Comments (17)
Thank you so much. I will keep running the experiments and let you know if there is any update.
from stablesr.
Hi. Without training settings as well as the figures for comparison, it is hard to tell the problem. Maybe the test data distribution is very different from the validation one.
from stablesr.
Thanks for your very quick response. I got similar results as this issue #26.
The following zip file contains the training config. I just follow your suggestion to reset the model path.
2023-06-25T16-19-48-project.zip
And here is the results (right: result; left: input). The bottom one is a sample from validation set and it is also has been used for training. The above one did has some difference with the input, but the result is very far from the model you provided.
Thanks!
from stablesr.
Hi.
First, the input is different. My result is generated from a resized 128x128 image while it seems that you directly used the original 720x720 image.
Second, my results are generated with cfw weight = 0.5.
Third, my model is trained on 8 V100 GPUs, of which the training batch size, i.e., 48x4 should be much larger than yours, I guess.
You can train longer for better results, from my experience.
from stablesr.
Thanks! By the way, how long did you spend for the fine-tuning stage, maybe just around 24 hours?
from stablesr.
For several days. The longer the better. One week should be enough.
from stablesr.
Hi. First, the input is different. My result is generated from a resized 128x128 image while it seems that you directly used the original 720x720 image. Second, my results are generated with cfw weight = 0.5. Third, my model is trained on 8 V100 GPUs, of which the training batch size, i.e., 48x4 should be much larger than yours, I guess. You can train longer for better results, from my experience.
Thanks a lot for your help. Actually I did not train the cfw yet. Currently, I just want to make sure my fine-tuning results is reasonable. I think both of the resolution and the cfw weight should not be the reason.
As shown in the above figure, I use the same image as input and test with different fine-tuning model (stablesr_000117.ckpt that you provided and the model trained with 4 A100 cards with batch size of 12 and accumulated_grad_batches of 4). I finetune the model for about 24hrs and get the epoch_000131.ckpt).
The command that I used is "python scripts/sr_val_ddpm_text_T_vqganfin_old.py --config configs/stableSRNew/v2-finetune-test.yaml --ckpt "./pretrained_models/stablesr_000117.ckpt" --vqgan_ckpt "./pretrained_models/vqgan_cfw_00011.ckpt" --init-img ./inputs/test_example --outdir out_landscape/ --ddpm_steps 200 --dec_w 0.0 --suffix 'stablesr117'".
I set the dec_w to 0.0, so the result is achieved by only consider the fine-tuning without CFW. Did you have other suggestion for me to dubug? Or do you think I just need to train more days?
from stablesr.
For several days. The longer the better. One week should be enough.
So the provided model (stable_000117.ckpt) is achieved by fine-tuned for around a week? I thought 117 epoch model do not need to spend for so much time to get.
from stablesr.
The speed of A100 is more than 2x than V100, and I do not remember the exact training time of the 512 model.
It is hard to say whether there is a problem.
You may check the performance of different epochs on the real image.
The performance may vary for different epochs.
From my experience, training longer do improves the performance.
from stablesr.
Dear author,
Could you also show me how to use the thop package to print the params and flops of the stablesr. I tried to this use the test script (vqganfin_old.py) but not get succeed yet. Thanks!
from stablesr.
Dear author, Could you also show me how to use the thop package to print the params and flops of the stablesr. I tried to this use the test script (vqganfin_old.py) but not get succeed yet. Thanks!
I finally solved this problem.
from stablesr.
Dear author,
Here the training log is attached. I'm wondering if there is any difference with yours?
train_reproduce_4card_bs12.log
from stablesr.
Hi may I ask how did you generate the latent for the second stage training? it's supposed to be 4D? Cause I got the error saying dimension incorrect like this:
The latent shape I checked is:
This is where I generated them:
Thank you
from stablesr.
Thanks a lot!
from stablesr.
Hi may I ask how did you generate the latent for the second stage training? it's supposed to be 4D? Cause I got the error saying dimension incorrect like this:
The latent shape I checked is:
This is where I generated them:
Thank you
I currently only conducted the fine-tuning experiments and haven't trained the CFW since I found that my fine-tuning result is not good enough to train the CFW. How about your fine-tuning results? For training the CFW, I saw there is a issue #28 that might can help you.
from stablesr.
Hi may I ask how did you generate the latent for the second stage training? it's supposed to be 4D? Cause I got the error saying dimension incorrect like this:
The latent shape I checked is:
This is where I generated them:
Thank youI currently only conducted the fine-tuning experiments and haven't trained the CFW since I found that my fine-tuning result is not good enough to train the CFW. How about your fine-tuning results? For training the CFW, I saw there is a issue #28 that might can help you.
I think they are making sense but yea different than the author's results hmm, maybe can try fix the seeds for inference to check if the finetuning is successful? https://huggingface.co/docs/diffusers/using-diffusers/reproducibility
from stablesr.
Hi may I ask how did you generate the latent for the second stage training? it's supposed to be 4D? Cause I got the error saying dimension incorrect like this:
The latent shape I checked is:
This is where I generated them:
Thank youI currently only conducted the fine-tuning experiments and haven't trained the CFW since I found that my fine-tuning result is not good enough to train the CFW. How about your fine-tuning results? For training the CFW, I saw there is a issue #28 that might can help you.
I think they are making sense but yea different than the author's results hmm, maybe can try fix the seeds for inference to check if the finetuning is successful? https://huggingface.co/docs/diffusers/using-diffusers/reproducibility
I'm wondering if it is possible to share one example that you generated using only the fine-tuned model? Thanks a lot!
from stablesr.
Related Issues (20)
- SR Result is a noise image HOT 1
- About the issue of non-decreasing training loss HOT 2
- packages is strictly installed follow the procedure but still xformers install went wrong
- RuntimeError: PytorchStreamReader in demo colab StableSR_inference.ipynb HOT 1
- SD-Turbo HOT 3
- Training dataset question (whether crop small patches) HOT 4
- The effect of using display pictures is very poor HOT 4
- How to train StableSR with SD-turbo? HOT 1
- It seems to be a val_dataloader issue HOT 1
- Reporting an Issue with Google Colab Demo HOT 1
- Is there any implementation StableSR in diffusers? HOT 1
- Can I run the StableSR without CFW? HOT 3
- about size match of tensor HOT 4
- Share finding for compression experiment HOT 3
- Test output is black HOT 2
- About FID HOT 2
- ConnectionResetError:[Error 104] Connection reset by peer HOT 1
- Is time-aware guidance really important?
- Is vqgan_finetune_00011.ckpt the same as vqgan_cfw_00011.ckpt?
- Is it possible to set the output size to 256*256 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 stablesr.