apple / ml-gmpi Goto Github PK
View Code? Open in Web Editor NEW[ECCV 2022, Oral Presentation] Official PyTorch implementation of GMPI
License: Other
[ECCV 2022, Oral Presentation] Official PyTorch implementation of GMPI
License: Other
Hi, I got error below when I start to train model with this command CUDA_VISIBLE_DEVICES=2,3,4,5,6 python launch.py --run_dataset FFHQ256 --nproc_per_node 0 --task-type gmpi --run-type train master_port 8378
but I can't figure out the reason.
I guess this error is occurred inside train.py's 313 code line if rank == 0:
But I'm not sure. If anyone has solved the problem, please help!
Setting up PyTorch plugin "bias_act_plugin"...
Using /root/.cache/torch_extensions/py38_cu113 as PyTorch extensions root...
Detected CUDA files, patching ldflags
Emitting ninja build file /root/.cache/torch_extensions/py38_cu113/bias_act_plugin/build.ninja...
Building extension module bias_act_plugin...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
ninja: no work to do.
Loading extension module bias_act_plugin...
Done setting up PyTorch plugin "bias_act_plugin".
Traceback (most recent call last):
File "/data/eden/ml-gmpi/run_gmpi.py", line 115, in <module>
main()
File "/data/eden/ml-gmpi/run_gmpi.py", line 49, in main
run_exp(**vars(args))
File "/data/eden/ml-gmpi/run_gmpi.py", line 110, in run_exp
mp.spawn(train, args=(num_gpus, config, master_port, run_dataset), nprocs=num_gpus, join=True)
File "/opt/conda/envs/gmpi/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 240, in spawn
return start_processes(fn, args, nprocs, join, daemon, start_method='spawn')
File "/opt/conda/envs/gmpi/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 198, in start_processes
while not context.join():
File "/opt/conda/envs/gmpi/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 140, in join
raise ProcessExitedException(
torch.multiprocessing.spawn.ProcessExitedException: process 0 terminated with signal SIGSEGV
/opt/conda/envs/gmpi/lib/python3.8/multiprocessing/resource_tracker.py:216: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown
warnings.warn('resource_tracker: There appear to be %d
Hi.....
When I tried to calculate the Depth score for given pretrained model on FFHQ256.
The score where:
depth: 0.53399503 0.35273126
angle: 0.004 0.006
After training the model from scratch for FFHQ256
The score where:
depth: 0.5855465 0.41952634
angle: 0.004 0.008
After training the model from scratch for FFHQ512
The score where different as compare to scores given in the table
depth: 0.523077 0.33253828
angle: 0.004 0.008
Hi, Can you Please provide the FFHQ data as, I am unable to download the ffhq dataset from the given google drive (https://drive.google.com/drive/folders/1LTBpJ0W_WLjqza3zdayligS8Dh1V1gA6) due to exceed off quota limit.
It would be great If you can provide the FFHQ processed dataset(FFHQ256X256, FFHQ512X512, FFHQ1024X1024).
Looking forward for your reply
Hi....
I have used same script as provided the documentation for the evaluation code
Script :
bash {GMPI_ROOT}/gmpi/eval/eval.sh {GMPI_ROOT} FFHQ256 20220727_102024290372 ${Deep3DFaceRecon_PATH} debug
But I am getting some error in calculating FID and KID Can you Please help me in this :
real_dir: /proj/cvl/users/x_fahkh/mn/ml-gmpi/runtime_dataset/real_data/FFHQ256/FFHQ_real_res_256_n_50000
Traceback (most recent call last):
File "/proj/cvl/users/x_fahkh/mn/ml-gmpi/gmpi/eval/prepare_fake_data.py", line 280, in
main(opt)
File "/proj/cvl/users/x_fahkh/mn/ml-gmpi/gmpi/eval/prepare_fake_data.py", line 96, in main
config = Config(init_dict=torch.load(opt.exp_config, map_location="cpu")["config"])
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch/serialization.py", line 594, in load
with _open_file_like(f, 'rb') as opened_file:
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch/serialization.py", line 230, in _open_file_like
return _open_file(name_or_buffer, mode)
