Elsaam2y / DINet_optimized

An optimized pipeline for DINet reducing inference latency for up to 60% 🚀. Kudos for the authors of the original repo for this amazing work.
104 stars 17 forks source link

推理报错是为什么呀 #28

Open xiaoliu123881 opened 3 weeks ago

xiaoliu123881 commented 3 weeks ago

(dinet_opt) @jupiter:~/DINet-master$ python inference.py --mouth_region_size=256 --source_video_path=./asserts/examples/test1.mp4 --source_openface_landmark_path=./asserts/examples/test1.csv --driving_audio_path=./asserts/examples/driving_audio_1.wav --pretrained_clip_DINet_path=./asserts/clip_training_DINet_256mouth.pth 2024-10-30 20:44:13.664312: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory 2024-10-30 20:44:13.664409: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. extracting frames from video: ./asserts/examples/test1.mp4 warning: the input video is not 25 fps, it would be better to trans it to 25 fps! extracting deepspeech feature from : ./asserts/examples/driving_audio_1.wav Traceback (most recent call last): File "/DINet-master/inference.py", line 44, in DSModel = DeepSpeech(opt.deepspeech_model_path) File "/DINet-master/utils/deep_speech.py", line 13, in init = self._prepare_deepspeech_net(model_path) File "/DINet-master/utils/deep_speech.py", line 22, in _prepare_deepspeech_net logits_ph = graph.get_tensor_by_name("deepspeech/logits:0") File "/.conda/envs/dinet_opt/lib/python3.9/site-packages/tensorflow/python/framework/ops.py", line 4150, in get_tensor_by_name return self.as_graph_element(name, allow_tensor=True, allow_operation=False) File "/.conda/envs/dinet_opt/lib/python3.9/site-packages/tensorflow/python/framework/ops.py", line 3974, in as_graph_element return self._as_graph_element_locked(obj, allow_tensor, allow_operation) File "/.conda/envs/dinet_opt/lib/python3.9/site-packages/tensorflow/python/framework/ops.py", line 4014, in _as_graph_element_locked raise KeyError("The name %s refers to a Tensor which does not " KeyError: "The name 'deepspeech/logits:0' refers to a Tensor which does not exist. The operation, 'deepspeech/logits', does not exist in the graph."