omerbt/TokenFlow

ValueError: attempt to get argmax of an empty sequence

nitinmukesh opened this issue · 1 comments

nitinmukesh commented

Any suggestions how to fix this issue
I am using the default provided with the repository, only updated the following in \TokenFlow\configs\config_pnp.yaml

batch_size: 8
to
batch_size: 1

data_path: 'data/woman-running'
to
data_path: 'data/woman-running.mp4'

(tokenflow) C:\tut\TokenFlow>python run_tokenflow_pnp.py --config_path "configs/config_pnp.yaml"
A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
  File "C:\Users\nitin\miniconda3\envs\tokenflow\lib\site-packages\xformers\__init__.py", line 55, in _is_triton_available
    from xformers.triton.softmax import softmax as triton_softmax  # noqa
  File "C:\Users\nitin\miniconda3\envs\tokenflow\lib\site-packages\xformers\triton\softmax.py", line 11, in <module>
    import triton
ModuleNotFoundError: No module named 'triton'
{'seed': 1, 'device': 'cuda', 'output_path': 'tokenflow-results_pnp_SD_2.1\\woman-running\\a marble sculpture of a woman running, Venus de Milo\\attn_0.5_f_0.8\\batch_size_1\\50', 'data_path': 'data/woman-running.mp4', 'latents_path': 'latents', 'n_inversion_steps': 500, 'n_frames': 40, 'sd_version': '2.1', 'guidance_scale': 7.5, 'n_timesteps': 50, 'prompt': 'a marble sculpture of a woman running, Venus de Milo', 'negative_prompt': 'ugly, blurry, low res, unrealistic, unaesthetic', 'batch_size': 1, 'pnp_attn_t': 0.5, 'pnp_f_t': 0.8}
{'seed': 1, 'device': 'cuda', 'output_path': 'tokenflow-results_pnp_SD_2.1\\woman-running\\a marble sculpture of a woman running, Venus de Milo\\attn_0.5_f_0.8\\batch_size_1\\50', 'data_path': 'data/woman-running.mp4', 'latents_path': 'latents', 'n_inversion_steps': 500, 'n_frames': 40, 'sd_version': '2.1', 'guidance_scale': 7.5, 'n_timesteps': 50, 'prompt': 'a marble sculpture of a woman running, Venus de Milo', 'negative_prompt': 'ugly, blurry, low res, unrealistic, unaesthetic', 'batch_size': 1, 'pnp_attn_t': 0.5, 'pnp_f_t': 0.8}
Loading SD model
model_index.json: 100%|████████████████████████████████████████████████████████████████| 543/543 [00:00<00:00, 673kB/s]
tokenizer/special_tokens_map.json: 100%|██████████████████████████████████████████████| 460/460 [00:00<00:00, 10.6kB/s]
tokenizer/tokenizer_config.json: 100%|████████████████████████████████████████████████| 807/807 [00:00<00:00, 50.9kB/s]
(…)ature_extractor/preprocessor_config.json: 100%|████████████████████████████████████| 342/342 [00:00<00:00, 57.9kB/s]
unet/config.json: 100%|███████████████████████████████████████████████████████████████| 911/911 [00:00<00:00, 83.5kB/s]
tokenizer/merges.txt: 100%|██████████████████████████████████████████████████████████| 525k/525k [00:00<00:00, 822kB/s]
scheduler/scheduler_config.json: 100%|████████████████████████████████████████████████| 346/346 [00:00<00:00, 33.6kB/s]
text_encoder/config.json: 100%|███████████████████████████████████████████████████████| 613/613 [00:00<00:00, 40.8kB/s]
vae/config.json: 100%|█████████████████████████████████████████████████████████████████| 553/553 [00:00<00:00, 217kB/s]
tokenizer/vocab.json: 100%|████████████████████████████████████████████████████████| 1.06M/1.06M [00:01<00:00, 544kB/s]
vae/diffusion_pytorch_model.safetensors: 100%|██████████████████████████████████████| 335M/335M [01:04<00:00, 5.20MB/s]
text_encoder/model.safetensors: 100%|█████████████████████████████████████████████| 1.36G/1.36G [02:50<00:00, 7.98MB/s]
unet/diffusion_pytorch_model.safetensors: 100%|███████████████████████████████████| 3.46G/3.46G [06:49<00:00, 8.45MB/s]
Fetching 13 files: 100%|███████████████████████████████████████████████████████████████| 13/13 [06:51<00:00, 31.69s/it]
Loading pipeline components...: 100%|████████████████████████████████████████████████████| 6/6 [00:06<00:00,  1.02s/it]
SD model loadedpytorch_model.safetensors: 100%|███████████████████████████████████| 3.46G/3.46G [06:49<00:00, 12.7MB/s]
Traceback (most recent call last):
  File "C:\tut\TokenFlow\run_tokenflow_pnp.py", line 301, in <module>
    run(config)
  File "C:\tut\TokenFlow\run_tokenflow_pnp.py", line 279, in run
    editor = TokenFlow(config)
  File "C:\tut\TokenFlow\run_tokenflow_pnp.py", line 60, in __init__
    self.latents_path = self.get_latents_path()
  File "C:\tut\TokenFlow\run_tokenflow_pnp.py", line 119, in get_latents_path
    latents_path = latents_path[np.argmax(n_frames)]
  File "<__array_function__ internals>", line 200, in argmax
  File "C:\Users\nitin\miniconda3\envs\tokenflow\lib\site-packages\numpy\core\fromnumeric.py", line 1242, in argmax
    return _wrapfunc(a, 'argmax', axis=axis, out=out, **kwds)
  File "C:\Users\nitin\miniconda3\envs\tokenflow\lib\site-packages\numpy\core\fromnumeric.py", line 54, in _wrapfunc
    return _wrapit(obj, method, *args, **kwds)
  File "C:\Users\nitin\miniconda3\envs\tokenflow\lib\site-packages\numpy\core\fromnumeric.py", line 43, in _wrapit
    result = getattr(asarray(obj), method)(*args, **kwds)
ValueError: attempt to get argmax of an empty sequence