TypeError: 'float' object cannot be interpreted as an integer

[lmc2000]

0it [00:02, ?it/s] Traceback (most recent call last): File "D:\Users\Limc\Downloads\point-e-main\point_e\测试运行point_e.py", line 49, in for x in tqdm(sampler.sample_batch_progressive(batch_size=1, model_kwargs=dict(images=[img]))): File "D:\DevelopTools\anaconda3\lib\site-packages\tqdm\std.py", line 1195, in iter for obj in iterable: File "D:\Users\Limc\Downloads\point-e-main\point_e\diffusion\sampler.py", line 163, in sample_batch_progressive for x in samples_it: File "D:\Users\Limc\Downloads\point-e-main\point_e\diffusion\k_diffusion.py", line 182, in karras_sample_progressive for obj in sample_fn( File "D:\DevelopTools\anaconda3\lib\site-packages\torch\autograd\grad_mode.py", line 43, in generator_context response = gen.send(None) File "D:\Users\Limc\Downloads\point-e-main\point_e\diffusion\k_diffusion.py", line 266, in sample_heun denoised = denoiser(x, sigma_hat * s_in) File "D:\Users\Limc\Downloads\point-e-main\point_e\diffusion\k_diffusion.py", line 174, in guided_denoiser x_0 = denoiser(x_t, sigma) File "D:\Users\Limc\Downloads\point-e-main\point_e\diffusion\k_diffusion.py", line 161, in denoiser _, denoised = model.denoise( File "D:\Users\Limc\Downloads\point-e-main\point_e\diffusion\k_diffusion.py", line 100, in denoise t = th.tensor( TypeError: 'float' object cannot be interpreted as an integer

[hjwdzh]

I meet the same problem and simply apply an integer conversion to sigma_to_t result. Not sure whether it will be the correct solution.

[lmc2000]

Thank you, the problem has been solved.