mat1 and mat2 must have the same dtype

[QUEST2179]

Follow Aligning proteins wiki

Traceback (most recent call last):
File "C:\Users\work\project\structure\deepblast-master\testDeepBlast.py", line 19, in
pred_alignment = model.align(x, y)
File "C:\Users\work\project\structure\deepblast-master\deepblast\trainer.py", line 84, in align
decoded, _ = next(gen)
File "C:\Users\work\project\structure\deepblast-master\deepblast\alignment.py", line 160, in traceback
zx, gx = self.blosum_factor(hx)
File "C:\Users\work\project\structure\deepblast-master\deepblast\alignment.py", line 95, in blosum_factor
zx = self.match_embedding(hx)
File "C:\Users\miniconda3\envs\torch10\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "C:\Users\work\project\structure\deepblast-master\deepblast\embedding.py", line 157, in forward
h = self.embed(x)
File "C:\Users\miniconda3\envs\torch10\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "C:\Users\miniconda3\envs\torch10\lib\site-packages\torch\nn\modules\linear.py", line 114, in forward
return F.linear(input, self.weight, self.bias)
RuntimeError: mat1 and mat2 must have the same dtype

[mortonjt]

Hi I havent tested this on windows, so I cant comment here. Id also double check if your model / data are on the gpu.

…

On Sat, Sep 16, 2023 at 12:05 AM QUEST2179 ***@***.***> wrote: Follow Aligning proteins wiki Traceback (most recent call last): File "C:\Users\work\project\structure\deepblast-master\testDeepBlast.py", line 19, in pred_alignment = model.align(x, y) File "C:\Users\work\project\structure\deepblast-master\deepblast\trainer.py", line 84, in align decoded, _ = next(gen) File "C:\Users\work\project\structure\deepblast-master\deepblast\alignment.py", line 160, in traceback zx, gx = self.blosum_factor(hx) File "C:\Users\work\project\structure\deepblast-master\deepblast\alignment.py", line 95, in blosum_factor zx = self.match_embedding(hx) File "C:\Users\miniconda3\envs\torch10\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "C:\Users\work\project\structure\deepblast-master\deepblast\embedding.py", line 157, in forward h = self.embed(x) File "C:\Users\miniconda3\envs\torch10\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "C:\Users\miniconda3\envs\torch10\lib\site-packages\torch\nn\modules\linear.py", line 114, in forward return F.linear(input, self.weight, self.bias) RuntimeError: mat1 and mat2 must have the same dtype — Reply to this email directly, view it on GitHub <#140>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AA75VXJPVWETCRU5KFBP2LDX2VFVHANCNFSM6AAAAAA42WHVIE> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>