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch/serialization.py", line 211, in init
super(_open_file, self).init(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: '/proj/cvl/users/x_fahkh/mn/ml-gmpi/ckpts/gmpi_pretrained/20220727_102024290372/config.pth'
Compute FID/KID from
real: /proj/cvl/users/x_fahkh/mn/ml-gmpi/runtime_dataset/real_data/FFHQ256/FFHQ_real_res_256_n_50000
fake: /proj/cvl/users/x_fahkh/mn/ml-gmpi/ckpts/gmpi_pretrained/20220727_102024290372/planes_96_n_50000/psi_1.0/fid_kid/rgb
Creating feature extractor "inception-v3-compat" with features ['2048']
Extracting features from input1
Traceback (most recent call last):
File "/proj/cvl/users/x_fahkh/mn/ml-gmpi/gmpi/eval/compute_fid_kid.py", line 29, in
verbose=True,
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch_fidelity/metrics.py", line 239, in calculate_metrics
featuresdict_1 = extract_featuresdict_from_input_id_cached(1, feat_extractor, **kwargs)
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch_fidelity/utils.py", line 372, in extract_featuresdict_from_input_id_cached
featuresdict = fn_recompute()
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch_fidelity/utils.py", line 360, in fn_recompute
return extract_featuresdict_from_input_id(input_id, feat_extractor, **kwargs)
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch_fidelity/utils.py", line 342, in extract_featuresdict_from_input_id
input = prepare_input_from_id(input_id, **kwargs)
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch_fidelity/utils.py", line 275, in prepare_input_from_id
return prepare_input_from_descriptor(input_desc, **kwargs)
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch_fidelity/utils.py", line 255, in prepare_input_from_descriptor
f'Input descriptor "input" field can be either an instance of Dataset, GenerativeModelBase class, or a string, '
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch_fidelity/helpers.py", line 9, in vassert
raise ValueError(message)
ValueError: Input descriptor "input" field can be either an instance of Dataset, GenerativeModelBase class, or a string, such as a path to a name of a registered dataset (cifar10-train, cifar10-val, stl10-train, stl10-test, stl10-unlabeled), a directory with file samples, or a path to an ONNX or PTH (JIT) module
Can you Please help me in this......
I have Some conceptual queries regarding the code:
When I put the random_pose = False in line 396 of mpi_rendering.py and pass the same pose as given by the dataloader([flat_w2c_mats_real] line 419 train.py ) to self.mpi() function [line 451 mpi_renderer.py] then after 6 iteration on 8 gpu the error arises .
Error:
pos: tensor([[0.5797, 0.0647, 0.1850]], device='cuda:0')
dir: tensor([[-0.6583, -0.1611, 0.7355]], device='cuda:0')
u: tensor([-1.0399, -1.0401, -1.0398, -1.0396], device='cuda:0')
v: tensor([-0.6758, -0.6710, -0.6656, -0.6603], device='cuda:0')
yaws: [[-0.6179566383361816]]
pitches: [[0.07507812976837158]]
Traceback (most recent call last):
File "/proj/cvl/users/x_fahkh/mn/debug-dmpi/gmpi/core/mpi.py", line 106, in homography
assert torch.min(u) >= -1, f"Ray's U direction goes out of plane at {distance}, min val {torch.min(u)}"
AssertionError: Ray's U direction goes out of plane at tensor([[1.1200]], device='cuda:0'), min val -1.0400704145431519
The question is that how is it possible that extrinsic parameter[flat_w2c_mats_real] of real image to leads out of plane of the rays.
Very nice work. How did you generate the camera poses for AFHQ dataset, can you give me a more detailed method?
Thank you for amazing work again.
I have some trouble to reproducing fid score..
Thank you so much.
Script for evaluating :
bash {GMPI_ROOT}/gmpi/eval/eval.sh {GMPI_ROOT} FFHQ512 20220727_104512601146 {Deep3DFaceRecon_PATH} nodebug
Can you Please help me in fixing the issue for evaluating the code for FFHQ512....
