Getting shape mismatch error when using a different input

[RajShekhorRoy]

getting this error RuntimeError: mat1 and mat2 shapes cannot be multiplied (128x128 and 256x128)

when I am using the code below which is basically an array of size 32x32x32 and timesteps of 128:

size = 32
device_val="cuda"
x_input = torch.tensor(np.random.rand(1,size, size, size)).to(device_val).type(torch.cuda.FloatTensor)
diffusion = Diffusion(img_size=size, device=device_val)
t = diffusion.sample_timesteps(128).to(device_val)
model = UNet().to(device_val)
xmodel=model(x_input,t)

In addition to that can you please explain a bit more how is this time embedding working especially in terms of the dimension?

[dome272]

Can you show the full error message? One problem seems to be that your size is 32 also for the channels. You need to change the c_in to your diffusion model: model = UNet(c_in=32).to(device_val). But do you really want that? This means you have images with 32 channels? Am Fr., 30. Juni 2023 um 19:22 Uhr schrieb Raj Shekhor Roy < ***@***.***>:

…

getting this error RuntimeError: mat1 and mat2 shapes cannot be multiplied (128x128 and 256x128) when I am using the code below which is basically an array of size 32x32x32 and timesteps of 128: size = 32 device_val="cuda" x_input = torch.tensor(np.random.rand(1,size, size, size)).to(device_val).type(torch.cuda.FloatTensor) diffusion = Diffusion(img_size=size, device=device_val) t = diffusion.sample_timesteps(128).to(device_val) model = UNet().to(device_val) xmodel=model(x_input,t) In addition to that can you please explain a bit more how is this time embedding working especially in terms of the dimension? — Reply to this email directly, view it on GitHub <#31>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AOYRYBRHSIAQWUJPKQEOPLDXN4DL7ANCNFSM6AAAAAAZ2DQG7Y> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

[RajShekhorRoy]

Here is the full error:

Traceback (most recent call last):
File "/home/rajroy/.local/share/JetBrains/Toolbox/apps/PyCharm-P/ch-0/212.4746.96/plugins/python/helpers/pydev/pydevd.py", line 1483, in _exec
pydev_imports.execfile(file, globals, locals) # execute the script
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/rajroy/.local/share/JetBrains/Toolbox/apps/PyCharm-P/ch-0/212.4746.96/plugins/python/helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "/home/rajroy/Diffusion-Models-pytorch/test.py", line 80, in
xmodel=model(x_input,t)
^^^^^^^^^^^^^^^^
File "/home/rajroy/anaconda3/envs/py_cryo/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/rajroy/Diffusion-Models-pytorch/original_moduels.py", line 170, in forward
x2 = self.down1(x1, t)
^^^^^^^^^^^^^^^^^
File "/home/rajroy/anaconda3/envs/py_cryo/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/rajroy/Diffusion-Models-pytorch/original_moduels.py", line 98, in forward
emb = self.emb_layer(t)[:, :, None, None].repeat(1, 1, x.shape[-2], x.shape[-1])
^^^^^^^^^^^^^^^^^
File "/home/rajroy/anaconda3/envs/py_cryo/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/rajroy/anaconda3/envs/py_cryo/lib/python3.11/site-packages/torch/nn/modules/container.py", line 217, in forward
input = module(input)
^^^^^^^^^^^^^
File "/home/rajroy/anaconda3/envs/py_cryo/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/rajroy/anaconda3/envs/py_cryo/lib/python3.11/site-packages/torch/nn/modules/linear.py", line 114, in forward
return F.linear(input, self.weight, self.bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: mat1 and mat2 shapes cannot be multiplied (128x128 and 256x128)
python-BaseException

One more thing is that I changed the default parameter in the model to provide the input channel number, in this way:

class UNet(nn.Module):
def init(self, c_in=32, c_out=32, time_dim=128, device="cuda"):