yueool

训练报错，RuntimeError: The size of tensor a (3) must match the size of tensor b (0) at non-singleton dimension 3 求解答

3

Traceback (most recent call last): File "D:\GeneFacePlusPlus_py39\utils\commons\trainer.py", line 240, in run_single_process self.train() File "D:\GeneFacePlusPlus_py39\utils\commons\trainer.py", line 320, in train self.evaluate(self.task, False, 'Sanity Val', max_batches=self.num_sanity_val_steps) File "D:\GeneFacePlusPlus_py39\utils\commons\trainer.py", line 282, in evaluate for...

训练时 raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format 求指导

3

训练 python tasks/run.py --config=egs/datasets/x6/lm3d_radnerf_sr.yaml --exp_name=motion2video_nerf/may_head --reset ---------------------------------------------------- Traceback (most recent call last): File "D:\GeneFacePlusPlus_py39\utils\commons\trainer.py", line 151, in fit self.run_single_process(self.task) File "D:\GeneFacePlusPlus_py39\utils\commons\trainer.py", line 209, in run_single_process self.restore_weights(checkpoint) File "D:\GeneFacePlusPlus_py39\utils\commons\trainer.py", line 476,...

当执行 fit_3dmm_landmark.py 时，每次都是进行到52%就失败了，换了素材同样是52%失败？请好心人解答下

2

 我的环境是这样的： win10 python39 torch==2.0.1 cuda117 pytorch3d==0.7.5 每次都是进行到 52% 报错：Fail to allocate bitmapto data/processed/videos/x6/debug_fit_3dmm.mp4