Error:
Load weights from /proj/cvl/users/x_fahkh/mn/ml-gmpi/ckpts/gmpi_pretrained/20220727_104512601146/generator.pth
Load weights from /proj/cvl/users/x_fahkh/mn/ml-gmpi/ckpts/gmpi_pretrained/20220727_104512601146/ema.pth
save_dir: /proj/cvl/users/x_fahkh/mn/ml-gmpi/ckpts/gmpi_pretrained/20220727_104512601146/planes_96_n_50000/psi_1.0/fid_kid/rgb
0%| | 0/50000 [00:00<?, ?it/s]
log: torch.Size([1, 96, 4, 512, 512]) (1, 512, 512, 3) (1, 512, 512, 1)
100%|█████████████████████████████████████████████████████████████████████████████████████████████████| 50000/50000 [3:22:49<00:00, 4.11it/s]
Compute FID/KID from
real: /proj/cvl/users/x_fahkh/mn/ml-gmpi/runtime_dataset/real_data/FFHQ512/FFHQ_real_res_512_n_50000
fake: /proj/cvl/users/x_fahkh/mn/ml-gmpi/ckpts/gmpi_pretrained/20220727_104512601146/planes_96_n_50000/psi_1.0/fid_kid/rgb
Creating feature extractor "inception-v3-compat" with features ['2048']
Extracting features from input1
Looking for samples non-recursivelty in "/proj/cvl/users/x_fahkh/mn/ml-gmpi/ckpts/gmpi_pretrained/20220727_104512601146/planes_96_n_50000/psi_1.0/fid_kid/rgb" with extensions png,jpg,jpeg
Found 50000 samples
Processing samples
Extracting features from input2
Looking for samples non-recursivelty in "/proj/cvl/users/x_fahkh/mn/ml-gmpi/runtime_dataset/real_data/FFHQ512/FFHQ_real_res_512_n_50000" with extensions png,jpg,jpeg
Found 71 samples
Traceback (most recent call last):
File "/proj/cvl/users/x_fahkh/mn/ml-gmpi/gmpi/eval/compute_fid_kid.py", line 29, in
verbose=True,
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch_fidelity/metrics.py", line 243, in calculate_metrics
featuresdict_2 = extract_featuresdict_from_input_id_cached(2, feat_extractor, **kwargs)
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch_fidelity/utils.py", line 372, in extract_featuresdict_from_input_id_cached
featuresdict = fn_recompute()
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch_fidelity/utils.py", line 360, in fn_recompute
return extract_featuresdict_from_input_id(input_id, feat_extractor, **kwargs)
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch_fidelity/utils.py", line 345, in extract_featuresdict_from_input_id
featuresdict = get_featuresdict_from_dataset(input, feat_extractor, batch_size, cuda, save_cpu_ram, verbose)
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch_fidelity/utils.py", line 111, in get_featuresdict_from_dataset
for bid, batch in enumerate(dataloader):
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 521, in next
data = self._next_data()
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1183, in _next_data
return self._process_data(data)
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1229, in _process_data
data.reraise()
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch/_utils.py", line 425, in reraise
raise self.exc_type(msg)
OSError: Caught OSError in DataLoader worker process 1.
Original Traceback (most recent call last):
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
data = fetcher.fetch(index)
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch_fidelity/datasets.py", line 31, in getitem
img = Image.open(path).convert('RGB')
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/PIL/Image.py", line 2822, in open
raise IOError("cannot identify image file %r" % (filename if filename else fp))
OSError: cannot identify image file '/proj/cvl/users/x_fahkh/mn/ml-gmpi/runtime_dataset/real_data/FFHQ512/FFHQ_real_res_512_n_50000/00070.png'
Can you Please have a look to this
In the TRAIN_EVAL.md, you used the following commands for estimating camera pose:
# For FFHQ
cd ${Deep3DFaceRecon_PATH}
python estimate_pose_ffhq.py --name=pretrained --epoch=20 --img_folder=${GMPI_ROOT}/runtime_dataset/dummy --gmpi_img_res ${RES} --gmpi_root ${GMPI_ROOT}
# For MetFace
cd ${Deep3DFaceRecon_PATH}
python estimate_pose_metfaces.py --name=pretrained --epoch=20 --img_folder=${GMPI_ROOT}/runtime_dataset/dummy --gmpi_root ${GMPI_ROOT}
However, I can not find these codes in the Deep3DFaceRecon_pytorch repository.
I guess you newly made these python files. Could you share these files?
Collecting package metadata (repodata.json): done
Solving environment: failed
ResolvePackageNotFound:
hi, when I try to run this command:
export PYTHONPATH=${GMPI_ROOT}:${GMPI_ROOT}/gmpi/models:$PYTHONPATH && \
python ${GMPI_ROOT}/gmpi/eval/vis/render_video.py \
--ckpt_path ${OUTPUT_DIR}/generator.pth \
--output_dir ${OUTPUT_DIR} \
--seeds ${SEED} \
--nplanes 96 \
--truncation_psi ${TRUNCATION_PSI} \
--exp_config ${OUTPUT_DIR}/config.pth \
--render_single_image 1
Then I meet this error, and my cuda version is 11.1
ImportError: /data/run01/scz5914/.cache/torch_extensions/upfirdn2d_plugin/upfirdn2d_plugin.so:
undefined symbol: _ZNSt15__exception_ptr13exception_ptr9_M_addrefEv
warnings.warn('Failed to build CUDA kernels for upfirdn2d. Falling back to slow reference implementation. Details:\n\n' + traceback.format_exc())
Fortunately, this error doesn't block the render image generating.
But I really hope to get faster inference speed.
So, do you know how to solve this problem?
PS: full error info
/HOME/scz5914/run/huangan_work/ml-gmpi/gmpi/models/torch_utils/ops/upfirdn2d.py:34: UserWarning: Failed to build CUDA kernels for upfirdn2d. Falling back to slow reference implementation. Details:
Traceback (most recent call last):
File "/HOME/scz5914/run/huangan_work/ml-gmpi/gmpi/models/torch_utils/ops/upfirdn2d.py", line 32, in _init
_plugin = custom_ops.get_plugin('upfirdn2d_plugin', sources=sources, extra_cuda_cflags=['--use_fast_math'])
File "/HOME/scz5914/run/huangan_work/ml-gmpi/gmpi/models/torch_utils/custom_ops.py", line 110, in get_plugin
torch.utils.cpp_extension.load(name=module_name, verbose=verbose_build, sources=sources, **build_kwargs)
File "/HOME/scz5914/.conda/envs/gmpi/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1092, in load
keep_intermediates=keep_intermediates)
File "/HOME/scz5914/.conda/envs/gmpi/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1318, in _jit_compile
return _import_module_from_library(name, build_directory, is_python_module)
File "/HOME/scz5914/.conda/envs/gmpi/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1701, in _import_module_from_library
module = importlib.util.module_from_spec(spec)
File "<frozen importlib._bootstrap>", line 583, in module_from_spec
File "<frozen importlib._bootstrap_external>", line 1043, in create_module
File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed
ImportError: /data/run01/scz5914/.cache/torch_extensions/upfirdn2d_plugin/upfirdn2d_plugin.so: undefined symbol: _ZNSt15__exception_ptr13exception_ptr9_M_addrefEv
Hi, thanks for your excellent work! When I tried to use the command in README.md
to extract a mesh with a 1024x1024 pre-trained model (i.e., FFHQ1024, MetFaces), I got the following error (I'm using a 40GB A100 GPU and extracting meshes with a low-resolution pre-trained model works properly.):
Traceback (most recent call last):
File "/data/miniconda3/envs/env-3.8.8/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/data/miniconda3/envs/env-3.8.8/lib/python3.8/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/group/30042/jialexu/projects/ml-gmpi/gmpi/eval/vis/extract_mesh.py", line 302, in <module>
main(opt)
File "/group/30042/jialexu/projects/ml-gmpi/gmpi/eval/vis/extract_mesh.py", line 255, in main
mesh = generate_mesh(
File "/group/30042/jialexu/projects/ml-gmpi/gmpi/eval/vis/extract_mesh.py", line 95, in generate_mesh
tmp_mpi_rgbas = gen(
File "/data/miniconda3/envs/env-3.8.8/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/group/30042/jialexu/projects/ml-gmpi/gmpi/models/networks/networks_cond_on_pos_enc.py", line 1323, in forward
img = self.synthesize(ws=ws, n_planes=n_planes, mpi_xyz_coords=mpi_xyz_coords, xyz_coords_only_z=xyz_coords_only_z,
File "/group/30042/jialexu/projects/ml-gmpi/gmpi/models/networks/networks_cond_on_pos_enc.py", line 1295, in synthesize
img = self.synthesis(ws, xyz_coords=mpi_xyz_coords, enable_feat_net_grad=enable_syn_feat_net_grad, xyz_coords_only_z=xyz_coords_only_z, n_planes=n_planes, **synthesis_kwargs)
File "/data/miniconda3/envs/env-3.8.8/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/group/30042/jialexu/projects/ml-gmpi/gmpi/models/networks/networks_cond_on_pos_enc.py", line 1205, in forward
x, img = block(x, img, cur_ws, xyz_coords=tmp_xyz_coords, xyz_coords_only_z=xyz_coords_only_z, n_planes=n_planes, enable_feat_net_grad=enable_feat_net_grad, **block_kwargs)
File "/data/miniconda3/envs/env-3.8.8/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/group/30042/jialexu/projects/ml-gmpi/gmpi/models/networks/networks_cond_on_pos_enc.py", line 792, in forward
img = upfirdn2d.upsample2d(img, self.resample_filter)
File "/group/30042/jialexu/projects/ml-gmpi/gmpi/models/torch_utils/ops/upfirdn2d.py", line 343, in upsample2d
return upfirdn2d(x, f, up=up, padding=p, flip_filter=flip_filter, gain=gain*upx*upy, impl=impl)
File "/group/30042/jialexu/projects/ml-gmpi/gmpi/models/torch_utils/ops/upfirdn2d.py", line 163, in upfirdn2d
return _upfirdn2d_cuda(up=up, down=down, padding=padding, flip_filter=flip_filter, gain=gain).apply(x, f)
File "/group/30042/jialexu/projects/ml-gmpi/gmpi/models/torch_utils/ops/upfirdn2d.py", line 237, in forward
y = _plugin.upfirdn2d(y, f, upx, upy, downx, downy, padx0, padx1, pady0, pady1, flip_filter, gain)
RuntimeError: output is too large
Do you have any advice to fix this error? Thanks in advance.
