.Adam(learning_rate=refiner_lr_scheduler,
parameters=refiner.parameters())
# if torch.cuda.is_available():
# encoder = torch.nn.DataParallel(encoder).cuda()
# decoder = torch.nn.DataParallel(decoder).cuda()
# merger = torch.nn.DataParallel(merger).cuda()
# Set up loss functions
bce_loss = paddle.nn.BCELoss()
# Load pretrained model if exists
init_epoch = 0
best_iou = -1
best_epoch = -1
if 'WEIGHTS' in cfg.CONST and cfg.TRAIN.RESUME_TRAIN:
print('[INFO] %s Recovering from %s ...' %
(dt.now(), cfg.CONST.WEIGHTS))
# load
encoder_state_dict = paddle.load(
os.path.join(cfg.CONST.WEIGHTS, "encoder.pdparams"))
encoder_solver_state_dict = paddle.load(
os.path.join(cfg.CONST.WEIGHTS, "encoder_solver.pdopt"))
encoder.set_state_dict(encoder_state_dict)
encoder_solver.set_state_dict(encoder_solver_state_dict)
decoder_state_dict = paddle.load(
os.path.join(cfg.CONST.WEIGHTS, "decoder.pdparams"))
decoder_solver_state_dict = paddle.load(
os.path.join(cfg.CONST.WEIGHTS, "decoder_solver.pdopt"))
decoder.set_state_dict(decoder_state_dict)
decoder_solver.set_state_dict(decoder_solver_state_dict)
if cfg.NETWORK.USE_MERGER:
merger_state_dict = paddle.load(
os.path.join(cfg.CONST.WEIGHTS, "merger.pdparams"))
merger_solver_state_dict = paddle.load(
os.path.join(cfg.CONST.WEIGHTS, "merger_solver.pdopt"))
merger.set_state_dict(merger_state_dict)
merger_solver.set_state_dict(merger_solver_state_dict)
if cfg.NETWORK.USE_REFINER:
refiner_state_dict = paddle.load(
os.path.join(cfg.CONST.WEIGHTS, "refiner.pdparams"))
refiner_solver_state_dict = paddle.load(
os.path.join(cfg.CONST.WEIGHTS, "refiner_solver.pdopt"))
refiner.set_state_dict(refiner_state_dict)
refiner_solver.set_state_dict(refiner_solver_state_dict)
print(
'[INFO] %s Recover complete. Current epoch #%d, Best IoU = %.4f at epoch #%d.'
% (dt.now(), init_epoch, best_iou, best_epoch))
# Summary writer for TensorBoard
output_dir = os.path.join(cfg.DIR.OUT_PATH, '%s', dt.now().isoformat())
log_dir = output_dir % 'logs'
ckpt_dir = output_dir % 'checkpoints'
# train_writer = SummaryWriter()
# val_writer = SummaryWriter(os.path.join(log_dir, 'test'))
train_writer = LogWriter(os.path.join(log_dir, 'train'))
val_writer = LogWriter(os.path.join(log_dir, 'val'))
# Training loop
for epoch_idx in range(init_epoch, cfg.TRAIN.NUM_EPOCHES):
# Tick / tock
epoch_start_time = time()
# Batch average meterics
batch_time = utils.network_utils.AverageMeter()
data_time = utils.network_utils.AverageMeter()
encoder_losses = utils.network_utils.AverageMeter()
refiner_losses = utils.network_utils.AverageMeter()
# # switch models to training mode
encoder.train()
decoder.train()
merger.train()
refiner.train()
batch_end_time = time()
n_batches = len(train_data_loader)
# print("****debug: length of train data loder",n_batches)
for batch_idx, (rendering_images, ground_truth_volumes) in enumerate(
train_data_loader()):
# # debug
# if batch_idx>1:
# break
# Measure data time
data_time.update(time() - batch_end_time)
# print("****debug: batch_idx",batch_idx)
# print(rendering_images.shape)
# print(ground_truth_volumes.shape)
# Get data from data loader
rendering_images = utils.network_utils.var_or_cuda(
rendering_images)
ground_truth_volumes = utils.network_utils.var_or_cuda(
ground_truth_volumes)
# Train the encoder, decoder, and merger
image_features = encoder(rendering_images)
raw_features, generated_volumes = decoder(image_features)
if cfg.NETWORK.USE_MERGER and epoch_idx >= cfg.TRAIN.EPOCH_START_USE_MERGER:
generated_volumes = merger(raw_features, generated_volumes)
# else:
# mergered_volumes = paddle.mean(generated_volumes, aixs=1)
encoder_loss = bce_loss(generated_volumes,
ground_truth_volumes) * 10
if cfg.NETWORK.USE_REFINER and epoch_idx >= cfg.TRAIN.EPOCH_START_USE_REFINER:
generated_volumes = refiner(generated_volumes)
refiner_loss = bce_loss(generated_volumes,
