ValueError: Invalid shape in axis 0: 0.

(SE3nv) user@DESKTOP-DKB20N1:~/RFdiffusion$ ./scripts/run_inference.py
inference.input_pdb=/home/user/RFdiffusion/scripts/imput/output.pdb
inference.deterministic=True
contigmap.contigs=[B42-67/0,10-15]
ppi.hotspot_res=[B50,B64,B77]
inference.num_designs=1000
inference.output_prefix=./base/binder_base
/home/user/RFdiffusion/rfdiffusion/util.py:253: 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.)
Z = torch.cross(Xn, Yn)
/home/user/miniconda3/envs/SE3nv/lib/python3.9/site-packages/dgl/backend/pytorch/sparse.py:104: FutureWarning: torch.cuda.amp.custom_fwd(args...) is deprecated. Please use torch.amp.custom_fwd(args..., device_type='cuda') instead.
@custom_fwd(cast_inputs=th.float16)
/home/user/miniconda3/envs/SE3nv/lib/python3.9/site-packages/dgl/backend/pytorch/sparse.py:128: FutureWarning: torch.cuda.amp.custom_bwd(args...) is deprecated. Please use torch.amp.custom_bwd(args..., device_type='cuda') instead.
def backward(ctx, dZ):
/home/user/miniconda3/envs/SE3nv/lib/python3.9/site-packages/dgl/backend/pytorch/sparse.py:177: FutureWarning: torch.cuda.amp.custom_fwd(args...) is deprecated. Please use torch.amp.custom_fwd(args..., device_type='cuda') instead.
@custom_fwd(cast_inputs=th.float16)
/home/user/miniconda3/envs/SE3nv/lib/python3.9/site-packages/dgl/backend/pytorch/sparse.py:207: FutureWarning: torch.cuda.amp.custom_bwd(args...) is deprecated. Please use torch.amp.custom_bwd(args..., device_type='cuda') instead.
def backward(ctx, *dZ):
/home/user/miniconda3/envs/SE3nv/lib/python3.9/site-packages/dgl/backend/pytorch/sparse.py:287: FutureWarning: torch.cuda.amp.custom_fwd(args...) is deprecated. Please use torch.amp.custom_fwd(args..., device_type='cuda') instead.
@custom_fwd(cast_inputs=th.float16)
/home/user/miniconda3/envs/SE3nv/lib/python3.9/site-packages/dgl/backend/pytorch/sparse.py:304: FutureWarning: torch.cuda.amp.custom_bwd(args...) is deprecated. Please use torch.amp.custom_bwd(args..., device_type='cuda') instead.
def backward(ctx, dZ):
/home/user/miniconda3/envs/SE3nv/lib/python3.9/site-packages/dgl/backend/pytorch/sparse.py:352: FutureWarning: torch.cuda.amp.custom_fwd(args...) is deprecated. Please use torch.amp.custom_fwd(args..., device_type='cuda') instead.
@custom_fwd(cast_inputs=th.float16)
/home/user/miniconda3/envs/SE3nv/lib/python3.9/site-packages/dgl/backend/pytorch/sparse.py:371: FutureWarning: torch.cuda.amp.custom_bwd(args...) is deprecated. Please use torch.amp.custom_bwd(args..., device_type='cuda') instead.
def backward(ctx, *dZ):
/home/user/miniconda3/envs/SE3nv/lib/python3.9/site-packages/dgl/backend/pytorch/sparse.py:431: FutureWarning: torch.cuda.amp.custom_fwd(args...) is deprecated. Please use torch.amp.custom_fwd(args..., device_type='cuda') instead.
@custom_fwd(cast_inputs=th.float16)
/home/user/miniconda3/envs/SE3nv/lib/python3.9/site-packages/dgl/backend/pytorch/sparse.py:467: FutureWarning: torch.cuda.amp.custom_bwd(args...) is deprecated. Please use torch.amp.custom_bwd(args..., device_type='cuda') instead.
def backward(ctx, grad_out):
/home/user/miniconda3/envs/SE3nv/lib/python3.9/site-packages/dgl/backend/pytorch/sparse.py:498: FutureWarning: torch.cuda.amp.custom_fwd(args...) is deprecated. Please use torch.amp.custom_fwd(args..., device_type='cuda') instead.
@custom_fwd(cast_inputs=th.float16)
/home/user/miniconda3/envs/SE3nv/lib/python3.9/site-packages/dgl/backend/pytorch/sparse.py:535: FutureWarning: torch.cuda.amp.custom_bwd(args...) is deprecated. Please use torch.amp.custom_bwd(args..., device_type='cuda') instead.
def backward(ctx, *grad_out):
/home/user/miniconda3/envs/SE3nv/lib/python3.9/site-packages/dgl/backend/pytorch/sparse.py:566: FutureWarning: torch.cuda.amp.custom_fwd(args...) is deprecated. Please use torch.amp.custom_fwd(args..., device_type='cuda') instead.
