Error running train_lora.py
YSYYU opened this issue · comments
Traceback (most recent call last):
File "/home/featurize/work/GaussianObject/train_lora.py", line 115, in
trainer.fit(model, dataloader)
File "/environment/miniconda3/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 545, in fit
call._call_and_handle_interrupt(
File "/environment/miniconda3/lib/python3.10/site-packages/pytorch_lightning/trainer/call.py", line 44, in _call_and_handle_interrupt
return trainer_fn(*args, **kwargs)
File "/environment/miniconda3/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 581, in _fit_impl
self._run(model, ckpt_path=ckpt_path)
File "/environment/miniconda3/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 990, in _run
results = self._run_stage()
File "/environment/miniconda3/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 1036, in _run_stage
self.fit_loop.run()
File "/environment/miniconda3/lib/python3.10/site-packages/pytorch_lightning/loops/fit_loop.py", line 202, in run
self.advance()
File "/environment/miniconda3/lib/python3.10/site-packages/pytorch_lightning/loops/fit_loop.py", line 359, in advance
self.epoch_loop.run(self._data_fetcher)
File "/environment/miniconda3/lib/python3.10/site-packages/pytorch_lightning/loops/training_epoch_loop.py", line 136, in run
self.advance(data_fetcher)
File "/environment/miniconda3/lib/python3.10/site-packages/pytorch_lightning/loops/training_epoch_loop.py", line 259, in advance
call._call_callback_hooks(trainer, "on_train_batch_end", batch_output, batch, batch_idx)
File "/environment/miniconda3/lib/python3.10/site-packages/pytorch_lightning/trainer/call.py", line 208, in _call_callback_hooks
fn(trainer, trainer.lightning_module, *args, **kwargs)
File "/home/featurize/work/GaussianObject/cldm/logger.py", line 75, in on_train_batch_end
self.log_img(pl_module, batch, batch_idx, split="train")
File "/home/featurize/work/GaussianObject/cldm/logger.py", line 56, in log_img
images = pl_module.log_images(batch, split=split, **self.log_images_kwargs)
File "/environment/miniconda3/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/home/featurize/work/GaussianObject/cldm/cldm.py", line 366, in log_images
log["conditioning"] = log_txt_as_img((512, 512), batch[self.cond_stage_key], size=16) # text
File "/home/featurize/work/GaussianObject/ldm/util.py", line 19, in log_txt_as_img
font = ImageFont.truetype('font/DejaVuSans.ttf', size=size)
File "/environment/miniconda3/lib/python3.10/site-packages/PIL/ImageFont.py", line 791, in truetype
return freetype(font)
File "/environment/miniconda3/lib/python3.10/site-packages/PIL/ImageFont.py", line 788, in freetype
return FreeTypeFont(font, size, index, encoding, layout_engine)
File "/environment/miniconda3/lib/python3.10/site-packages/PIL/ImageFont.py", line 226, in init
self.font = core.getfont(
OSError: cannot open resource
May I ask why such an error occurred and how should it be corrected.
Sorry for the delayed response and thank you for your patience. We apologize for the oversight of missing font/DejaVuSans.ttf in our repository. It has now been added. Please check the updated repo.
Sorry for the delayed response and thank you for your patience. We apologize for the oversight of missing
font/DejaVuSans.ttfin our repository. It has now been added. Please check the updated repo.
Hi @GaussianObject , thank you for your solution, it works for me.
By the way, thank you for the great work!