Hi,
Can you please let me know what is the maximum range of yaw and pitches the GMPI can handle
Hello, thank you for good research.
I want to train your model and refer your research.
But, when I download and preprocessing FFHQ, there is some problem.
FFHQ tfrecord -> FFHQ 256 preprocessing is suggested.
But the FFHQ tfrecord google drive api is disconnected everytime. (how do you download it?)
Is there any other option I can download it ?
There is no repository who provide 13G FFHQ 256 dataset...
If you give me a favor, It will be a great help. Thank you.
Hi......
I have some problem in training the FFHQ1024 Model. I have been training the model on 8 NVIDIA A100 GPUs, 40GB Memory still I am getting a error after some iterations of training.
Progress to next stage: 0%| | 657/200000 [2:05:43<602:34:30, 10.88s/it]�[A
Total progress: 0%| | 1/3000 [2:06:06<6303:11:19, 7566.35s/it]
Total progress: 0%| | 1/3000 [2:06:06<6303:11:48, 7566.36s/it]
Progress to next stage: 0%| | 0/200000 [2:05:55<?, ?it/s]
[Experiment: ./experiments/seed_123-dist_8-FFHQ1024-torgba_cond_normalize_add_z-embed_func_modulated_lrelu-20220727_205418050892] [Epoch: 0/3000] [D loss: 0.7179927229881287] [G loss: 1.4626858234405518] [Step: 620] [Img Size: 1024] [Batch Size: 4] [TopK: 2] Loading extension module upfirdn2d_plugin...
Done setting up PyTorch plugin "upfirdn2d_plugin".
Progress to next stage: 0%| | 0/200000 [2:05:55<?, ?it/s]
Loading extension module upfirdn2d_plugin...
Done setting up PyTorch plugin "upfirdn2d_plugin".
Total progress: 0%| | 1/3000 [2:06:06<6303:14:46, 7566.42s/it]
Setting up PyTorch plugin "bias_act_plugin"...
Using /home/x_fahkh/.cache/torch_extensions as PyTorch extensions root...
Loading extension module bias_act_plugin...
Done setting up PyTorch plugin "bias_act_plugin".
Setting up PyTorch plugin "upfirdn2d_plugin"...
Using /home/x_fahkh/.cache/torch_extensions as PyTorch extensions root...
Loading extension module upfirdn2d_plugin...
Done setting up PyTorch plugin "upfirdn2d_plugin".
Progress to next stage: 0%| | 0/200000 [2:05:55<?, ?it/s]
/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/multiprocessing/semaphore_tracker.py:144: UserWarning: semaphore_tracker: There appear to be 33 leaked semaphores to clean up at shutdown
len(cache))
Traceback (most recent call last):
File "/proj/cvl/users/x_fahkh/mn/ml-gmpi/run_gmpi.py", line 115, in <module>
main()
File "/proj/cvl/users/x_fahkh/mn/ml-gmpi/run_gmpi.py", line 49, in main
run_exp(**vars(args))
File "/proj/cvl/users/x_fahkh/mn/ml-gmpi/run_gmpi.py", line 110, in run_exp
mp.spawn(train, args=(num_gpus, config, master_port, run_dataset), nprocs=num_gpus, join=True)
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 230, in spawn
return start_processes(fn, args, nprocs, join, daemon, start_method='spawn')
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 188, in start_processes
while not context.join():
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 136, in join
signal_name=name
torch.multiprocessing.spawn.ProcessExitedException: process 6 terminated with signal SIGBUS
Can You Please help me out in this....
Hi....
I tried to get to calculate the identity metric but there are some dependency issue in the code. Can you Please help me out in this.