@custom_fwd(cast_inputs=th.float16)
/home/user/miniconda3/envs/SE3nv/lib/python3.9/site-packages/dgl/backend/pytorch/sparse.py:575: FutureWarning: torch.cuda.amp.custom_bwd(args...) is deprecated. Please use torch.amp.custom_bwd(args..., device_type='cuda') instead.
def backward(ctx, dy):
/home/user/miniconda3/envs/SE3nv/lib/python3.9/site-packages/dgl/backend/pytorch/sparse.py:595: FutureWarning: torch.cuda.amp.custom_fwd(args...) is deprecated. Please use torch.amp.custom_fwd(args..., device_type='cuda') instead.
@custom_fwd(cast_inputs=th.float16)
/home/user/miniconda3/envs/SE3nv/lib/python3.9/site-packages/dgl/backend/pytorch/sparse.py:603: FutureWarning: torch.cuda.amp.custom_bwd(args...) is deprecated. Please use torch.amp.custom_bwd(args..., device_type='cuda') instead.
def backward(ctx, dy):
/home/user/miniconda3/envs/SE3nv/lib/python3.9/site-packages/dgl/backend/pytorch/sparse.py:666: FutureWarning: torch.cuda.amp.custom_fwd(args...) is deprecated. Please use torch.amp.custom_fwd(args..., device_type='cuda') instead.
@custom_fwd(cast_inputs=th.float16)
/home/user/miniconda3/envs/SE3nv/lib/python3.9/site-packages/dgl/backend/pytorch/sparse.py:692: FutureWarning: torch.cuda.amp.custom_fwd(args...) is deprecated. Please use torch.amp.custom_fwd(args..., device_type='cuda') instead.
@custom_fwd(cast_inputs=th.float16)
/home/user/miniconda3/envs/SE3nv/lib/python3.9/site-packages/e3nn/o3/_wigner.py:10: FutureWarning: You are using torch.load with weights_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 for weights_only will be flipped to True. 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=True for 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.
_Jd, _W3j_flat, _W3j_indices = torch.load(os.path.join(os.path.dirname(file), 'constants.pt'))
/home/user/RFdiffusion/rfdiffusion/Track_module.py:236: FutureWarning: torch.cuda.amp.autocast(args...) is deprecated. Please use torch.amp.autocast('cuda', args...) instead.
@torch.cuda.amp.autocast(enabled=False)
[2025-01-01 19:32:57,369][main][INFO] - Found GPU with device_name NVIDIA GeForce RTX 3080 Ti. Will run RFdiffusion on NVIDIA GeForce RTX 3080 Ti
Reading models from /home/user/RFdiffusion/rfdiffusion/inference/../../models
[2025-01-01 19:32:57,369][rfdiffusion.inference.model_runners][INFO] - Reading checkpoint from /home/user/RFdiffusion/rfdiffusion/inference/../../models/Complex_base_ckpt.pt
This is inf_conf.ckpt_path
/home/user/RFdiffusion/rfdiffusion/inference/../../models/Complex_base_ckpt.pt
/home/user/RFdiffusion/rfdiffusion/inference/model_runners.py:181: FutureWarning: You are using torch.load with weights_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 for weights_only will be flipped to True. 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=True for 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.
self.ckpt = torch.load(
Assembling -model, -diffuser and -preprocess configs from checkpoint
USING MODEL CONFIG: self._conf[model][n_extra_block] = 4
USING MODEL CONFIG: self._conf[model][n_main_block] = 32
USING MODEL CONFIG: self._conf[model][n_ref_block] = 4
USING MODEL CONFIG: self._conf[model][d_msa] = 256
USING MODEL CONFIG: self._conf[model][d_msa_full] = 64
USING MODEL CONFIG: self._conf[model][d_pair] = 128
USING MODEL CONFIG: self._conf[model][d_templ] = 64
USING MODEL CONFIG: self._conf[model][n_head_msa] = 8
USING MODEL CONFIG: self._conf[model][n_head_pair] = 4
USING MODEL CONFIG: self._conf[model][n_head_templ] = 4
USING MODEL CONFIG: self._conf[model][d_hidden] = 32
USING MODEL CONFIG: self._conf[model][d_hidden_templ] = 32
USING MODEL CONFIG: self._conf[model][p_drop] = 0.15
USING MODEL CONFIG: self._conf[model][SE3_param_full] = {'num_layers': 1, 'num_channels': 32, 'num_degrees': 2, 'n_heads': 4, 'div': 4, 'l0_in_features': 8, 'l0_out_features': 8, 'l1_in_features': 3, 'l1_out_features': 2, 'num_edge_features': 32}
