metahuman-stream
metahuman-stream copied to clipboard
lipku
Real time streaming digital human based on nerf
which command should I execute to set up metahuman-stream using docker as readme file looks bit confusing? 请问我应该执行哪个命令来使用 Docker 设置 metahuman-stream？因为读起来 readme 文件有点混乱。
synctalk貌似效果比ernerf要好很多，配置环境一致，可以加入synctalk，或者直接掉换掉ernef的。 Regards
错误信息如下 Digest: sha256:7ea98f14222a8ac4d120dc6e711f44c4b93958220106b4fa6fc4c9f51b7397b6 Status: Downloaded newer image for registry.cn-hangzhou.aliyuncs.com/lipku/nerfstream:v1.3 docker: Error response from daemon: failed to create task for container: failed to create shim task: OCI runtime create failed: runc...
报错信息如下： stream = np.frombuffer(buffer, dtype=np.int16).astype(np.float32) / 32767 ValueError: buffer size must be a multiple of element size 2024-04-29T08:23:06Z {'REMOTE_ADDR': '127.0.0.1', 'REMOTE_PORT': '62544', 'HTTP_HOST': '127.0.0.1:8000', (hidden keys: 31)} failed with ValueError
Traceback (most recent call last): File "/home/anaconda3/envs/nerfstream/lib/python3.10/site-packages/gevent/pywsgi.py", line 1107, in handle_one_response self.run_application() File "/home/anaconda3/envs/nerfstream/lib/python3.10/site-packages/geventwebsocket/handler.py", line 75, in run_application self.run_websocket() File "/home/anaconda3/envs/nerfstream/lib/python3.10/site-packages/geventwebsocket/handler.py", line 52, in run_websocket list(self.application(self.environ, lambda s, h, e=None:...
[INFO] Trainer: ngp | 2024-05-07_08-43-54 | cuda | fp16 | data/video [INFO] #parameters: 1789121 [INFO] Loading data/pretrained/ngp_kf.pth ... Traceback (most recent call last): File "D:\metahuman-stream-main\app.py", line 442, in trainer =...
``` [INFO] loading ASR model cpierse/wav2vec2-large-xlsr-53-esperanto... /root/miniconda3/envs/nerfstream/lib/python3.10/site-packages/transformers/configuration_utils.py:363: UserWarning: Passing `gradient_checkpointing` to a config initialization is deprecated and will be removed in v5 Transformers. Using `model.gradient_checkpointing_enable()` instead, or if you are...
