Comments (5)
Can you give more details?
from marigold.
Hi @markkua thanks for the message. I modified my training code from instruct_pix2pix to enable the marigold fine-tuning protocol and I changed the input and output conv layer of the unet to match my task, e.g. I'm taking RGB images as input and output albedo (also in RGB). I also modified the Marigold pipeline to adapt the inference to enable the three-channel output.
Also, I'm using DDPM during training with 1k diffusion steps and DDIM with 50 sample steps at inference. I also set the ensemble to 10 to match your implementation details. The training takes roughly 48 hrs on A100 and I attached an example below.
Input | Output |
---|---|
I think the training works since it generates the albedo, however, it's noticeable that there is still noise on the centered object. The generation is not clean enough. The results presented in the paper are stunning. I think I may missed something I didn't notice yet.
Looking forward to hearing your insights.
Best,
Jing
from marigold.
Hi,
From your description, I assume that you adjust the unet output layer to have three latents. As you are exporting three-channel albedo, have you tried directly using one latent, which gives you three channels after decoding.
On the other hand, adapting Marigold to a different modality might require different training hyperparameters.
Best.
from marigold.
Hi @markkua ,
Thanks for the message. I'm currently outputting only one latent code (4-dim) as the output of the unet. I believe the network structure has not changed that much. The colored output is also via a similar decoder in marigold_pipeline but comment this line.
As for the training, I also prepared 10k image pairs of input RGB images and albedo images.
Please let me know if I missed anything or misunderstood anything.
Best,
Jing
from marigold.
Solved, thx
from marigold.
Related Issues (20)
- Validation Error
- Fine-tune the base model
- What does the consistent value of 721.5377 represent in eigen_test_files_with_gt.txt? HOT 1
- Questions about LCM model training HOT 2
- noob questions about code understanding. HOT 3
- [HuggingFace] is it possible to fine-tune Marigold using the AutoTrainer on my custom dataset ?
- very slow inference
- Use data sets of different resolutions for training
- Use data sets with different resolutions for training
- The purpose of using v_prediction as the target? HOT 1
- where can I get the "output/marigold_base/checkpoint/latest" HOT 1
- The demo 3D looks ok but not match with the predicted depth image HOT 1
- How to organize the vkitti data HOT 1
- train the model on my custom dataset HOT 1
- Unusual slow training speed HOT 8
- About some problems that arise during training HOT 9
- issue with reproducing results in the paper HOT 1
- Is it possible to train the model by feeding it rgb images + 8-bit relative depth maps ? HOT 1
- Muti-GPUs training
- Data cannot be read during training 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 marigold.