Hello，I am trying to finetune ContourCraft for Gaussian Garments，but I met some problems. Following the official finetuning instructions, I got following error:
(ccraft) ysq@3090x2:/mnt/8T/ysq/gaugar/ContourCraft$ python train.py config=finetune/00122_Outer /mnt/8T/ysq/anaconda3/envs/ccraft/lib/python3.10/site-packages/torch/cuda/__init__.py:58: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you. import pynvml # type: ignore[import] Warp 1.11.1 initialized: CUDA Toolkit 12.9, Driver 12.7 Devices: "cpu" : "x86_64" "cuda:0" : "NVIDIA GeForce RTX 3090" (24 GiB, sm_86, mempool enabled) Kernel cache: /home/ysq/.cache/warp/1.11.1 smpl_root: /mnt/8T/ysq/gaugar/ContourCraft/ccraft_data/aux_data/body_models Loading split from: /mnt/8T/ysq/gaugar/ContourCraft/ccraft_data/aux_data/datasplits/finetuning/00122_Outer/train.csv WARNING: male model not found in /mnt/8T/ysq/gaugar/ContourCraft/ccraft_data/aux_data/body_models. /mnt/8T/ysq/anaconda3/envs/ccraft/lib/python3.10/site-packages/chumpy/__init__.py:11: FutureWarning: In the futurenp.boolwill be defined as the corresponding NumPy scalar. from numpy import bool, int, float, complex, object, unicode, str, nan, inf /mnt/8T/ysq/anaconda3/envs/ccraft/lib/python3.10/site-packages/chumpy/__init__.py:11: FutureWarning: In the futurenp.objectwill be defined as the corresponding NumPy scalar. from numpy import bool, int, float, complex, object, unicode, str, nan, inf /mnt/8T/ysq/anaconda3/envs/ccraft/lib/python3.10/site-packages/chumpy/__init__.py:11: FutureWarning: In the futurenp.strwill be defined as the corresponding NumPy scalar. from numpy import bool, int, float, complex, object, unicode, str, nan, inf WARNING: female model not found in /mnt/8T/ysq/gaugar/ContourCraft/ccraft_data/aux_data/body_models. WARNING: neutral model not found in /mnt/8T/ysq/gaugar/ContourCraft/ccraft_data/aux_data/body_models. /mnt/8T/ysq/gaugar/ContourCraft/material/utils.py:15: UserWarning: Using torch.cross without specifying the dim arg is deprecated. Please either pass the dim explicitly or simply use torch.linalg.cross. The default value of dim will change to agree with that of linalg.cross in a future release. (Triggered internally at ../aten/src/ATen/native/Cross.cpp:62.) out = torch.linalg.norm(torch.cross(u, v), axis=-1) / 2.0 /mnt/8T/ysq/gaugar/ContourCraft/utils/arguments.py:282: FutureWarning: You are usingtorch.loadwithweights_only=False(the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value forweights_onlywill be flipped toTrue. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=Truefor any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. sd = torch.load(checkpoint_path) LOADED CHECKPOINT FROM /mnt/8T/ysq/gaugar/ContourCraft/ccraft_data/trained_models/contourcraft.pth optimizer LOADED! scheduler LOADED! wandb: [wandb.Api()] Loaded credentials for https://api.wandb.ai from /home/ysq/.netrc. wandb: Currently logged in as: 3290628905 (3290628905-tianjin-university) to https://api.wandb.ai. Usewandb login --reloginto force relogin WARNING: Wandb initialization failed: Error uploading run: returned error 404: {"data":{"upsertBucket":null},"errors":[{"message":"project not found","path":["upsertBucket"]}]} finetune/00122_Outer: 0%| | 0/200 [00:00<?, ?it/s]filepath: /mnt/8T/ysq/gaugar/Gaussian-Garments/output/00122_Outer/stage4/smplx/Take9.npz sequence_raw: dict_keys(['betas', 'expression', 'trans', 'root_orient', 'pose_body', 'pose_hand', 'pose_jaw', 'pose_eye', 'mocap_frame_rate']) Module utils.warp_u.proximity f3809b5 load on device 'cuda:0' took 0.72 ms (cached) WARNING: Wandb writer is not initialized, skipping logging finetune/00122_Outer: 0%|▏ | 1/200 [01:06<3:40:06, 66.36s/it]garment_name: dress