USING MODEL CONFIG: self._conf[model][SE3_param_topk] = {'num_layers': 1, 'num_channels': 32, 'num_degrees': 2, 'n_heads': 4, 'div': 4, 'l0_in_features': 64, 'l0_out_features': 64, 'l1_in_features': 3, 'l1_out_features': 2, 'num_edge_features': 64}
USING MODEL CONFIG: self._conf[model][freeze_track_motif] = False
USING MODEL CONFIG: self._conf[model][use_motif_timestep] = True
USING MODEL CONFIG: self._conf[diffuser][T] = 50
USING MODEL CONFIG: self._conf[diffuser][b_0] = 0.01
USING MODEL CONFIG: self._conf[diffuser][b_T] = 0.07
USING MODEL CONFIG: self._conf[diffuser][schedule_type] = linear
USING MODEL CONFIG: self._conf[diffuser][so3_type] = igso3
USING MODEL CONFIG: self._conf[diffuser][crd_scale] = 0.25
USING MODEL CONFIG: self._conf[diffuser][so3_schedule_type] = linear
USING MODEL CONFIG: self._conf[diffuser][min_b] = 1.5
USING MODEL CONFIG: self._conf[diffuser][max_b] = 2.5
USING MODEL CONFIG: self._conf[diffuser][min_sigma] = 0.02
USING MODEL CONFIG: self._conf[diffuser][max_sigma] = 1.5
USING MODEL CONFIG: self._conf[preprocess][sidechain_input] = False
USING MODEL CONFIG: self._conf[preprocess][motif_sidechain_input] = True
USING MODEL CONFIG: self._conf[preprocess][d_t1d] = 24
USING MODEL CONFIG: self._conf[preprocess][d_t2d] = 44
USING MODEL CONFIG: self._conf[preprocess][prob_self_cond] = 0.5
USING MODEL CONFIG: self._conf[preprocess][str_self_cond] = True
USING MODEL CONFIG: self._conf[preprocess][predict_previous] = False
[2025-01-01 19:32:59,859][rfdiffusion.inference.model_runners][INFO] - Loading checkpoint.
[2025-01-01 19:32:59,960][rfdiffusion.diffusion][INFO] - Using cached IGSO3.
Successful diffuser init
[2025-01-01 19:33:00,044][main][INFO] - Making design ./base/binder_base_0
[2025-01-01 19:33:00,073][rfdiffusion.inference.model_runners][INFO] - Using contig: ['B42-67/0', '10-15']
With this beta schedule (linear schedule, beta_0 = 0.04, beta_T = 0.28), alpha_bar_T = 0.00013696050154976547
[2025-01-01 19:33:00,087][rfdiffusion.inference.model_runners][INFO] - Sequence init: RLIYYSYGAGSTEKGDIPDGYKASRP
/home/user/miniconda3/envs/SE3nv/lib/python3.9/site-packages/dgl/backend/pytorch/tensor.py:352: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
assert input.numel() == input.storage().size(), "Cannot convert view "
[2025-01-01 19:33:01,430][rfdiffusion.inference.utils][INFO] - Sampled motif RMSD: 0.15
Error executing job with overrides: ['inference.input_pdb=/home/user/RFdiffusion/scripts/imput/output.pdb', 'inference.deterministic=True', 'contigmap.contigs=[B42-67/0,10-15]', 'ppi.hotspot_res=[B50,B64,B77]', 'inference.num_designs=1000', 'inference.output_prefix=./base/binder_base']
Traceback (most recent call last):
File "/home/user/RFdiffusion/./scripts/run_inference.py", line 94, in main
px0, x_t, seq_t, plddt = sampler.sample_step(
File "/home/user/RFdiffusion/rfdiffusion/inference/model_runners.py", line 695, in sample_step
x_t_1, px0 = self.denoiser.get_next_pose(
File "/home/user/RFdiffusion/rfdiffusion/inference/utils.py", line 471, in get_next_pose
frames_next = get_next_frames(
File "/home/user/RFdiffusion/rfdiffusion/inference/utils.py", line 67, in get_next_frames
] = diffuser.so3_diffuser.reverse_sample_vectorized(
File "/home/user/RFdiffusion/rfdiffusion/diffusion.py", line 500, in reverse_sample_vectorized
scipy_R.from_matrix(R_0t.cpu().numpy()).as_rotvec()
File "_rotation.pyx", line 759, in scipy.spatial.transform._rotation.Rotation.from_matrix
File "_rotation.pyx", line 19, in scipy.spatial.transform._rotation._empty2
File "stringsource", line 154, in View.MemoryView.array.cinit
ValueError: Invalid shape in axis 0: 0.
Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.

May I ask Drs. what is the reason for this problem? What should I do to solve it?

Reproduce the command from scripts/run_inference.py with the shown contig and input PDB settings. Start by tracing the inference path through rfdiffusion/inference/model_runners.py and the reported shape error, then confirm that the same design completes without ValueError.