this was discussed here a while ago, now some more details. ---------- Forwarded message --------- From: Qian Yun <[email protected]> Date: Mon, Nov 16, 2020 at 12:35 PM Subject: [fricas-devel] the "deep learning" "neural network" symbolic integrator To: <[email protected]>
Hi guys, I assume you all know the paper "DEEP LEARNING FOR SYMBOLIC MATHEMATICS" by facebook AI researchers, almost one year ago, posted on https://arxiv.org/abs/1912.01412 And the code was posted 8 months ago: https://github.com/facebookresearch/SymbolicMathematics Have you played with it? Finally I have some time recently and played with it for a while, and I believe I found some flaws. I will post my findings with more details later. And it's a really interesting experience. If you have some spare time and want to have fun, I strongly advise you to play with it and try to break it :-) Tips: to run the jupyter notebook example, apply the following patch to run it on CPU instead of CUDA: - Best, - Qian ===================== diff --git a/beam_integration.ipynb b/beam_integration.ipynb index f9ef329..00754e3 100644 --- a/beam_integration.ipynb +++ b/beam_integration.ipynb @@ -64,6 +64,6 @@ "\n", " # model parameters\n", - " 'cpu': False,\n", + " 'cpu': True,\n", " 'emb_dim': 1024,\n", " 'n_enc_layers': 6,\n", " 'n_dec_layers': 6,\n", diff --git a/src/model/__init__.py b/src/model/__init__.py index 2b0a044..73ec446 100644 --- a/src/model/__init__.py +++ b/src/model/__init__.py @@ -38,7 +38,7 @@ # reload pretrained modules if params.reload_model != '': logger.info(f"Reloading modules from {params.reload_model} ...") - reloaded = torch.load(params.reload_model) + reloaded = torch.load(params.reload_model, map_location=torch.device('cpu')) for k, v in modules.items(): assert k in reloaded if all([k2.startswith('module.') for k2 in reloaded[k].keys()]): diff --git a/src/utils.py b/src/utils.py index bd90608..ef87582 100644 --- a/src/utils.py +++ b/src/utils.py @@ -25,7 +25,7 @@ FALSY_STRINGS = {'off', 'false', '0'} TRUTHY_STRINGS = {'on', 'true', '1'} -CUDA = True +CUDA = False class AttrDict(dict): -- You received this message because you are subscribed to the Google Groups "FriCAS - computer algebra system" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/fricas-devel/7c33eab4-41f6-7d3f-0758-01a0bf9e641e%40gmail.com. -- You received this message because you are subscribed to the Google Groups "sage-devel" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/sage-devel/CAAWYfq1-CECSrQPXntNd8q_YHFhLK9DYvsn6%2Bt5-G%2Bf5gPzTgg%40mail.gmail.com.