finetune/00122_Outer: 0%|▏ | 1/200 [01:06<3:40:09, 66.38s/it] Traceback (most recent call last): File "/mnt/8T/ysq/gaugar/ContourCraft/train.py", line 56, in <module> main() File "/mnt/8T/ysq/gaugar/ContourCraft/train.py", line 47, in main global_step = runner_module.run_epoch(runner, aux_modules, dataloaders_dict, config, writer, File "/mnt/8T/ysq/gaugar/ContourCraft/runners/finetune.py", line 673, in run_epoch sample = next(long_iter) File "/mnt/8T/ysq/anaconda3/envs/ccraft/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 630, in __next__ data = self._next_data() File "/mnt/8T/ysq/anaconda3/envs/ccraft/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 673, in _next_data data = self._dataset_fetcher.fetch(index) # may raise StopIteration File "/mnt/8T/ysq/anaconda3/envs/ccraft/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py", line 52, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/mnt/8T/ysq/anaconda3/envs/ccraft/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py", line 52, in <listcomp> data = [self.dataset[idx] for idx in possibly_batched_index] File "/mnt/8T/ysq/gaugar/ContourCraft/datasets/ccraft.py", line 961, in __getitem__ sample = self.loader.load_sample(fname, idx, garment_name, gender, betas_id=betas_id) File "/mnt/8T/ysq/gaugar/ContourCraft/datasets/ccraft.py", line 892, in load_sample sample = self.garment_builder.build(sample, sequence, idx, garment_name) File "/mnt/8T/ysq/gaugar/ContourCraft/datasets/ccraft.py", line 713, in build self.load_garment_dict(garment_name) File "/mnt/8T/ysq/gaugar/ContourCraft/datasets/ccraft.py", line 674, in load_garment_dict body_model = self.body_models_dict[gender] KeyError: 'female'
have you ever met the same problem? Or maybe I haven't considered some details？ Can you tell me more implementation details？Thanks.
Hello，I am trying to finetune ContourCraft for Gaussian Garments，but I met some problems. Following the official finetuning instructions, I got following error:
(ccraft) ysq@3090x2:/mnt/8T/ysq/gaugar/ContourCraft$ python train.py config=finetune/00122_Outer /mnt/8T/ysq/anaconda3/envs/ccraft/lib/python3.10/site-packages/torch/cuda/__init__.py:58: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you. import pynvml # type: ignore[import] Warp 1.11.1 initialized: CUDA Toolkit 12.9, Driver 12.7 Devices: "cpu" : "x86_64" "cuda:0" : "NVIDIA GeForce RTX 3090" (24 GiB, sm_86, mempool enabled) Kernel cache: /home/ysq/.cache/warp/1.11.1 smpl_root: /mnt/8T/ysq/gaugar/ContourCraft/ccraft_data/aux_data/body_models Loading split from: /mnt/8T/ysq/gaugar/ContourCraft/ccraft_data/aux_data/datasplits/finetuning/00122_Outer/train.csv WARNING: male model not found in /mnt/8T/ysq/gaugar/ContourCraft/ccraft_data/aux_data/body_models. /mnt/8T/ysq/anaconda3/envs/ccraft/lib/python3.10/site-packages/chumpy/__init__.py:11: FutureWarning: In the futurenp.boolwill be defined as the corresponding NumPy scalar. from numpy import bool, int, float, complex, object, unicode, str, nan, inf /mnt/8T/ysq/anaconda3/envs/ccraft/lib/python3.10/site-packages/chumpy/__init__.py:11: FutureWarning: In the futurenp.objectwill be defined as the corresponding NumPy scalar. from numpy import bool, int, float, complex, object, unicode, str, nan, inf /mnt/8T/ysq/anaconda3/envs/ccraft/lib/python3.10/site-packages/chumpy/__init__.py:11: FutureWarning: In the futurenp.strwill be defined as the corresponding NumPy scalar. from numpy import bool, int, float, complex, object, unicode, str, nan, inf WARNING: female model not found in /mnt/8T/ysq/gaugar/ContourCraft/ccraft_data/aux_data/body_models. WARNING: neutral model not found in /mnt/8T/ysq/gaugar/ContourCraft/ccraft_data/aux_data/body_models. /mnt/8T/ysq/gaugar/ContourCraft/material/utils.py:15: