Comments (4)
I am also getting the above issue - Did you manage to find a fix @SejeongPark8354 ?
from hgraph2graph.
getting a very similar issue when running train_generator.py
:
Namespace(anneal_iter=25000, anneal_rate=0.9, atom_vocab=<hgraph.vocab.Vocab object at 0x000001C10639ED48>, batch_size=20, clip_norm=5.0, depthG=15, depthT=15, diterG=3, diterT=1, dropout=0.0, embed_size=250, epoch=20, hidden_size=125, kl_anneal_iter=2000, latent_size=32, load_model=None, lr=0.001, max_beta=1.0, print_iter=50, rnn_type='LSTM', save_dir='ckpt/cyclic_truncated_pretrained', save_iter=5000, seed=7, step_beta=0.001, train='train_processed/cyclic_truncated_processed/', vocab='data/chembl/cyclic_peptide_vocab_truncated.txt', warmup=10000)
C:\Users\Marshall\Anaconda3\envs\hgraph-rdkit\lib\site-packages\torch\nn\_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
warnings.warn(warning.format(ret))
Model #Params: 1318K
0%|▏ | 2/1000 [00:32<4:01:50, 14.54s/it]C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [146,0,0], thread: [40,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [146,0,0], thread: [41,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [146,0,0], thread: [42,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [146,0,0], thread: [43,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [146,0,0], thread: [44,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [146,0,0], thread: [45,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [146,0,0], thread: [46,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [146,0,0], thread: [47,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [146,0,0], thread: [48,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [146,0,0], thread: [49,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [146,0,0], thread: [50,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [146,0,0], thread: [51,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [146,0,0], thread: [52,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [146,0,0], thread: [53,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [146,0,0], thread: [54,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [146,0,0], thread: [55,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [146,0,0], thread: [56,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [146,0,0], thread: [57,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [146,0,0], thread: [58,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [146,0,0], thread: [59,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [148,0,0], thread: [44,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [148,0,0], thread: [45,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [148,0,0], thread: [46,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [148,0,0], thread: [47,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [148,0,0], thread: [48,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [148,0,0], thread: [49,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [148,0,0], thread: [50,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [148,0,0], thread: [51,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [148,0,0], thread: [52,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [148,0,0], thread: [53,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [148,0,0], thread: [54,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [148,0,0], thread: [55,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [148,0,0], thread: [56,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [148,0,0], thread: [57,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [148,0,0], thread: [58,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [148,0,0], thread: [59,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [148,0,0], thread: [60,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [148,0,0], thread: [61,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [148,0,0], thread: [62,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:975: block: [148,0,0], thread: [63,0,0] Assertion “srcIndex < srcSelectDimSize” failed.
0%|▏ | 2/1000 [00:35<4:56:07, 17.80s/it]
Traceback (most recent call last):
File "train_generator.py", line 92, in <module>
loss, kl_div, wacc, iacc, tacc, sacc = model(*batch, beta=beta)
File "C:\Users\Marshall\Anaconda3\envs\hgraph-rdkit\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Users\Marshall\hgraph2graph-master\hgraph\hgnn.py", line 55, in forward
root_vecs, tree_vecs, _, graph_vecs = self.encoder(tree_tensors, graph_tensors)
File "C:\Users\Marshall\Anaconda3\envs\hgraph-rdkit\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Users\Marshall\hgraph2graph-master\hgraph\encoder.py", line 129, in forward
tensors = self.embed_graph(graph_tensors)
File "C:\Users\Marshall\hgraph2graph-master\hgraph\encoder.py", line 114, in embed_graph
fpos = self.E_apos.index_select(index=fmess[:, 3], dim=0)
RuntimeError: CUDA error: device-side assert triggered
from hgraph2graph.
Actually, I think I figured it out. There's a parameter defined in mol_graph.py
, MAX_POS = 20
, which limits the E_apos matrix, E_pos matrix, and subsequently when in the enconder, the f_mess matrix will be out of index which is why you get the error.
I think it's an issue of molecule size and graph complexity - in the paper, there's a subscript:
"The number of possible attachments are limited because the number of attaching atoms between two motifs is small and the attaching points must be consecutive.3
3In our experiments, the number of possible attachments are
usually less than 20 for polymers and small molecules."
from hgraph2graph.
I agree with the above person's advice. I first use "os.environ['CUDA_LAUNCH_BLOCKING'] = '1'" to locate the bug, I find there are some problem with "fpos = self.E_apos.index_select(index=fmess[:, 3], dim=0)". And then I use the slice to locate where the error is,I find the max number of fmess[:,3] is 22 while self.E_apos only has 20 dims. So I increase the MAX_POS in mol_graph.py and solve this problem. I think the operation would not affect the models, maybe waste some memory.
from hgraph2graph.
Related Issues (20)
- Question Polymer Data
- Question about constraint optimization
- All assm_labels are zero?
- how to convert the chembl checkpoint kept file to an binary format
- PicklingError("Can't pickle <class 'Boost.Python.ArgumentError'>: import of module 'Boost.Python failed")' HOT 7
- README error HOT 7
- Unrecognized arguments: --nsamples 1000 HOT 1
- IndexError: tuple index out of range HOT 12
- Getting error while running pip install . HOT 3
- TypeError: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first HOT 2
- TypeError: forward() missing 2 required positional arguments: 'y_orders' and 'beta' HOT 2
- AssertionError HOT 12
- Pretrained chembl model requires old rdkit HOT 2
- Some motifs in generated vocabulary are not parseable for rdkit
- Finetune result interpretation
- vocab size of data/chembl/vocab.txt: 5623, but when get_vocab.py the new vocab.txt is 5625 HOT 3
- ZeroDivisionError when size smaller than 1000 using single mode
- If anyone has done fine tuning, please share environment.yaml HOT 1
- Preprocess Error————————Broken pipe
- size mismatch when load chembl-pretrained ckpt
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 hgraph2graph.