Eval.sh
eval "$(conda shell.bash hook)"
conda activate gmpi
export MKL_NUM_THREADS=5 && export NUMEXPR_NUM_THREADS=5 &&
python ${REPO_DIR}/gmpi/eval/prepare_fake_data.py
--ckpt_path ${CKPT_DIR}/generator.pth
--seed ${SEED}
--save_dir ${CONSIST_DIR}
--nplanes ${N_PLANES}
--n_imgs ${N_CONSIST}
--task consistency
--exp_config ${CKPT_DIR}/config.pth
--truncation_psi ${TRUNCATION_PSI}
--dataset ${DATASET}
--stylegan2_sanity_check ${SANITY_CHECK}
eval "$(conda shell.bash hook)"
conda activate deepface
python ${REPO_DIR}/gmpi/eval/compute_consistency.py
--input_dir ${CONSIST_DIR}/consistency
--n_imgs ${N_CONSIST}
--nproc 2
COMMAND TO RUN:
bash {GMPI_ROOT}/gmpi/eval/eval.sh ${GMPI_ROOT} FFHQ256 20220727_102024290372 {Deep3DFaceRecon_PATH} nodebug
ERROR :
Traceback (most recent call last):
File "/proj/cvl/users/x_fahkh/mn/ml-gmpi/gmpi/eval/compute_consistency.py", line 12, in
import tensorflow as tf
File "/home/x_fahkh/.conda/envs/deepfaces/lib/python3.7/site-packages/tensorflow/init.py", line 51, in
from ._api.v2 import compat
File "/home/x_fahkh/.conda/envs/deepfaces/lib/python3.7/site-packages/tensorflow/_api/v2/compat/init.py", line 37, in
from . import v1
File "/home/x_fahkh/.conda/envs/deepfaces/lib/python3.7/site-packages/tensorflow/_api/v2/compat/v1/init.py", line 30, in
from . import compat
File "/home/x_fahkh/.conda/envs/deepfaces/lib/python3.7/site-packages/tensorflow/_api/v2/compat/v1/compat/init.py", line 37, in
from . import v1
File "/home/x_fahkh/.conda/envs/deepfaces/lib/python3.7/site-packages/tensorflow/_api/v2/compat/v1/compat/v1/init.py", line 47, in
from tensorflow._api.v2.compat.v1 import lite
File "/home/x_fahkh/.conda/envs/deepfaces/lib/python3.7/site-packages/tensorflow/_api/v2/compat/v1/lite/init.py", line 9, in
from . import experimental
File "/home/x_fahkh/.conda/envs/deepfaces/lib/python3.7/site-packages/tensorflow/_api/v2/compat/v1/lite/experimental/init.py", line 8, in
from . import authoring
File "/home/x_fahkh/.conda/envs/deepfaces/lib/python3.7/site-packages/tensorflow/_api/v2/compat/v1/lite/experimental/authoring/init.py", line 8, in
from tensorflow.lite.python.authoring.authoring import compatible
File "/home/x_fahkh/.conda/envs/deepfaces/lib/python3.7/site-packages/tensorflow/lite/python/authoring/authoring.py", line 43, in
from tensorflow.lite.python import convert
File "/home/x_fahkh/.conda/envs/deepfaces/lib/python3.7/site-packages/tensorflow/lite/python/convert.py", line 29, in
from tensorflow.lite.python import util
File "/home/x_fahkh/.conda/envs/deepfaces/lib/python3.7/site-packages/tensorflow/lite/python/util.py", line 26, in
import flatbuffers
ModuleNotFoundError: No module named 'flatbuffers'
Hi....
Can you Please help me calculating the Depth and Pose metric.....
eval "$(conda shell.bash hook)"
conda activate gmpi
export MKL_NUM_THREADS=5 && export NUMEXPR_NUM_THREADS=5 &&
python ${REPO_DIR}/gmpi/eval/prepare_fake_data.py
--ckpt_path ${CKPT_DIR}/generator.pth
--seed ${SEED}
--save_dir ${GEO_DIR}
--nplanes ${N_PLANES}
--n_imgs ${N_GEO}
--task geometry
--exp_config ${CKPT_DIR}/config.pth
--save_depth 1
--dataset ${DATASET}
--truncation_psi ${TRUNCATION_PSI}
--stylegan2_sanity_check ${SANITY_CHECK}
eval "$(conda shell.bash hook)"
conda activate mtcnn_env
export MKL_NUM_THREADS=5 && export NUMEXPR_NUM_THREADS=5 &&
python ${REPO_DIR}/gmpi/eval/prepare_face_landmarks.py
--data_dir ${GEO_DIR}/geometry/rgb
eval "$(conda shell.bash hook)"
conda activate deep3d_pytorch
cd ${Deep3DFaceRecon_PATH}
python ${Deep3DFaceRecon_PATH}/estimate_pose_gmpi.py
--name=pretrained
--epoch=20
--gmpi_img_root ${GEO_DIR}/geometry/rgb
--gmpi_depth_root ${GEO_DIR}/geometry/depth
--gmpi_detect_root ${GEO_DIR}/geometry/rgb/detections
eval "$(conda shell.bash hook)"
conda activate gmpi
python ${REPO_DIR}/gmpi/eval/compute_geometry.py
--geo_dir ${GEO_DIR}/geometry
--angle_err 1
Script of training
bash ${GMPI_ROOT}/gmpi/eval/eval.sh ${GMPI_ROOT} FFHQ256 20220727_102024290372 ${Deep3DFaceRecon_PATH} nodebug
Error:
warnings.warn(incompatible_device_warn.format(device_name, capability, " ".join(arch_list), device_name))
Transfer BFM09 to BFM_model_front......
