Comments (3)
Fixed it the problem was I was getting this error before
attempting to unscale fp16 gradients
if fixed by changing this
accelerator.clip_grad_norm_(params_to_clip, args.max_grad_norm)
optimizer.step()
lr_scheduler.step()
optimizer.zero_grad()
to
#accelerator.clip_grad_norm_(params_to_clip, args.max_grad_norm)
#optimizer.step()
lr_scheduler.step()
optimizer.zero_grad()
this apparently disabled some critical part of the process the actual fix was editing
"C:\Users\{your username}\anaconda3\envs\ST\Lib\site-packages\torch\cuda\amp\grad_scaler.py"
and changing
with torch.no_grad():
for group in optimizer.param_groups:
for param in group["params"]:
if param.grad is None:
continue
to
with torch.no_grad():
for group in optimizer.param_groups:
for param in group["params"]:
if param.grad is None:
continue
allow_fp16 = True
apparently theres an issue when using mixed precision and you need to explicitly enable this not sure of a better solution to add to the main train script's code as opposed to editing torch's files directly
from custom-diffusion.
Also as a side note since it seems that the gradient clipping is to focus the training.
Is it possible to use this method to finetune the entire model with this repo only asking as I cant finetune on a 8gb gpu with any other method and it would be interesting if this could technically fine tune the entire model
from custom-diffusion.
Hi,
Thanks a lot for pointing out the error with mixed precision training. I will look into it more.
Regarding enabling full fine-tune in the same code, it should be possible by adding another type in the --freeze_model
flag, and enabling all params to have gradients in the create_custom_diffusion
function. Also, in case of full fine-tuning calling save_progress
during training and load_model
during inference is not required.
Let me know if you need more details. I will see if I can update the code to enable this as well.
Thanks.
from custom-diffusion.
Related Issues (20)
- Errors in using diffuser version HOT 3
- A question for the regularization captions HOT 1
- questions about crossattn in CustomDiffusionAttnProcessor
- Question about the cross attention HOT 1
- ImportError: cannot import name 'insecure_hashlib' from 'huggingface_hub.utils' 怎么解决? HOT 1
- Hi, How toMultiple-Concept Fine-tuning for DreamBooth?
- if it OK with no regularization? my results don't have any consistancy with reference images. HOT 3
- Ours (w/fine-tune all) ? HOT 2
- OOM while running sample.py HOT 4
- why my optimization based weights merging is not work? HOT 4
- Is it possible to train multi joint training with SDXL? diffusers_training_sdxl.py seems impossible for multi joint training. HOT 2
- Question about loss on valid image region during training HOT 1
- Missing text prompts? HOT 2
- Does the diffusers version now work properly? HOT 3
- why the results produced by the model training and verification are inconsistent with the results I test using the saved model weights? HOT 1
- Evaluation:where is the “prompts.json”file?
- Unable to retrieve the image used for regularization. HOT 1
- Is this version trained with lora? HOT 1
- Tensors not Updated after Training HOT 1
- retrieve.py question HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from custom-diffusion.