yerfor
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
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 batch_idx, batch in enumerate(pbar):
File "D:\GeneFacePlusPlus_py39\python\lib\site-packages\tqdm\std.py", line 1182, in iter
for obj in iterable:
File "D:\GeneFacePlusPlus_py39\python\lib\site-packages\torch\utils\data\dataloader.py", line 633, in next
data = self._next_data()
File "D:\GeneFacePlusPlus_py39\python\lib\site-packages\torch\utils\data\dataloader.py", line 677, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "D:\GeneFacePlusPlus_py39\python\lib\site-packages\torch\utils\data_utils\fetch.py", line 51, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "D:\GeneFacePlusPlus_py39\python\lib\site-packages\torch\utils\data_utils\fetch.py", line 51, in
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 batch_idx, batch in enumerate(pbar): File "D:\GeneFacePlusPlus_py39\python\lib\site-packages\tqdm\std.py", line 1182, in iter for obj in iterable: File "D:\GeneFacePlusPlus_py39\python\lib\site-packages\torch\utils\data\dataloader.py", line 633, in next data = self._next_data() File "D:\GeneFacePlusPlus_py39\python\lib\site-packages\torch\utils\data\dataloader.py", line 677, in _next_data data = self._dataset_fetcher.fetch(index) # may raise StopIteration File "D:\GeneFacePlusPlus_py39\python\lib\site-packages\torch\utils\data_utils\fetch.py", line 51, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "D:\GeneFacePlusPlus_py39\python\lib\site-packages\torch\utils\data_utils\fetch.py", line 51, in data = [self.dataset[idx] for idx in possibly_batched_index] File "D:\GeneFacePlusPlus_py39\tasks\radnerfs\dataset_utils.py", line 406, in getitem bg_torso_img = bg_torso_img[..., :3] * bg_torso_img[..., 3:] + self.bg_img * (1 - bg_torso_img[..., 3:]) RuntimeError: The size of tensor a (3) must match the size of tensor b (0) at non-singleton dimension 3 'pkill' 不是内部或外部命令，也不是可运行的程序 或批处理文件。
你好，我也遇到了这个问题。请问解决了吗？
我解决了这个问题，应该是eye_blink_dim设置问题，找到egs\datasets\May\lm3d_radnerf_sr.yaml修改如下
eye_blink_dim: 8 #2 把2改为8，就ok； 其实不用它原来的checkpoints是不存在这个问题的