Traceback (most recent call last):
File "/home/x_fahkh/.conda/envs/deep3d_pytorch/lib/python3.6/site-packages/scipy/io/matlab/mio.py", line 39, in _open_file
return open(file_like, mode), True
FileNotFoundError: [Errno 2] No such file or directory: 'BFM/01_MorphableModel.mat'During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/proj/cvl/users/x_fahkh/mn/ml-gmpi/Deep3DFaceRecon_pytorch/estimate_pose_gmpi.py", line 133, in
main(0, opt, opt.gmpi_img_root, opt.gmpi_depth_root, opt.gmpi_detect_root)
File "/proj/cvl/users/x_fahkh/mn/ml-gmpi/Deep3DFaceRecon_pytorch/estimate_pose_gmpi.py", line 64, in main
model = create_model(opt)
File "/proj/cvl/users/x_fahkh/mn/ml-gmpi/Deep3DFaceRecon_pytorch/models/init.py", line 65, in create_model
instance = model(opt)
File "/proj/cvl/users/x_fahkh/mn/ml-gmpi/Deep3DFaceRecon_pytorch/models/facerecon_model.py", line 95, in init
is_train=self.isTrain, default_name=opt.bfm_model
File "/proj/cvl/users/x_fahkh/mn/ml-gmpi/Deep3DFaceRecon_pytorch/models/bfm.py", line 40, in init
transferBFM09(bfm_folder)
File "/proj/cvl/users/x_fahkh/mn/ml-gmpi/Deep3DFaceRecon_pytorch/util/load_mats.py", line 34, in transferBFM09
original_BFM = loadmat(osp.join(bfm_folder, '01_MorphableModel.mat'))
File "/home/x_fahkh/.conda/envs/deep3d_pytorch/lib/python3.6/site-packages/scipy/io/matlab/mio.py", line 216, in loadmat
with _open_file_context(file_name, appendmat) as f:
File "/home/x_fahkh/.conda/envs/deep3d_pytorch/lib/python3.6/contextlib.py", line 81, in enter
return next(self.gen)
File "/home/x_fahkh/.conda/envs/deep3d_pytorch/lib/python3.6/site-packages/scipy/io/matlab/mio.py", line 19, in _open_file_context
f, opened = _open_file(file_like, appendmat, mode)
File "/home/x_fahkh/.conda/envs/deep3d_pytorch/lib/python3.6/site-packages/scipy/io/matlab/mio.py", line 45, in _open_file
return open(file_like, mode), True
FileNotFoundError: [Errno 2] No such file or directory: 'BFM/01_MorphableModel.mat'
0%| | 0/1023 [00:00<?, ?it/s]
Traceback (most recent call last):
File "/proj/cvl/users/x_fahkh/mn/ml-gmpi/gmpi/eval/compute_geometry.py", line 93, in
tmp_depth_err = compute_depth_err(tmp_aligned_depth_f, tmp_pred_depth_f, tmp_pred_mask_f)
File "/proj/cvl/users/x_fahkh/mn/ml-gmpi/gmpi/eval/compute_geometry.py", line 26, in compute_depth_err
depth = np.load(alinged_depth_f)
File "/home/x_fahkh/.conda/envs/gmpi/lib/python3.7/site-packages/numpy/lib/npyio.py", line 416, in load
fid = stack.enter_context(open(os_fspath(file), "rb"))
FileNotFoundError: [Errno 2] No such file or directory: '/proj/cvl/users/x_fahkh/mn/ml-gmpi/ckpts/gmpi_pretrained/20220727_102024290372/planes_96_n_1024/psi_1.0/geometry/recon/aligned_depth/000000.npy'
Hello, I'm interested in your model. So I'm trying to rendering image by pretrained model.
I'm trying to render image and video at FFHQ512 dataset.
According to docs/TRAIN_EVAL.md, I understand that if I make ffhq512x512.zip by styleganv2-ada-pytorch and ffh1512_deep3dface_coeffs, then
I can render image, video and extrach mesh.