ground_truth_volumes) * 10
# else:
# refiner_loss = encoder_loss
# Gradient decent
encoder_solver.clear_grad()
decoder_solver.clear_grad()
merger_solver.clear_grad()
refiner_solver.clear_grad()
if cfg.NETWORK.USE_REFINER and epoch_idx >= cfg.TRAIN.EPOCH_START_USE_REFINER:
encoder_loss.backward(retain_graph=True)
refiner_loss.backward()
# else:
# encoder_loss.backward()
encoder_solver.step()
decoder_solver.step()
merger_solver.step()
refiner_solver.step()
# Append loss to average metrics
encoder_losses.update(encoder_loss.numpy())
refiner_losses.update(refiner_loss.numpy())
# Append loss to TensorBoard
n_itr = epoch_idx * n_batches + batch_idx
train_writer.add_scalar(tag='EncoderDecoder/BatchLoss',
step=n_itr,
value=encoder_loss.numpy())
train_writer.add_scalar('Refiner/BatchLoss',
value=refiner_loss.numpy(),
step=n_itr)
# Tick / tock
batch_time.update(time() - batch_end_time)
batch_end_time = time()
if (batch_idx % int(cfg.CONST.INFO_BATCH)) == 0:
print(
'[INFO] %s [Epoch %d/%d][Batch %d/%d] BatchTime = %.3f (s) DataTime = %.3f (s) EDLoss = %.4f RLoss = %.4f'
% (dt.now(), epoch_idx + 1, cfg.TRAIN.NUM_EPOCHES,
batch_idx + 1, n_batches, batch_time.val, data_time.val,
encoder_loss.numpy(), refiner_loss.numpy()))
# Append epoch loss to TensorBoard
train_writer.add_scalar(tag='EncoderDecoder/EpochLoss',
step=epoch_idx + 1,
value=encoder_losses.avg)
train_writer.add_scalar('Refiner/EpochLoss',
value=refiner_losses.avg,
step=epoch_idx + 1)
# update scheduler each step
encoder_lr_scheduler.step()
decoder_lr_scheduler.step()
merger_lr_scheduler.step()
refiner_lr_scheduler.step()
# Tick / tock
epoch_end_time = time()
print(
'[INFO] %s Epoch [%d/%d] EpochTime = %.3f (s) EDLoss = %.4f RLoss = %.4f'
% (dt.now(), epoch_idx + 1, cfg.TRAIN.NUM_EPOCHES, epoch_end_time -
epoch_start_time, encoder_losses.avg, refiner_losses.avg))
# Update Rendering Views
if cfg.TRAIN.UPDATE_N_VIEWS_RENDERING:
n_views_rendering = random.randint(1, cfg.CONST.N_VIEWS_RENDERING)
train_data_loader.dataset.set_n_views_rendering(n_views_rendering)
print('[INFO] %s Epoch [%d/%d] Update #RenderingViews to %d' %
(dt.now(), epoch_idx + 2, cfg.TRAIN.NUM_EPOCHES,
n_views_rendering))
# Validate the training models
iou = test_net(cfg, epoch_idx + 1, output_dir, val_data_loader,
val_writer, encoder, decoder, merger, refiner)
# Save weights to file
if (epoch_idx + 1) % cfg.TRAIN.SAVE_FREQ == 0:
if not os.path.exists(ckpt_dir):
os.makedirs(ckpt_dir)
utils.network_utils.save_checkpoints(
cfg, os.path.join(ckpt_dir,
'ckpt-epoch-%04d' % (epoch_idx + 1)),
epoch_idx + 1, encoder, encoder_solver, decoder,
decoder_solver, merger, merger_solver, refiner, refiner_solver,
best_iou, best_epoch)
if iou > best_iou:
if not os.path.exists(ckpt_dir):
os.makedirs(ckpt_dir)
best_iou = iou
best_epoch = epoch_idx + 1
utils.network_utils.save_checkpoints(
cfg, os.path.join(ckpt_dir, 'best-ckpt'), epoch_idx + 1,
encoder, encoder_solver, decoder, decoder_solver, merger,
merger_solver, refiner, refiner_solver, best_iou, best_epoch)
def demo_net(cfg, imgs_path):
encoder = Encoder(cfg)
decoder = Decoder(cfg)
merger = Merger(cfg)
print('[INFO] %s Loading weights from %s ...' %
(dt.now(), cfg.CONST.WEIGHTS))
encoder_state_dict = paddle.load(
os.path.join(cfg.CONST.WEIGHTS, "encoder.pdparams"))
encoder.set_state_dict(encoder_state_dict)
decoder_state_dict = paddle.load(
os.path.join(cfg.CONST.WEIGHTS, "decoder.pdparams"))
decoder.set_state_dict(decoder_state_dict)
if cfg.NETWORK.USE_MERGER:
merger_state_dict = paddle.load(
os.path.join(cfg.CONST.WEIGHTS, "merger.pdparams"))
merger.set_state_dict(merger_state_dict)
# Switch models to evaluation mode
encoder.eval()
decoder.eval()
merger.eval()
rendering_images = []
if os.path.isfile(imgs_path):
print("demo img")
rendering_image = cv2.imread(imgs_path, cv2.IMREAD_UNCHANGED).astype(
np.float32) / 255.
