Cai Jimin
Cai Jimin
Thanks very much for your tensorflow re-implementation of EAST. I want to freeze the graph with the checkpoint using freeze_graph.py, and I don't know the exact name of --output_node_names. I...
We use ros-kinetic and witnessed a few crashes occasionally. It’s hard to reproduce and I didn’t have reproducible test case. ``` #0 0x00007fc0be68f428 in __GI_raise (sig=sig@entry=6) at ../sysdeps/unix/sysv/linux/raise.c:54 #1 0x00007fc0be69102a...
We use ```ros-kinetic-dynamic-reconfigure 1.5.49-0xenial-20180316-113241-0800```. And occasionally ```rosrun dynamic_reconfigure dynparam load``` command reports ```error updating parameters: don't know parameter xxx```. After spent some time to investigate the symptom, I think race...
### System Info ```shell +-----------------------------------------------------------------------------+ | HL-SMI Version: hl-1.17.0-fw-51.1.0 | | Driver Version: 1.17.0-8a5dfb8 | |-------------------------------+----------------------+----------------------+ docker: vault.habana.ai/gaudi-docker/1.17.0/ubuntu22.04/habanalabs/pytorch-installer-2.3.1 ``` ### Information - [X] The official example scripts - [ ]...
首先非常感谢作者,我运行的方式为 `python app.py --transport webrtc --model wav2lip --avatar_id wav2lip256_avatar1` 启动后在浏览器里输入的是http://:8010/dashboard.html,“对话模式”的文本输入正常,后面调用LLM,包括语音播报也正常。 有个问题是点了麦克风按钮,进行语音输入的时候浏览器会报错 ``` Uncaught TypeError: Cannot set properties of null (setting 'srcObject') at RTCPeerConnection. (client.js:61:56) ``` 看了一下代码 ``` // connect audio...