search

YoujiaZhang / USD

(Arxiv 2023) Optimized View and Geometry Distillation from Multi-view Diffuser
https://youjiazhang.github.io/USD/
MIT License
11 stars 1 forks source link

RuntimeError: mat1 and mat2 shapes cannot be multiplied (154x768 and 1024x320) #1

Open tky5622 opened 8 months ago

tky5622 commented 8 months ago

Hi, thank you for your excellent work! I tried it, but I was faced with this error every time. How can we solve it? Thanks 

0/? [00:00<?, ?it/s]Traceback (most recent call last):
  File "/workspace/assethub-ml-server/api/common/libs/USD/launch.py", line 240, in <module>
    main(args, extras)
  File "/workspace/assethub-ml-server/api/common/libs/USD/launch.py", line 183, in main
    trainer.fit(system, datamodule=dm, ckpt_path=cfg.resume)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 543, in fit
    call._call_and_handle_interrupt(
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/trainer/call.py", line 44, in _call_and_handle_interrupt
    return trainer_fn(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 579, in _fit_impl
    self._run(model, ckpt_path=ckpt_path)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 986, in _run
    results = self._run_stage()
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 1032, in _run_stage
    self.fit_loop.run()
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/loops/fit_loop.py", line 205, in run
    self.advance()
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/loops/fit_loop.py", line 363, in advance
    self.epoch_loop.run(self._data_fetcher)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/loops/training_epoch_loop.py", line 138, in run
    self.advance(data_fetcher)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/loops/training_epoch_loop.py", line 242, in advance
    batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/loops/optimization/automatic.py", line 191, in run
    self._optimizer_step(batch_idx, closure)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/loops/optimization/automatic.py", line 269, in _optimizer_step
    call._call_lightning_module_hook(
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/trainer/call.py", line 157, in _call_lightning_module_hook
    output = fn(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/core/module.py", line 1303, in optimizer_step
    optimizer.step(closure=optimizer_closure)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/core/optimizer.py", line 152, in step
    step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/strategies/strategy.py", line 239, in optimizer_step
    return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/plugins/precision/precision.py", line 122, in optimizer_step
    return optimizer.step(closure=closure, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/torch/optim/optimizer.py", line 373, in wrapper
    out = func(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/torch/optim/optimizer.py", line 76, in _use_grad
    ret = func(self, *args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/torch/optim/adamw.py", line 161, in step
    loss = closure()
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/plugins/precision/precision.py", line 108, in _wrap_closure
    closure_result = closure()
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/loops/optimization/automatic.py", line 144, in __call__
    self._result = self.closure(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/loops/optimization/automatic.py", line 129, in closure
    step_output = self._step_fn()
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/loops/optimization/automatic.py", line 319, in _training_step
    training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values())
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/trainer/call.py", line 309, in _call_strategy_hook
    output = fn(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/pytorch_lightning/strategies/strategy.py", line 391, in training_step
    return self.lightning_module.training_step(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/USD/threestudio/systems/usd.py", line 68, in training_step
    guidance_out = self.guidance(
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/USD/threestudio/models/guidance/usd_guidance.py", line 411, in forward
    grad = self.compute_grad_usd(
  File "/workspace/assethub-ml-server/api/common/libs/USD/threestudio/models/guidance/usd_guidance.py", line 304, in compute_grad_usd
    noise_pred = self.forward_unet(
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/torch/amp/autocast_mode.py", line 16, in decorate_autocast
    return func(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/USD/threestudio/models/guidance/usd_guidance.py", line 189, in forward_unet
    return unet(
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/diffusers/models/unet_2d_condition.py", line 905, in forward
    sample, res_samples = downsample_block(
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/diffusers/models/unet_2d_blocks.py", line 993, in forward
    hidden_states = attn(
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/diffusers/models/transformer_2d.py", line 291, in forward
    hidden_states = block(
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/diffusers/models/attention.py", line 170, in forward
    attn_output = self.attn2(
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/diffusers/models/attention_processor.py", line 321, in forward
    return self.processor(
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/diffusers/models/attention_processor.py", line 1117, in __call__
    key = attn.to_k(encoder_hidden_states)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/workspace/assethub-ml-server/api/common/libs/ImageDream/venv_image/lib/python3.10/site-packages/torch/nn/modules/linear.py", line 114, in forward
    return F.linear(input, self.weight, self.bias)
RuntimeError: mat1 and mat2 shapes cannot be multiplied (154x768 and 1024x320)

RuntimeError: mat1 and mat2 shapes cannot be multiplied (154x768 and 1024x320)

YoujiaZhang commented 8 months ago

Thank you very much for your attention to my work~ I observed that it may be https://github.com/YoujiaZhang/USD/blob/master/threestudio/models/guidance/usd_guidance.py#L304 There is a problem with this place

tky5622 commented 8 months ago

Thank you very much for your attention to my work~ I observed that it may be https://github.com/YoujiaZhang/USD/blob/master/threestudio/models/guidance/usd_guidance.py#L304 There is a problem with this place

thank you for your answer I'll try to debug and fix it do you have any idea on this issue ?