Anatoly Belikov
Anatoly Belikov
see also my arguments on caching vs deterministic grounded schema nodes https://github.com/opencog/atomspace/issues/1907#issuecomment-439340307
I misunderstood when recalculation of evaluation link happens. So there are cases: 1) In bindlink rewrite clause 2) During consecutive calls by rule engine 2 is addressable by external caching...
thank you, indeed there were some issues
It should fix issue https://github.com/KindXiaoming/pykan/issues/52
I made basic test on MNIST https://github.com/KindXiaoming/pykan/pull/57 though it gives me segmentation fault on cuda or with larger than 28*28, 25,10 networks
It should be possible to apply convolution with https://pytorch.org/docs/stable/generated/torch.nn.Unfold.html and use relatively small KAN
@sayakpaul i built xformers from source but the issue is still present
Looks the same with pytorch 2.0.0, xformers installed with pip install xformers==0.0.19 ``` File "/home/imgen/miniconda3/envs/py31/lib/python3.10/site-packages/xformers/ops/fmha/__init__.py", line 317, in _memory_efficient_attention_forward_requires_grad inp.validate_inputs() File "/home/imgen/miniconda3/envs/py31/lib/python3.10/site-packages/xformers/ops/fmha/common.py", line 73, in validate_inputs raise ValueError( ValueError: Query/Key/Value...
@sayakpaul Which code quality issues? What should i fix?