Comments (6)
I will close this as we have merged the PR #22.
from mace.
I think the problem might be cause by setting the defuault datatype in the training script, but not in the evaluation. Can you try setting the flag --default_dtype
the same way for eval as for train.
from mace.
Thanks for the qqquick reply, let me check it
from mace.
I think the problem might be cause by setting the defuault datatype in the training script, but not in the evaluation. Can you try setting the flag
--default_dtype
the same way for eval as for train.
Hey, It works, but with more stories. I set the flag --default_dtype='float32
firstly, then it gives out the report as below:
Traceback (most recent call last):
File "/u/mncui/software/mace_v2/scripts/eval_configs.py", line 113, in <module>
main()
File "/u/mncui/software/mace_v2/scripts/eval_configs.py", line 78, in main
output = model(batch, training=False)
File "/u/mncui/software/anaconda3/envs/mace_env2/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/u/mncui/software/anaconda3/envs/mace_env2/lib/python3.7/site-packages/mace/modules/models.py", line 226, in forward
edge_index=data.edge_index,
File "/u/mncui/software/anaconda3/envs/mace_env2/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/u/mncui/software/anaconda3/envs/mace_env2/lib/python3.7/site-packages/mace/modules/blocks.py", line 517, in forward
node_feats[sender], edge_attrs, tp_weights
File "/u/mncui/software/anaconda3/envs/mace_env2/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/u/mncui/software/anaconda3/envs/mace_env2/lib/python3.7/site-packages/e3nn/o3/_tensor_product/_tensor_product.py", line 529, in forward
return self._compiled_main_left_right(x, y, real_weight)
File "/u/mncui/software/anaconda3/envs/mace_env2/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
RuntimeError: The following operation failed in the TorchScript interpreter.
Traceback of TorchScript, serialized code (most recent call last):
File "code/__torch__/torch/fx/graph_module/___torch_mangle_8.py", line 109, in forward
einsum_18 = torch.einsum("dba,dbc->dbac", [reshape_5, reshape_28])
mul_2 = torch.mul(reshape_7, 2.2360679774997898)
tensordot_1 = torch.tensordot(mul_2, _w3j_1_1_2, [2], [1])
~~~~~~~~~~~~~~~ <--- HERE
einsum_19 = torch.einsum("edab,ecad->ecb", [tensordot_1, einsum_18])
reshape_29 = torch.reshape(einsum_19, [getitem_4, 640])
Traceback of TorchScript, original code (most recent call last):
einsum_18 = torch.functional.einsum('dba,dbc->dbac', reshape_5, reshape_28); reshape_28 = None
mul_2 = reshape_7 * 2.23606797749979; reshape_7 = None
tensordot_1 = torch.functional.tensordot(mul_2, _w3j_1_1_2, [2], [1]); mul_2 = _w3j_1_1_2 = None
~~~~~~~~~~~~~~~~~~~~~~~~~~ <--- HERE
einsum_19 = torch.functional.einsum('edab,ecad->ecb', tensordot_1, einsum_18); tensordot_1 = einsum_18 = None
reshape_29 = einsum_19.reshape(getitem_4, 640); einsum_19 = None
RuntimeError: Tensor for 'out' is on CPU, Tensor for argument #1 'self' is on CPU, but expected them to be on GPU (while checking arguments for addmm)
I guess it might be related to cuda setting, so I add another flag --device=cuda \
, then It works!!!
I checked the output.xyz
, exactly right, thanks a lot for the information!!!
By the way, another small curiousity about the flag --config_type_weights
, my understanding, it is a dict
, where I can define the weight for each config_type like {'diamond':0.5, 'graphene':0.7, ...}, right?
I wonder is it possible to set a weight for each structure in order to emphasize where could MACE pay attention to (new configurations).
from mace.
I am glad it works! :)
The per configuration weights are implemented in this pull request: #22
I think we will merge it later today to the develop branch. cc @ilyes319
from mace.
Great! Thanks a lot!
from mace.
Related Issues (20)
- LAMMPS-GPU (mace) installed Failed HOT 3
- Issue on integrating lammps with MACE potential HOT 10
- Restart of the training using --restart_latest doesn't properly work - resolved -
- Deployment of the MACE Model Without Using ASE HOT 5
- Error while using multihead interface HOT 2
- Segmentation fault during LAMMPS-MACE-CPU run HOT 1
- Problems with parallelization on CPU (Using LAMMPS) HOT 1
- Improve plotting script
- Automatically add parameters to optimizer
- Change stress to virials internally
- ASE documentation update? HOT 4
- Move to ruff for linting and formating? HOT 3
- Tripeptides Data for MACE-OFF Model
- Bug on loading finetuning model HOT 2
- Remove `e3nn` version pin HOT 2
- models created from multihead fine tuning don't work in lammps HOT 6
- universal loss (at least in multi-head-interface branch) does not support per-config weight
- cannot turn off multihead finetuning in multi-head-interface branch HOT 17
- Colab Tutorial Link Does not work HOT 2
- help message for `--pair_repulsion` is wrong HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from mace.