wendellgithub0206

> 你好！我訓練了40個epochs，batch_size=1，但是生成器的損失函數好像沒有收斂，這是為什麼呢？能否請您提供一些建議，謝謝 -For the generator, its Loss drops rapidly, and it is likely that the discriminator is too weak, causing thegenerator to easily "fool" the discriminator. -For the discriminator, the...

@donglixp First, thank you for your help! I tried using the method you provided and received the following message. ``` [master 45d484f] Saving files before refreshing line endings 1 file...

@donglixp Okay, I understand. I will try to change the environment. Thank you very much for your help!

> 我懂了。該錯誤可能是由使用 WSL 引起的。我不確定 WSL 是否支援 Gradio。 Hi! @donglixp Thank you for all your help so far. I have confirmed that WSL supports Gradio. The current error: ``` (kosmos) wendell@DESKTOP-3Q0HFJ3:~/unilm/kosmos-2$...

I adjusted the version of xformer The current error: ``` /home/wendell/anaconda3/envs/kosmos/lib/python3.9/site-packages/torch/distributed/launch.py:180: FutureWarning: The module torch.distributed.launch is deprecated and will be removed in future. Use torchrun. Note that --use_env is set...

I want to know how to train and how to apply the model after training is complete? How to present the results?