orin-beep / hotspot Goto Github PK

Hey there,

Thanks for developing this software.

I bumped into some issues here:

There is nothing wrong when I run the example data.

But, when I try mine (~ 450 MB after pretreatment by preprocessing.py), the pipeline reported error below. Could you please help me out? I guess somewhere in the HOTSPOT.py uses gpu? is it possible to not use it?

Identifying classes in Bacteria ...
76793 plasmid contigs to be predicted ...
Traceback (most recent call last):
File "/home/disk1/HOTSPOT/HOTSPOT.py", line 181, in
logit, _ = model(sentence)
File "/home/disk1/Anaconda3/envs/hotspot/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _c all_impl
return forward_call(*input, **kwargs)
File "/home/disk1/HOTSPOT/library/model.py", line 210, in forward
feat1 = self.Trans1(sentence1)
File "/home/disk1/Anaconda3/envs/hotspot/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _c all_impl
return forward_call(*input, **kwargs)
File "/home/disk1/HOTSPOT/library/model.py", line 170, in forward
enc_src = self.encoder(src, src_mask)
File "/home/disk1/Anaconda3/envs/hotspot/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _c all_impl
return forward_call(*input, **kwargs)
File "/home/disk1/HOTSPOT/library/model.py", line 127, in forward
out = self.layers(out, out, out, mask)
File "/home/disk1/Anaconda3/envs/hotspot/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _c all_impl
return forward_call(*input, **kwargs)
File "/home/disk1/HOTSPOT/library/model.py", line 84, in forward
attention = self.attention(value, key, query, mask)
File "/home/disk1/Anaconda3/envs/hotspot/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _c all_impl
return forward_call(*input, **kwargs)
File "/home/disk1/HOTSPOT/library/model.py", line 39, in forward
energy = torch.einsum("nqhd,nkhd->nhqk", [queries, keys])
File "/home/disk1/Anaconda3/envs/hotspot/lib/python3.8/site-packages/torch/functional.py", line 358, in einsum
return einsum(equation, *_operands)
File "/home/disk1/Anaconda3/envs/hotspot/lib/python3.8/site-packages/torch/functional.py", line 360, in einsum
return _VF.einsum(equation, operands) # type: ignore[attr-defined]

RuntimeError: CUDA out of memory. Tried to allocate 978.00 MiB (GPU 0; 1.95 GiB total capacity; 898.40 MiB already a llocated; 615.62 MiB free; 938.00 MiB reserved in total by PyTorch) If reserved memory is >> allocated memory try se tting max_split_size_mb to avoid fragmentation. See documentation for Memory Management and PYTORCH_CUDA_ALLOC_CONF

Hi there,

Great work with this tool! I'm testing it right now on my data and just realised that the --threads parameter in HOTSPOT.py doesn't work as it should. In my case I set it to 10 and it just defaulted to using all the available threads in the server. Just a heads up as this can generate some problems in the future...
Thanks!