Comments (8)
Hi,
Thanks for your interest in our work. I have uploaded the training log for your reference. Our experiments are conducted with pytorch 1.10.0, cuda 11.1, and mmseg 0.18.0. We didn't set the random seed so there might be some differences between identical runs.
from denseclip.
@raoyongming
Thanks for your reply. My env is torch1.8.1_cuda10.1_mmseg_0.19.0, and I set a seed=0.
I think the "torch1.8.1_cuda10.1_mmseg_0.19.0" shouldn't make (43.5->42.8) degeneration of mIoU, I will try without setting seed.
from denseclip.
@raoyongming
Hi,
I find that with random seed setting, I can still not reproduce the paper results:
Have you verified the impact of the random seed of DenseCLIP? e.g., train multiple models and verify the robustness?
Look forward to your reply, Thanks!
Since DenseCLIP is a great work, and I want to use it as a baseline.
from denseclip.
I just check the logs of our experiments. It seems DenseCLIP-50 with the setting reported in our paper can generally achieve >43.0 mIoU in multiple runs in our environment. With different context lengths (4-32), DenseCLIP-r50 achieved 42.2-43.5 mIoU on ADE. I also notice the best results on ADE may depend on the last few iterations since the dataset is relatively small. So I think it seems ~43 mIoU should be reasonable considering it has largely outperformed the baseline (39.6 with CLIP+FPN).
from denseclip.
@raoyongming
Thanks for the quick reply!
Do you mean you got the 43.5 with the context_length of 32?
and according to the following calculation:
"context_length = self.text_encoder.context_length - self.context_length"
we get 32 by:
"32 = 37 - 5"
am I right?
look for your reply.
from denseclip.
Sorry for the confusion. The 43.5 mIoU is achieved by the model with a context length of 8 as reported in our paper. I mean the performance of different context lengths is in the range of 42.2-43.5. A longer context may not lead to better performance.
from denseclip.
@raoyongming
Thanks for the reply.
I tried 4 more different random seeds and got 42.6-43.1 mIoU with DenseCLIP-R50.
from denseclip.
I am not sure which reason causes the slightly low performance in your experiments. It may be related to the environment (hardware, cuda/pytorch versions, etc.). Since we tune the hyper-parameters based on DenseCLIP-R50, it is also possible that DenseCLIP-R50 will have higher performance than average. Maybe you can use the reproduced results as your baseline since your method and our baseline are evaluated in the same environment?
from denseclip.
Related Issues (20)
- Prompt learning via CoOp HOT 2
- Questions about text input HOT 2
- New MMCV and MMSegmentation version HOT 2
- about single-scale and multi-scale settings HOT 1
- Loading pretrained CLIP parameters but tuncate context_length in positional_embedding? HOT 2
- What does the different contexts_length setting based on? What is the meaning of separation? HOT 4
- vit-b-denseclip for semantic segmentation is lost HOT 1
- Code HOT 2
- question about how to use vit backbone in detection HOT 1
- question on the device HOT 1
- Code for any backbone(ImageNet) experiments on ADE20K segmentation
- downloading the pretrained weights HOT 1
- Question about DenseCLIP for Any Visual Backbone HOT 6
- Question about training process HOT 2
- super(SingleStageDetector, self).__init__(init_cfg) TypeError: __init__() takes 1 positional argument but 2 were given HOT 1
- Request about the pre-trained model of Swin Transformer+DenseCLIP
- Training details
- CUDA out of memory HOT 1
- some question about pixel-text matching loss HOT 1
- A little question about dimensions
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from denseclip.