guided-diffusion
guided-diffusion copied to clipboard
openai
Although the poster had closed the issue related to this https://github.com/openai/guided-diffusion/issues/23, I encountered the same issues when resuming training from a model checkpoint and solved it with OP's fix which...
I use python -m torch.distributed.launch --nproc_per_node=4 ... to train in a multiGPU way, but it is stuck in "dist_util.setup_dist()" which is the first sentence of main. Any body know the...
Hi, @unixpickle Thanks for your awesome work and open source. I met the `nan` issue when training on ImageNet 128x128, ``` ----------------------------- | lg_loss_scale | -1.62e+04 | | loss |...
In Line 297 of `unet.py`, I find the `flag` argument of `checkpoint(...)` is set to `True`. This is unlike other modules, which set the `flag` argument to `self.use_checkpoint`. Is it...
The generated image is too dark from official 256x256_diffusion_uncond.pt, anybody know about this?  specifically, in 'image_sample.py': copy sample before doing transformation on sample ```python sample_copy = sample sample =...
when i use [openai/improved-diffusion](https://github.com/openai/improved-diffusion) train my data to get a diffusion model ,i get three .pt, which one is the diffusion model? when i load the model in [andreas128](https://github.com/andreas128)[RePaint](https://github.com/andreas128/RePaint) ,i...
I want to sample images from the pretrained 64x64_diffusion model but am hitting a segfault with the suggested run configuration. I've downloaded the 64x64 checkpoints to a `models` folder and...
Hi, Thanks for sharing this repo! I am trying to train the models from scratch. It seems that TrainLoop(...).run_loop() function has a while loop that is running on infinitely, as...
Is there a feature similar to `max_to_keep` to limit how many checkpoints are saved? It would be nice to be able to limit to, say, 5, and delete all previous...
