Wok

It is mode collapse.  See [this tutorial](https://arxiv.org/abs/1701.00160v3) for instance.

> excuse me, what dataset are you using for training, I use ffhq, but the training is really too slow... It is in the first post. > Hello, > I...

You can find expected training times for StyleGAN2 here: https://github.com/NVlabs/stylegan2-ada-pytorch#expected-training-time For 128x128 resolution, with only 1 GPU, you should expect 13 seconds per kimg of training. For full training with...

For reference, this was @AdamDanielKing's answer on [HackerNews](https://news.ycombinator.com/item?id=20749037): > TalkToTransformer.com uses preemptible P4 GPUs on Google Kubernetes Engine. Changing the number of workers and automatically restarting them when they're preempted...

Were you able to use the finetuned model on Google Colab? I mean, are we sure that the issue only arises when using the model locally?

Isn't there a discrepancy between your two "run names"? Moreover, what happens if you leave `overwrite` to its default value (`False`)?

> In a new cell, copy paste the above to fine tune further Try to restart the Python session. #77 From the [README](https://github.com/minimaxir/gpt-2-simple/blob/master/README.md): > NB: Restart the Python session first...

> it wasn't clear to me that re-finetuning on the same model was covered by this - perhaps the wording can be tweaked to make this clearer? I agree. The...

> success: 8 You need to check what that error code means.

Based on [the README](https://github.com/bukson/steampy#market-methods) and [the code](https://github.com/bukson/steampy/blob/master/steampy/market.py), I would say no.