But when I apply render a image to get mpi results, this error came out.
RuntimeError: Unable to find a valid cuDNN algorithm to run convolution
I locate pretrained model files at ml-gmpi/ckpts/gmpi_pretrained/FFHQ512.
Could you tell me why this problem happen.
Thanks for your attention.
Hi. I'm trying to run this project on Google Colab with GPU runtime. After setting up the environment and downloading the source code and pretrain weights. I encounter the following error when rendering a single image:
Traceback (most recent call last):
File "/content/ml-gmpi/gmpi/eval/vis/render_video.py", line 228, in <module>
generator = setup_model(opt, config, metadata, mpi_xyz_input, mpi_xyz_only_z, vis_mesh=False, device=device)
File "/content/ml-gmpi/gmpi/eval/common.py", line 120, in setup_model
_ = stylegan2_misc.print_module_summary(generator, [z, c, mpi_xyz_input, mpi_xyz_only_z, n_g_out_planes])
File "/content/ml-gmpi/gmpi/models/torch_utils/misc.py", line 216, in print_module_summary
outputs = module(*inputs)
File "/usr/local/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1148, in _call_impl
result = forward_call(*input, **kwargs)
File "/content/ml-gmpi/gmpi/models/networks/networks_cond_on_pos_enc.py", line 1323, in forward
img = self.synthesize(ws=ws, n_planes=n_planes, mpi_xyz_coords=mpi_xyz_coords, xyz_coords_only_z=xyz_coords_only_z,
File "/content/ml-gmpi/gmpi/models/networks/networks_cond_on_pos_enc.py", line 1295, in synthesize
img = self.synthesis(ws, xyz_coords=mpi_xyz_coords, enable_feat_net_grad=enable_syn_feat_net_grad, xyz_coords_only_z=xyz_coords_only_z, n_planes=n_planes, **synthesis_kwargs)
File "/usr/local/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1148, in _call_impl
result = forward_call(*input, **kwargs)
File "/content/ml-gmpi/gmpi/models/networks/networks_cond_on_pos_enc.py", line 1205, in forward
x, img = block(x, img, cur_ws, xyz_coords=tmp_xyz_coords, xyz_coords_only_z=xyz_coords_only_z, n_planes=n_planes, enable_feat_net_grad=enable_feat_net_grad, **block_kwargs)
File "/usr/local/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1148, in _call_impl
result = forward_call(*input, **kwargs)
File "/content/ml-gmpi/gmpi/models/networks/networks_cond_on_pos_enc.py", line 782, in forward
x = self.conv0(x, w_conv0, fused_modconv=fused_modconv, **layer_kwargs)
File "/usr/local/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1148, in _call_impl
result = forward_call(*input, **kwargs)
File "/content/ml-gmpi/gmpi/models/networks/networks_cond_on_pos_enc.py", line 417, in forward
x = modulated_conv2d(x=x, weight=self.weight, styles=styles, noise=noise, up=self.up,
File "/content/ml-gmpi/gmpi/models/torch_utils/misc.py", line 104, in decorator
return fn(*args, **kwargs)
File "/content/ml-gmpi/gmpi/models/networks/networks_cond_on_pos_enc.py", line 180, in modulated_conv2d
x = conv2d_resample.conv2d_resample(x=x, w=weight.to(x.dtype), f=resample_filter, up=up, down=down, padding=padding, flip_weight=flip_weight)
File "/content/ml-gmpi/gmpi/models/torch_utils/misc.py", line 104, in decorator
return fn(*args, **kwargs)
File "/content/ml-gmpi/gmpi/models/torch_utils/ops/conv2d_resample.py", line 136, in conv2d_resample
x = _conv2d_wrapper(x=x, w=w, stride=up, padding=[pyt,pxt], groups=groups, transpose=True, flip_weight=(not flip_weight))
File "/content/ml-gmpi/gmpi/models/torch_utils/ops/conv2d_resample.py", line 52, in _conv2d_wrapper
return op(x, w, stride=stride, padding=padding, groups=groups)
File "/content/ml-gmpi/gmpi/models/torch_utils/ops/conv2d_gradfix.py", line 44, in conv_transpose2d
return torch.nn.functional.conv_transpose2d(input=input, weight=weight, bias=bias, stride=stride, padding=padding, output_padding=output_padding, groups=groups, dilation=dilation)
RuntimeError: "slow_conv_transpose2d_out_cpu" not implemented for 'Half'
The Colab notebook and its full output can be found here:
https://colab.research.google.com/drive/1Iw1yetX-1b1zRhGXa12tpjTT_Un9kkQ3?usp=sharing
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.