JD Wu comments

Results 30 comments of


                                            JD Wu

issue with caffelib.cpp

same problem

Dueling Deep Q Learning with Doom: Memory Error

I changed pretrain_length and memory_size to 10000 then it work. But I think my RAM should be enough. Why comment 1million for GPU? it seems out of memory in the...

Training with different image size

you can train it with image size = 256 first, I will fix it soon.

I cannot start the Werewolf game, but I can run original metagpt startup successfully.

same here, any solution?

I cannot start the Werewolf game, but I can run original metagpt startup successfully.

I built werewolf game with new MetaGPT myself. Check here: https://github.com/WuJunde/werewolf_ai_agents if anyone is interested.

Multi-gpu fails on SLURM clusters

More than welcome to pull request

RuntimeError: a leaf Variable that requires grad is being used in an in-place operation.

> 我也遇到了这个问题，因为我是windows，dist.init_process_group(backend="gloo", init_method="env://")，所以初始化中的backend首先需要修改，不然就会报ncll错误。然后就遇到了跟您一样的问题，但是这样修改后可以跑通，在dist.broadcast前加入 > p = p +0 就可以了。我用的是自己的训练数据，但是现在的问题是GPU 利用率非常低，只能达到六七十的样子。请问您完美解决这个问题了吗 @170744039 Hi! Thank you for your awesome solution for Windows. Could you help to pull a request for your modification?...

JD Wu

issue with caffelib.cpp

Dueling Deep Q Learning with Doom: Memory Error

Training with different image size

I cannot start the Werewolf game, but I can run original metagpt startup successfully.

I cannot start the Werewolf game, but I can run original metagpt startup successfully.

Multi-gpu fails on SLURM clusters

RuntimeError: a leaf Variable that requires grad is being used in an in-place operation.

RuntimeError: a leaf Variable that requires grad is being used in an in-place operation.

BRATS model generating only black Samples

DATASET