CreamyLong

RuntimeError: result type Float can't be cast to the desired output type Byte when using average_models.py file , I got the above error.

[BUG]: AttributeError: module 'torch.distributed' has no attribute '_reduce_scatter_base'

1

### 🐛 Describe the bug When I run the code from https://github.com/hpcaitech/ColossalAI-Examples/tree/main/image/resnet, I got errors > **AttributeError: module 'torch.distributed' has no attribute '_reduce_scatter_base_** then I annotated the code in **colossalai/communication/collective.py**...

How do I build a image dataset with for IDDPM which uses labels for training?

1

I find that there is no dataset script in mmgen/datasets for conditional IDDPM traning.

'noist' to 'noisy'

add vae

3

reformat maybe needed

Grad strides do not match bucket view strides.

2

When I use DDP， I got this warning. Which code cause this? UserWarning: Grad strides do not match bucket view strides. This may indicate grad was not created according to...

When load the GLIGEN model, get the error of some weights unused. ``` from diffusers import StableDiffusionGLIGENPipeline pipe = StableDiffusionGLIGENPipeline.from_pretrained("gligen/diffusers-inpainting-text-box", revision="fp16", torch_dtype=torch.float16,local_files_only=True) pipe.to("cuda") ``` The config attributes {'use_gated_attention': True} were...

In A2C eval(), the agent does not move in the game, is the file loaded by fault?

is the network in A2C code same as the network in the paper? I find many difference