rendering_image = np.asarray(rendering_image)[np.newaxis, :, :, :]
# print(rendering_image.shape)
IMG_SIZE = cfg.CONST.IMG_H, cfg.CONST.IMG_W
CROP_SIZE = cfg.CONST.CROP_IMG_H, cfg.CONST.CROP_IMG_W
test_transforms = utils.data_transforms.Compose([
utils.data_transforms.CenterCrop(IMG_SIZE, CROP_SIZE),
utils.data_transforms.RandomBackground(
cfg.TEST.RANDOM_BG_COLOR_RANGE),
utils.data_transforms.Normalize(mean=cfg.DATASET.MEAN,
std=cfg.DATASET.STD),
utils.data_transforms.ToTensor(),
])
rendering_image = test_transforms(rendering_image)
# print(rendering_image)
rendering_image = paddle.reshape(rendering_image, [1, 1, 3, 224, 224])
with paddle.no_grad():
# Get data from data loader
rendering_image = utils.network_utils.var_or_cuda(rendering_image)
# Test the encoder, decoder and merger
image_features = encoder(rendering_image)
raw_features, generated_volume = decoder(image_features)
if cfg.NETWORK.USE_MERGER:
generated_volume = merger(raw_features, generated_volume)
else:
generated_volume = paddle.mean(generated_volume, axis=1)
for th in cfg.TEST.DEMO_VOXEL_THRESH:
_volume = paddle.greater_equal(
generated_volume, paddle.to_tensor(th)).astype("float32")
_volume = paddle.reshape(_volume, [32, 32, 32])
# print(_volume.shape)
# print(_volume)
# Append generated volumes to TensorBoard
if cfg.DIR.OUT_PATH:
# Volume Visualization
pred_file_name = os.path.join(
cfg.DIR.OUT_PATH,
imgs_path.split('/')[-1].split('.')[0] + '.obj')
print("save ", pred_file_name)
utils.voxel.voxel2obj(pred_file_name,
_volume.cpu().numpy())
elif os.path.isdir(imgs_path):
print("demo dir")
rendering_files_path = os.listdir(imgs_path)
for rendering_file_path in rendering_files_path:
if '.png' not in rendering_file_path:
continue
print(os.path.join(imgs_path, rendering_file_path))
rendering_image = cv2.imread(
os.path.join(imgs_path, rendering_file_path),
cv2.IMREAD_UNCHANGED).astype(np.float32) / 255.
rendering_image = np.asarray(rendering_image)[np.newaxis, :, :, :]
# print(rendering_image.shape)
IMG_SIZE = cfg.CONST.IMG_H, cfg.CONST.IMG_W
CROP_SIZE = cfg.CONST.CROP_IMG_H, cfg.CONST.CROP_IMG_W
test_transforms = utils.data_transforms.Compose([
utils.data_transforms.CenterCrop(IMG_SIZE, CROP_SIZE),
utils.data_transforms.RandomBackground(
cfg.TEST.RANDOM_BG_COLOR_RANGE),
utils.data_transforms.Normalize(mean=cfg.DATASET.MEAN,
std=cfg.DATASET.STD),
utils.data_transforms.ToTensor(),
])
rendering_image = test_transforms(rendering_image)
# print(rendering_image)
rendering_image = paddle.reshape(rendering_image,
[1, 1, 3, 224, 224])
with paddle.no_grad():
# Get data from data loader
rendering_image = utils.network_utils.var_or_cuda(
rendering_image)
# Test the encoder, decoder and merger
image_features = encoder(rendering_image)
raw_features, generated_volume = decoder(image_features)
if cfg.NETWORK.USE_MERGER:
generated_volume = merger(raw_features, generated_volume)
else:
generated_volume = paddle.mean(generated_volume, axis=1)
# for th in cfg.TEST.VOXEL_THRESH:
# _volume = paddle.greater_equal(generated_volume, paddle.to_tensor(th)).astype("float32")
# print(_volume.shape)
# Append generated volumes to TensorBoard
if cfg.DIR.OUT_PATH:
# Volume Visualization
gv = generated_volume.detach().cpu().numpy()
pred_file_name = os.path.join(
cfg.DIR.OUT_PATH, imgs_path,
rendering_file_path.split('.')[0] + '.obj')
utils.voxel.voxel2obj(
pred_file_name, gv[0, 1] > cfg.TEST.DEMO_VOXEL_THRESH)
else:
raise Exception("error input path")
