RuntimeError: "slow_conv2d_cpu" not implemented for 'Half'

[likeatingcake]

(latte) yueyc@super-AS-4124GS-TNR:~/Latte$ bash sample/ffs.sh Using Ema! WARNING: using half percision for inferencing! 0%| | 0/250 [00:00<?, ?it/s] Traceback (most recent call last): File "/home/yueyc/Latte/sample/sample.py", line 141, in main(omega_conf) File "/home/yueyc/Latte/sample/sample.py", line 108, in main samples = diffusion.p_sample_loop( ^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/yueyc/Latte/diffusion/gaussian_diffusion.py", line 454, in p_sample_loop for sample in self.p_sample_loop_progressive( File "/home/yueyc/Latte/diffusion/gaussian_diffusion.py", line 505, in p_sample_loop_progressive out = self.p_sample( ^^^^^^^^^^^^^^ File "/home/yueyc/Latte/diffusion/gaussian_diffusion.py", line 406, in p_sample out = self.p_mean_variance( ^^^^^^^^^^^^^^^^^^^^^ File "/home/yueyc/Latte/diffusion/respace.py", line 92, in p_mean_variance return super().p_mean_variance(self._wrap_model(model), *args, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/yueyc/Latte/diffusion/gaussian_diffusion.py", line 279, in p_mean_variance model_output = model(x, t, model_kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/yueyc/Latte/diffusion/respace.py", line 130, in call return self.model(x, new_ts, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/yueyc/Latte/models/latte.py", line 330, in forward x = self.x_embedder(x) + self.pos_embed
^^^^^^^^^^^^^^^^^^ File "/home/yueyc/anaconda3/envs/latte/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, *kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/yueyc/anaconda3/envs/latte/lib/python3.11/site-packages/timm/layers/patch_embed.py", line 87, in forward x = self.proj(x) ^^^^^^^^^^^^ File "/home/yueyc/anaconda3/envs/latte/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(args, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/yueyc/anaconda3/envs/latte/lib/python3.11/site-packages/torch/nn/modules/conv.py", line 463, in forward return self._conv_forward(input, self.weight, self.bias) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/yueyc/anaconda3/envs/latte/lib/python3.11/site-packages/torch/nn/modules/conv.py", line 459, in _conv_forward return F.conv2d(input, weight, bias, self.stride, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ RuntimeError: "slow_conv2d_cpu" not implemented for 'Half'

这是我接触的第一个项目，可能会有很多问题求大家解答

[maxin-cn]

slow_conv2d_cpu

Hi, thanks for your interest. Are you running this project on CPU? I haven't tried this project on CPU.

[likeatingcake]

慢速_conv2d_cpu

您好，感谢您的关注。你在CPU上运行这个项目吗？我还没有在CPU上尝试过这个项目。

您好，后来我改为在GPU上运行这个项目，成功解决了这个问题