Open bstnhnsl opened 8 months ago
I'm trying to tokenflow via jupyterlab env.
On the last step, when running
run_tokenflow_pnp.py
, I get this error:Traceback (most recent call last): File "/home/jovyan/token-flow/run_tokenflow_pnp.py", line 301, in <module> run(config) File "/home/jovyan/token-flow/run_tokenflow_pnp.py", line 280, in run editor = TokenFlow(config) File "/home/jovyan/token-flow/run_tokenflow_pnp.py", line 62, in __init__ self.paths, self.frames, self.latents, self.eps = self.get_data() File "/home/jovyan/token-flow/run_tokenflow_pnp.py", line 183, in get_data eps = self.get_ddim_eps(latents, range(self.config["n_frames"])).to(torch.float16).to(self.device) File "/home/jovyan/token-flow/run_tokenflow_pnp.py", line 187, in get_ddim_eps noisest = max([int(x.split('_')[-1].split('.')[0]) for x in glob.glob(os.path.join(self.latents_path, f'noisy_latents_*.pt'))]) ValueError: max() arg is an empty sequence
因为你没有先执行preprocess.py代码,导致路径os.path.join(self.latents_path, f'noisylatents*.pt')上的文件不存在。你应该先执行preprocess.py代码,再执行run_tokenflow_pnp.py。
I'm trying to tokenflow via jupyterlab env.
On the last step, when running
run_tokenflow_pnp.py
, I get this error: