generate nothing using batchsize=4

[ysngfo]

I clone the repo and successfully run it ,when i set the batchsize=1 ,everything is OK,but when set to 4, it tell me [WARNING] Empty rays_indices! and generate nothing. I use dreamfusion-sd.yaml with prompt "a DSLR photo of a tiger dressed as a doctor"

[mediccccc]

i met the same problem, did you modified the functoion "get_inversion_timesteps"?

[ysngfo]

i met the same problem, did you modified the functoion "get_inversion_timesteps"?

I change nothing beside the batchsize

[mediccccc]

i met the same problem, did you modified the functoion "get_inversion_timesteps"?

I change nothing beside the batchsize

I run the code: python launch.py --config configs/sdi.yaml --train --gpu 0 system.prompt_processor.prompt="a dog, 3d asset”
But this error came up:
File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/trainer/trainer.py", line 978, in _run_stage
self.fit_loop.run()
File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/loops/fit_loop.py", line 201, in run
self.advance()
File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/loops/fit_loop.py", line 354, in advance
self.epoch_loop.run(self._data_fetcher)
File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/loops/training_epoch_loop.py", line 133, in run
self.advance(data_fetcher)
File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/loops/training_epoch_loop.py", line 218, in advance
batch_output = self.automatic_optimization.run(trainer.optimizers[0], kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/loops/optimization/automatic.py", line 185, in run
self._optimizer_step(kwargs.get("batch_idx", 0), closure)
File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/loops/optimization/automatic.py", line 261, in _optimizer_step
call._call_lightning_module_hook(
File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/trainer/call.py", line 142, in _call_lightning_module_hook
output = fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/core/module.py", line 1265, in optimizer_step
optimizer.step(closure=optimizer_closure)
File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/core/optimizer.py", line 158, in step
step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/strategies/strategy.py", line 224, in optimizer_step
return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/plugins/precision/amp.py", line 70, in optimizer_step
closure_result = closure()
^^^^^^^^^
File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/loops/optimization/automatic.py", line 140, in call
self._result = self.closure(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/loops/optimization/automatic.py", line 126, in closure
step_output = self._step_fn()
^^^^^^^^^^^^^^^
File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/loops/optimization/automatic.py", line 308, in _training_step
training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values())
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/trainer/call.py", line 288, in _call_strategy_hook
output = fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/strategies/strategy.py", line 366, in training_step
return self.model.training_step(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/linux/workspace/threestudio/threestudio/systems/sdi.py", line 42, in training_step
guidance_out = self.guidance(
^^^^^^^^^^^^^^
File "/home/linux/workspace/threestudio/threestudio/models/guidance/stable_diffusion_sdi_guidance.py", line 510, in call
target, noisy_img, noise, guidance_eval_utils = self.compute_grad_sdi(
^^^^^^^^^^^^^^^^^^^^^^
File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/home/linux/workspace/threestudio/threestudio/models/guidance/stable_diffusion_sdi_guidance.py", line 441, in compute_grad_sdi
latents_noisy, noise = self.invert_noise(
^^^^^^^^^^^^^^^^^^
File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/home/linux/workspace/threestudio/threestudio/models/guidance/stable_diffusion_sdi_guidance.py", line 392, in invert_noise
timesteps = self.get_inversion_timesteps(invert_to_t, B)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/linux/workspace/threestudio/threestudio/models/guidance/stable_diffusion_sdi_guidance.py", line 357, in get_inversion_timesteps
timesteps = timesteps[timesteps < int(invert_to_t)]
^^^^^^^^^^^^^^^^
ValueError: only one element tensors can be converted to Python scalars
and I suspect it's a problem with the get_inversion_timesteps function

[ysngfo]

i met the same problem, did you modified the functoion "get_inversion_timesteps"?

I change nothing beside the batchsize

I run the code: python launch.py --config configs/sdi.yaml --train --gpu 0 system.prompt_processor.prompt="a dog, 3d asset” But this error came up: File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/trainer/trainer.py", line 978, in _run_stage self.fit_loop.run() File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/loops/fit_loop.py", line 201, in run self.advance() File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/loops/fit_loop.py", line 354, in advance self.epoch_loop.run(self._data_fetcher) File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/loops/training_epoch_loop.py", line 133, in run self.advance(data_fetcher) File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/loops/training_epoch_loop.py", line 218, in advance batch_output = self.automatic_optimization.run(trainer.optimizers[0], kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/loops/optimization/automatic.py", line 185, in run self._optimizer_step(kwargs.get("batch_idx", 0), closure) File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/loops/optimization/automatic.py", line 261, in _optimizer_step call._call_lightning_module_hook( File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/trainer/call.py", line 142, in _call_lightning_module_hook output = fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/core/module.py", line 1265, in optimizer_step optimizer.step(closure=optimizer_closure) File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/core/optimizer.py", line 158, in step step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/strategies/strategy.py", line 224, in optimizer_step return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/plugins/precision/amp.py", line 70, in optimizer_step closure_result = closure() ^^^^^^^^^ File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/loops/optimization/automatic.py", line 140, in call self._result = self.closure(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/loops/optimization/automatic.py", line 126, in closure step_output = self._step_fn() ^^^^^^^^^^^^^^^ File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/loops/optimization/automatic.py", line 308, in _training_step training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/trainer/call.py", line 288, in _call_strategy_hook output = fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/pytorch_lightning/strategies/strategy.py", line 366, in training_step return self.model.training_step(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/linux/workspace/threestudio/threestudio/systems/sdi.py", line 42, in training_step guidance_out = self.guidance( ^^^^^^^^^^^^^^ File "/home/linux/workspace/threestudio/threestudio/models/guidance/stable_diffusion_sdi_guidance.py", line 510, in call target, noisy_img, noise, guidance_eval_utils = self.compute_grad_sdi( ^^^^^^^^^^^^^^^^^^^^^^ File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/home/linux/workspace/threestudio/threestudio/models/guidance/stable_diffusion_sdi_guidance.py", line 441, in compute_grad_sdi latents_noisy, noise = self.invert_noise( ^^^^^^^^^^^^^^^^^^ File "/home/linux/anaconda3/envs/3dp/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/home/linux/workspace/threestudio/threestudio/models/guidance/stable_diffusion_sdi_guidance.py", line 392, in invert_noise timesteps = self.get_inversion_timesteps(invert_to_t, B) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/linux/workspace/threestudio/threestudio/models/guidance/stable_diffusion_sdi_guidance.py", line 357, in get_inversion_timesteps timesteps = timesteps[timesteps < int(invert_to_t)] ^^^^^^^^^^^^^^^^ ValueError: only one element tensors can be converted to Python scalars and I suspect it's a problem with the get_inversion_timesteps function

I try to run the command you give ,and it works well in my environment.