Comments (5)
I have now tried fine-tuning my pre-trained model using both your hologerry/detectron2
codebase and the standard facebookresearch/detectron2
and in both cases I get around 39.8 bb AP. However, when I use your pre-trained weights for SoCo_FPN_100ep
and fine-tune on the standard detectron2 code I get 42.1 AP (very similar to the reported number in your paper of 41.9).
This suggests there is something different in the pre-training hyperparameters since I'm unable to replicate the paper's results.
Thanks for any help!
from soco.
Hi, I found that the result of mocov2 in Table 1 of the SOCO paper is particularly high (40.4 bb AP). But the experiment I have run shows that the result of fine-tuning a mask RCNN-R50 FPN with mocov2 backbone should be similar to the supervised pre-training (38.9 bb AP). Do you find this problem? Thanks!!!
from soco.
I've found the source of the difference. De to an error in the apex automatic mixed precision library I ended up using optimization setting O2 in my original run. When I fixed the bug and reran with optimization O1 it achieves 41.8 bb AP.
@yanjk3 Sorry I've not experimented on mocov2 in this setting so can't help. But good luck!
from soco.
Does the author not update this library ?
from soco.
Hello @linusericsson and @xiaoxiong007 The optimization level does affect the performance, for all results of our models are trained with O1 level.
There might be quite small differences among different runs as provided in the supplemental materials.
from soco.
Related Issues (20)
- training efficiency HOT 1
- TypeError: __call__() missing 1 required positional argument: 'view_size' HOT 1
- Question about COCO pretrained model HOT 1
- About BatchNormalization in finetuning Stage
- The settings between paper and code HOT 2
- HifaFace code
- What are the format requirements for the data? HOT 4
- How to turn off scale-aware assignment
- How to start pre training
- finetune detector HOT 1
- Hi,Can you provide the requirement.txt file ? HOT 1
- Is there a more detailed code instruction document? HOT 1
- pretrained models of R101
- pretrained models of R101
- imagenet_root
- dataset
- Question about the roi_box_head
- loss is negative and learning rate remain at 0
- Hi,how can i get proposals with cluster info in detr
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 soco.