UserWarning: Using torch.cross without specifying the dim arg is deprecated. Please either pass the dim explicitly or simply use torch.linalg.cross. The default value of dim will change to agree with that of linalg.cross in a future release. (Triggered internally at ../aten/src/ATen/native/Cross.cpp:62.) out = torch.linalg.norm(torch.cross(u, v), axis=-1) / 2.0 /mnt/8T/ysq/gaugar/ContourCraft/utils/arguments.py:282: FutureWarning: You are usingtorch.loadwithweights_only=False(the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value forweights_onlywill be flipped toTrue. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user viatorch.serialization.add_safe_globals. We recommend you start settingweights_only=Truefor any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. sd = torch.load(checkpoint_path) LOADED CHECKPOINT FROM /mnt/8T/ysq/gaugar/ContourCraft/ccraft_data/trained_models/contourcraft.pth optimizer LOADED! scheduler LOADED! wandb: [wandb.Api()] Loaded credentials for https://api.wandb.ai from /home/ysq/.netrc. wandb: Currently logged in as: 3290628905 (3290628905-tianjin-university) to https://api.wandb.ai. Usewandb login --reloginto force relogin WARNING: Wandb initialization failed: Error uploading run: returned error 404: {"data":{"upsertBucket":null},"errors":[{"message":"project not found","path":["upsertBucket"]}]} finetune/00122_Outer: 0%| | 0/200 [00:00<?, ?it/s]filepath: /mnt/8T/ysq/gaugar/Gaussian-Garments/output/00122_Outer/stage4/smplx/Take9.npz sequence_raw: dict_keys(['betas', 'expression', 'trans', 'root_orient', 'pose_body', 'pose_hand', 'pose_jaw', 'pose_eye', 'mocap_frame_rate']) Module utils.warp_u.proximity f3809b5 load on device 'cuda:0' took 0.72 ms (cached) WARNING: Wandb writer is not initialized, skipping logging finetune/00122_Outer: 0%|▏ | 1/200 [01:06<3:40:06, 66.36s/it]garment_name: dress finetune/00122_Outer: 0%|▏ | 1/200 [01:06<3:40:09, 66.38s/it] Traceback (most recent call last): File "/mnt/8T/ysq/gaugar/ContourCraft/train.py", line 56, in <module> main() File "/mnt/8T/ysq/gaugar/ContourCraft/train.py", line 47, in main global_step = runner_module.run_epoch(runner, aux_modules, dataloaders_dict, config, writer, File "/mnt/8T/ysq/gaugar/ContourCraft/runners/finetune.py", line 673, in run_epoch sample = next(long_iter) File "/mnt/8T/ysq/anaconda3/envs/ccraft/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 630, in __next__ data = self._next_data() File "/mnt/8T/ysq/anaconda3/envs/ccraft/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 673, in _next_data data = self._dataset_fetcher.fetch(index) # may raise StopIteration File "/mnt/8T/ysq/anaconda3/envs/ccraft/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py", line 52, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/mnt/8T/ysq/anaconda3/envs/ccraft/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py", line 52, in <listcomp> data = [self.dataset[idx] for idx in possibly_batched_index] File "/mnt/8T/ysq/gaugar/ContourCraft/datasets/ccraft.py", line 961, in __getitem__ sample = self.loader.load_sample(fname, idx, garment_name, gender, betas_id=betas_id) File "/mnt/8T/ysq/gaugar/ContourCraft/datasets/ccraft.py", line 892, in load_sample sample = self.garment_builder.build(sample, sequence, idx, garment_name) File "/mnt/8T/ysq/gaugar/ContourCraft/datasets/ccraft.py", line 713, in build self.load_garment_dict(garment_name) File "/mnt/8T/ysq/gaugar/ContourCraft/datasets/ccraft.py", line 674, in load_garment_dict body_model = self.body_models_dict[gender] KeyError: 'female'have you ever met the same problem? Or maybe I haven't considered some details？ Can you tell me more implementation details？Thanks.