Comments (9)
Duplicate with issue #12
"These metric files mainly serve as a reference for training losses. Please always refer to PQ numbers in the table."
from maskformer.
I have another question: in the last page of mask2former, use a config batch_size=16, epoch=75
for maskformer, would get a similar result to a config of batch_size=64, epoch=300
for maskformer, How big is the gap between these two results?
from maskformer.
I don't get the question. Table XI (c) of the Mask2Former paper reports the results with batch size 16.
from maskformer.
So, Is first row in Table XI (c) of the Mask2Former paper the result of maskformer using config batch_size=16, epoch=75
rather than using config batch_size=64, epoch=300
?
from maskformer.
Yes, Table XI (c) uses the parameters in Table XI (a), which is batch_size=16, epoch=75
. Note that the total number of iterations is the same, we simply decreases the batch_size and that's why number of epochs decreases by a factor of 4. So you can use the same MaskFormer config but only changing batchsize from 64 to 16 without other modification.
from maskformer.
Thank you.
from maskformer.
I am reimplementing maskformer based on mmdetection, see pr. When training with config r50 batch_size=16 epoch=75
, I get a result: PQ=46.9, which is 0.4 better than the result reported on paper Mask2former. Is this a normal fluctuation range?
from maskformer.
Yes, Table XI (c) uses the parameters in Table XI (a), which is
batch_size=16, epoch=75
. Note that the total number of iterations is the same, we simply decreases the batch_size and that's why number of epochs decreases by a factor of 4. So you can use the same MaskFormer config but only changing batchsize from 64 to 16 without other modification.
Beside the different batch_size, the weight_decay is also different. In maskformer(r50), weight_decay is 0.0001
, in Table XI (a) in paper mask2former, weight_decay is 0.0005 for maskformer.from maskformer.
Thanks a lot for reimplementing it on mmdetection!
I used weight decay 0.0001, the 0.0005 in the paper is a typo (thanks for pointing it out). If you trained the model using weight decay 0.0005, it could lead to a slight increase in the performance.
I think the reimplementation should be good as long as it performs no worse than the original MaskFormer (https://github.com/facebookresearch/MaskFormer/blob/main/MODEL_ZOO.md#panoptic-segmentation-models). Please remember to document the difference of parameters (batch size, weight decay, etc) in the README.
from maskformer.
Related Issues (20)
- Attention mask in last Swin basic layer HOT 1
- The comparsion between per-pixel classification and masks classification. HOT 1
- Question about general inference HOT 2
- Pascal_VOC12 is not working HOT 2
- About ignore value HOT 1
- Unable to open file (file signature not found) HOT 1
- Query on the Matching Step
- Get raw logits per pixel HOT 3
- Inputs preprocessing HOT 2
- Question about transformer decoder HOT 2
- How to train instance segmentation with COCO dataset? HOT 6
- Question about different decoder head HOT 1
- Extract only mask from the output
- Question about Pixel decoder last Conv2d layer
- A few questions about the configuration files
- Unable to train the model
- Error in training
- Whether mask embedding can also be seen as a dynamic kernel parameter?
- ValueError
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 maskformer.