Comments (9)
Nice spot! Thanks! You are right about 7 blocks!!!
For RELU, I think as an activation function, without specific explanation, it should be added automatically.
I will fix the bug and retrain the model, the previous train mIOU seems to be a result of overfitting.
from deeplabv3-tensorflow.
You are welcome. How about weight decay of BN ?
from deeplabv3-tensorflow.
Yes, I will add it to config.py
.
from deeplabv3-tensorflow.
Hi, I found some changing architecture in your code in ASPP. You changed from concat to tf.add_n in the convolution (1×1) and convolutions (3x3) with difference rate, called (a) part. The ouput of addition will feed to global average pooling (b) part. Then results will concat to the (a). Why did you change from concat to add in (a)? And why is not input of global pooling features of block 4? And I also did not find that Batchnorm did not train in your ASPP. Thanks
from deeplabv3-tensorflow.
Hi, John, you are right. For the current version of validation mIOU, I trained with Imaging Pooling over the ASPP modules, this is different, I reverted to the original one shown in the paper since this is a reimplementation.
But I do find that the modified Imaging Pooling has some effect. I will retrain a little bit.
from deeplabv3-tensorflow.
Very surprised, When you train your model, do you also train the parameter of BN? The paper mentioned that he trained the BN with batch size 16 for 30k. After that, he froze the BN parameter and train with low learning rate. I asked this because you just use batch size 4, but still got very high performance (better than batch size 12 in the paper). I am running your code in my machine and I will lets you know my performance.
from deeplabv3-tensorflow.
@John1231983 I am rethinking the relu function in ASPP module. I heard you achieved 73% in validation data. So are you using relu or not?
from deeplabv3-tensorflow.
@NanqingD there are some variation over the Deeplabv3 arch if you are interested. See tensorflow/tensorflow#16452 (comment)
from deeplabv3-tensorflow.
Yes, it should include Relu as default option.
from deeplabv3-tensorflow.
Related Issues (20)
- Training Batch Normalization HOT 27
- shuffle batch out of range error HOT 1
- Multigrid block misunderstanding. HOT 16
- Can you share weights for the Network?
- get bug of memory leaks HOT 6
- '''image-level feature'''
- runs error
- How to visualize training results? HOT 4
- Verification problem?
- training error
- Checkpoint Error HOT 1
- No result in training
- ImportError: cannot import name 'VOC_CATS'
- Bad profoemance on the right and botton side of the image
- AttributeError: 'Namespace' object has no attribute 'is_training'
- PosiDeLabVv3 TysFouth-Fouth-Fas-FasMaskrCNN和TysSouth-DeLIPAB RESNET HOT 1
- streaming mean iou
- Where to get the SegmentationClassAug labels? HOT 1
- An issue about the train_voc12.py finished with exit code -1073741819 when processed step 1000 !!! HOT 1
- SPLIT_NAME.txt
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 deeplabv3-tensorflow.