Comments (6)
Hi @whiteking64 ,
Thanks for your interest in LSeg!
- Currently, we provide the demo model for users to play around with it using any label set with random length and order.
- For all the ablation study such as the results in 5.1, we train LSeg with DPT and a smaller ViT-B/32 backbone together with the CLIP ViT-B/32 text encoder on ADE20k dataset. Therefore, you can follow the training and testing instruction in README. The primary thing to change is to set
--backbone clip_vitb32_384
, you can check details via this link. - For these experiments, for the demo model, we use batch size = 8, it is the same with the
train.sh
, we use 8 gpus, for each GPU, we load one batch. - Yes, we will share these weights. Please allow some time for me to sort them out (as well as the code). Should be in the next few months.
- For more details about the argument, please check here.
Hope this helps. Best wishes for your research!
from lang-seg.
Yes!
from lang-seg.
Thank you again!!
from lang-seg.
Thank you for your reply.
So, the command to reproduce your results in section 5.1 without any blocks (block depth = 0) is
python train_lseg.py \
--dataset ade20k \
--data_path ../datasets \
--batch_size 8 \
--exp_name lseg_ade20k_l32 \
--base_lr 0.004 \
--weight_decay 1e-4 \
--no-scaleinv \
--max_epochs 240 \
--widehead \
--accumulate_grad_batches 2 \
--backbone clip_vitb32_384 \
--num_features=512
I changed the backbone
and num_features
(which is 256 by default and in Table 5 you used 512 on the first row, and it is the same result as Table 4 with depth 0)
Am I correct?
Also, I just ran experimentally with batch size = 1 with 1 GPU. It took about 17 hours for one epoch. With 8 GPUs, I assume it is reduced to 2.1 hours, but 240 epochs would tale days to complete. Was it so on your experiments?
from lang-seg.
Hi @whiteking64 ,
In this case, when you are using smaller backbone, you could increase the --batch_size
as 4 or larger based on your GPU memory. I set it as 4 in my experiments, you could change it based on your GPU memory. As has been mentioned in the paper, we primarily use Quadro RTX 6000 or V100 for experiments, so it seems faster than your speed. In addition, we primarily follow the training principle of DPT. You could also refer to it for more details.
Hope this helps!
from lang-seg.
Is Model for demo
of this repo the same as the model in Section 5.2?
from lang-seg.
Related Issues (20)
- Different zero shot results, grad strides do not match butcket view strides HOT 2
- question about the "other" class HOT 1
- How long does it takes for default training? HOT 1
- Reproduction issue for Table 5 HOT 2
- How to get pixel-level embeddings HOT 4
- How to train the zero-shot model? HOT 2
- i have a question about text feature dimention HOT 1
- Can you provide the command to train models for Pascal-5i, COCO-20i, and fss? HOT 1
- Model parameter descriptions HOT 1
- RuntimeError: Trying to backward through the graph a second time HOT 2
- Training set used in demo model HOT 1
- Hard to reproduce the zero-shot results on COCO dataset. HOT 2
- Error with Pytorch Encoding HOT 13
- Link to zero-shot model of COCO fold 1
- about finetune_weights HOT 1
- about backward between enconde_text and encode_image HOT 1
- How to prepare and train on medical images?
- How can I download the torch-encoding library? HOT 1
- Installation errors HOT 1
- Problem when running the streamlit app
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 lang-seg.