kleinlee / DH_live

每个人都能用的数字人
567 stars 122 forks source link

报错 #46

Open zhangsanfather opened 3 weeks ago

zhangsanfather commented 3 weeks ago

微信图片_20240930141405 ===> Epoch2: Loss_DI: 0.2643 Loss_GI: 0.2390 Loss_perception: 7.0056 lr_g = 0.0001000 lr_d = 0.0001000 ===> Epoch2: Loss_DI: 0.2647 Loss_GI: 0.2664 Loss_perception: 6.9089 lr_g = 0.0001000 lr_d = 0.0001000 ===> Epoch2: Loss_DI: 0.2565 Loss_GI: 0.2877 Loss_perception: 6.6394 lr_g = 0.0001000 lr_d = 0.0001000 ===> Epoch2: Loss_DI: 0.2627 Loss_GI: 0.2995 Loss_perception: 6.7119 lr_g = 0.0001000 lr_d = 0.0001000 Traceback (most recent call last): File "F:\ai\DH_live\train\train_render_model.py", line 103, in for iteration, data in enumerate(training_data_loader): File "F:\ai\DH_live\py311\Lib\site-packages\torch\utils\data\dataloader.py", line 630, in next data = self._next_data() ^^^^^^^^^^^^^^^^^ File "F:\ai\DH_live\py311\Lib\site-packages\torch\utils\data\dataloader.py", line 673, in _next_data data = self._dataset_fetcher.fetch(index) # may raise StopIteration ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ai\DH_live\py311\Lib\site-packages\torch\utils\data_utils\fetch.py", line 52, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ai\DH_live\py311\Lib\site-packages\torch\utils\data_utils\fetch.py", line 52, in data = [self.dataset[idx] for idx in possibly_batched_index]


  File "F:\ai\DH_live\train\..\talkingface\data\few_shot_dataset.py", line 151, in __getitem__
    target_keypoints = self.driving_keypoints[video_index][current_clip]
                       ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^
IndexError: index 268 is out of bounds for axis 0 with size 267
Eikwang commented 2 weeks ago

素材片段太长了