Long-Range-Grouping-Transformer
Long-Range-Grouping-Transformer copied to clipboard
Published
20 hours ago •
LiyingCV
LiyingCV
How can we create a demo file to test trained models and visualize results?
Greetings!!! I'm sorry to bother you again. Now that the model has been trained, I would like to ask for advice on how to test and generate a 3D voxel model using your own images. I will be grateful if model visualization script is collected in a test file.
Thank you very much for your reply, following your instructions, I referred to Pix2Vox and got the following visualization script showed as below: `
encoder = Encoder(cfg)
decoder = Decoder(cfg)
merger = Merger(cfg)
# cfg.CONST.WEIGHTS = '/home/caig/Desktop/pix2vox/Pix2Vox/pretrain/Pix2Vox-A-ShapeNet.pth'
cfg.CONST.WEIGHTS = './pths/UMIFormer.pth'
checkpoint = torch.load(cfg.CONST.WEIGHTS, map_location=torch.device('cpu'))
fix_checkpoint = {}
fix_checkpoint['encoder_state_dict'] = OrderedDict(
(k.split('module.')[1:][0], v) for k, v in checkpoint['encoder_state_dict'].items())
fix_checkpoint['decoder_state_dict'] = OrderedDict(
(k.split('module.')[1:][0], v) for k, v in checkpoint['decoder_state_dict'].items())
fix_checkpoint['merger_state_dict'] = OrderedDict(
(k.split('module.')[1:][0], v) for k, v in checkpoint['merger_state_dict'].items())
# fix_checkpoint['refiner_state_dict'] = OrderedDict(
# (k.split('module.')[1:][0], v) for k, v in checkpoint['refiner_state_dict'].items())
epoch_idx = checkpoint['epoch_idx']
encoder.load_state_dict(fix_checkpoint['encoder_state_dict'])
decoder.load_state_dict(fix_checkpoint['decoder_state_dict'])
merger.load_state_dict(fix_checkpoint['merger_state_dict'])
# if cfg.NETWORK.USE_REFINER:
# print('Use refiner')
# refiner.load_state_dict(fix_checkpoint['refiner_state_dict'])
# if cfg.NETWORK.USE_MERGER:
# print('Use merger')
# merger.load_state_dict(fix_checkpoint['merger_state_dict'])
encoder.eval()
decoder.eval()
merger.eval()
# refiner.eval()
# img1_path = './datasets/ShapeNet/ShapeNetRendering/03211117/1a92363c2a155ed3c397356311cbeea4/rendering/17.png'
img1_path = './datasets/Pix3D/img/chair/0016.png'
img1_np = cv2.imread(img1_path, cv2.IMREAD_UNCHANGED).astype(np.float32) / 255.
sample = np.array([img1_np])
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_images = test_transforms(rendering_images=sample)
rendering_images = rendering_images.unsqueeze(0)
with torch.no_grad():
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 = torch.mean(generated_volume, dim=1)
# if cfg.NETWORK.USE_REFINER and epoch_idx >= cfg.TRAIN.EPOCH_START_USE_REFINER:
# generated_volume = refiner(generated_volume)
generated_volume = merger(raw_features, generated_volume)
generated_volume = generated_volume.squeeze(0)
img_dir = './output/TestResult'
gv = generated_volume.cpu().numpy()
gv_new = np.swapaxes(gv, 2, 1)
rendering_views = utils.binvox_visualization.get_volume_views(gv_new, os.path.join(img_dir),
epoch_idx)`
I am using this script in the runner.py `
# Start train/test process
if not args.test and not args.batch_test:
train_net(cfg)
else:
if 'WEIGHTS' in cfg.CONST and os.path.exists(cfg.CONST.WEIGHTS):
if args.test:
test_net(test_single)
elif args.batch_test:
batch_test(cfg)
else:
logging.error('Please specify the file path of checkpoint.')
