Chen Yang

Posting a train-log for who wants to know performance of this model . train-set 7.5w val-set 8.3k, using the default training-config but batch_size = 6. - Training: - 3669s -...

> 这个模型训练出来，有多大啊 103M

> I think you can contact the author of DewarpNet by email. Hi, could you share Doc3d dataset with baidu cloud. Cause i cannot cantact with author of DewarpNet. Thanks

> coming soon 你好，请问现在支持了？

> coming soon 你好，请问现在支持了？

> 同样碰到类似问题, 初始内存2.3G, 识别一段时间后会涨到6G, 而且内存不断上涨 你好，请问您这个问题解决了？

> I start the Gradio app.py. Before the UI is ready it complains it cannot download https://github.com/deepinsight/insightface/releases/download/v0.7/antelopev2.zip Clicking the link gives a 404. Download from this [URL](https://github.com/deepinsight/insightface/issues/1896#issuecomment-1023867304)

> 有人帮忙看看上面的仓库吗，国外的一个作者复现了EMO，我大致看了一下代码没有很大的问题，但是现在训练脚本跑不起来，哪位大神帮忙看看！ 请问你怎么确定它是可以的呐？有那些可信的点？

> Running with CUDA 11.7 on Ubuntu 20/04. > [2023-04-19 10:49:12,862] [WARNING] [runner.py:190:fetch_hostfile] Unable to find hostfile, will proceed with training with local resources only. [2023-04-19 10:49:12,872] [INFO] [runner.py:540:main] cmd...

> i mean the default training script for deepchat. 我刚好也在跑这个，跑了一个完整的流程，也遇到同样的OOM问题。 系统环境如下 cat /etc/issue　| Ubuntu 18.04.6 LTS \n \l nvcc --version　| Build cuda_11.3.r11.3/compiler.29745058_0 nvidia-smi | 3090 (单卡24G) pip list...