sys.exit(2)
` however, there is still something wrong when I try to generate the voxel model, and the Traceback info
_warnings.warn(
Traceback (most recent call last):
File "runner.py", line 20, in <module>
from core.test_single_image import test_single
File "/root/UMIFormer/core/test_single_image.py", line 16, in <module>
class test_single():
File "/root/UMIFormer/core/test_single_image.py", line 18, in test_single
encoder = Encoder(cfg)
File "/root/UMIFormer/models/encoder/encoder_vit_ivdb.py", line 21, in __init__
self.encoder = self.create_model(
File "/root/UMIFormer/models/encoder/encoder_vit_ivdb.py", line 57, in create_model
return self._create_vision_transformer(
File "/root/UMIFormer/models/encoder/encoder_vit_ivdb.py", line 43, in _create_vision_transformer
model = self.decoupling_type(
File "/root/UMIFormer/models/encoder/encoder_vit_ivdb.py", line 200, in __init__
if torch.distributed.get_rank() == 0:
File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/distributed_c10d.py", line 822, in get_rank
default_pg = _get_default_group()
File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/distributed_c10d.py", line 410, in _get_default_group
raise RuntimeError(
RuntimeError: Default process group has not been initialized, please make sure to call init_process_group.
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 13409) of binary: /root/miniconda3/bin/python
Traceback (most recent call last):
File "/root/miniconda3/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/root/miniconda3/lib/python3.8/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/launch.py", line 193, in <module>
main()
File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/launch.py", line 189, in main
launch(args)
File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/launch.py", line 174, in launch
run(args)
File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/run.py", line 710, in run
elastic_launch(
File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 131, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 259, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
============================================================
runner.py FAILED
------------------------------------------------------------
Failures:
<NO_OTHER_FAILURES>
------------------------------------------------------------
Root Cause (first observed failure):
[0]:
time : 2024-01-13_12:59:56
host : autodl-container-d82911a03c-d427ecf0
rank : 0 (local_rank: 0)
exitcode : 1 (pid: 13409)
error_file: <N/A>_
so, what should I do to fix this? Thank you very much!!! （I'm really sorry for my weak coding skills (༎ຶ ෴ ༎ຶ)）
Thank you very much for your reply, following your instructions, I referred to Pix2Vox and got the following visualization script showed as below: `
encoder = Encoder(cfg) decoder = Decoder(cfg) merger = Merger(cfg) # cfg.CONST.WEIGHTS = '/home/caig/Desktop/pix2vox/Pix2Vox/pretrain/Pix2Vox-A-ShapeNet.pth' cfg.CONST.WEIGHTS = './pths/UMIFormer.pth' checkpoint = torch.load(cfg.CONST.WEIGHTS, map_location=torch.device('cpu')) fix_checkpoint = {} fix_checkpoint['encoder_state_dict'] = OrderedDict( (k.split('module.')[1:][0], v) for k, v in checkpoint['encoder_state_dict'].items()) fix_checkpoint['decoder_state_dict'] = OrderedDict( (k.split('module.')[1:][0], v) for k, v in checkpoint['decoder_state_dict'].items()) fix_checkpoint['merger_state_dict'] = OrderedDict( (k.split('module.')[1:][0], v) for k, v in checkpoint['merger_state_dict'].items()) # fix_checkpoint['refiner_state_dict'] = OrderedDict( # (k.split('module.')[1:][0], v) for k, v in checkpoint['refiner_state_dict'].items()) epoch_idx = checkpoint['epoch_idx'] encoder.load_state_dict(fix_checkpoint['encoder_state_dict']) decoder.load_state_dict(fix_checkpoint['decoder_state_dict']) merger.load_state_dict(fix_checkpoint['merger_state_dict']) # if cfg.NETWORK.USE_REFINER: # print('Use refiner') # refiner.load_state_dict(fix_checkpoint['refiner_state_dict']) # if cfg.NETWORK.USE_MERGER: # print('Use merger') # merger.load_state_dict(fix_checkpoint['merger_state_dict']) encoder.eval() decoder.eval() merger.eval() # refiner.eval() # img1_path = './datasets/ShapeNet/ShapeNetRendering/03211117/1a92363c2a155ed3c397356311cbeea4/rendering/17.png' img1_path = './datasets/Pix3D/img/chair/0016.png' img1_np = cv2.imread(img1_path, cv2.IMREAD_UNCHANGED).astype(np.float32) / 255. sample = np.array([img1_np]) 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_images = test_transforms(rendering_images=sample) rendering_images = rendering_images.unsqueeze(0) with torch.no_grad(): 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 = torch.mean(generated_volume, dim=1) # if cfg.NETWORK.USE_REFINER and epoch_idx >= cfg.TRAIN.EPOCH_START_USE_REFINER: # generated_volume = refiner(generated_volume) generated_volume = merger(raw_features, generated_volume) generated_volume = generated_volume.squeeze(0) img_dir = './output/TestResult' gv = generated_volume.cpu().numpy() gv_new = np.swapaxes(gv, 2, 1) rendering_views = utils.binvox_visualization.get_volume_views(gv_new, os.path.join(img_dir), epoch_idx)`I am using this script in the runner.py `
# Start train/test process if not args.test and not args.batch_test: train_net(cfg) else: if 'WEIGHTS' in cfg.CONST and os.path.exists(cfg.CONST.WEIGHTS): if args.test: test_net(test_single) elif args.batch_test: batch_test(cfg) else: logging.error('Please specify the file path of checkpoint.') sys.exit(2)` however, there is still something wrong when I try to generate the voxel model, and the Traceback info
_warnings.warn( Traceback (most recent call last): File "runner.py", line 20, in <module> from core.test_single_image import test_single File "/root/UMIFormer/core/test_single_image.py", line 16, in <module> class test_single(): File "/root/UMIFormer/core/test_single_image.py", line 18, in test_single encoder = Encoder(cfg) File "/root/UMIFormer/models/encoder/encoder_vit_ivdb.py", line 21, in __init__ self.encoder = self.create_model( File "/root/UMIFormer/models/encoder/encoder_vit_ivdb.py", line 57, in create_model return self._create_vision_transformer( File "/root/UMIFormer/models/encoder/encoder_vit_ivdb.py", line 43, in _create_vision_transformer model = self.decoupling_type( File "/root/UMIFormer/models/encoder/encoder_vit_ivdb.py", line 200, in __init__ if torch.distributed.get_rank() == 0: File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/distributed_c10d.py", line 822, in get_rank default_pg = _get_default_group() File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/distributed_c10d.py", line 410, in _get_default_group raise RuntimeError( RuntimeError: Default process group has not been initialized, please make sure to call init_process_group. ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 13409) of binary: /root/miniconda3/bin/python Traceback (most recent call last): File "/root/miniconda3/lib/python3.8/runpy.py", line 194, in _run_module_as_main return _run_code(code, main_globals, None, File "/root/miniconda3/lib/python3.8/runpy.py", line 87, in _run_code exec(code, run_globals) File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/launch.py", line 193, in <module> main() File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/launch.py", line 189, in main launch(args) File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/launch.py", line 174, in launch run(args) File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/run.py", line 710, in run elastic_launch( File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 131, in __call__ return launch_agent(self._config, self._entrypoint, list(args)) File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 259, in launch_agent raise ChildFailedError( torch.distributed.elastic.multiprocessing.errors.ChildFailedError: ============================================================ runner.py FAILED ------------------------------------------------------------ Failures: <NO_OTHER_FAILURES> ------------------------------------------------------------ Root Cause (first observed failure): [0]: time : 2024-01-13_12:59:56 host : autodl-container-d82911a03c-d427ecf0 rank : 0 (local_rank: 0) exitcode : 1 (pid: 13409) error_file: <N/A>_so, what should I do to fix this? Thank you very much!!! （I'm really sorry for my weak coding skills (༎ຶ ෴ ༎ຶ)）
It seems like you made some mistakes about the initialization of Encoder. Please check your code.