Comments (3)
If you look at this url, when you use tf.layers.batch_normalization, you have to define update_ops
However, there were the following issues (Only in my case... NOT all people)
- There was a problem that the learning was not good(the accuracy was low).
- I personally like simple code. In that case, I wrote the code in a way that I would not add it because I do not think it would be well understood by other users.
It seemed like other users did not know something about control_dependencies or get_collection
So I used batch_norm in contrib
If you do updates_collections = None, the code is much simpler and easier to understand.
Also, the performance has been increased, and if you gave None, it's the same as doing control_dependencies above.
thank you
from densenet-tensorflow.
Oh wow! Many thanks for your detailed explanations!
You are so friendly~
I'm surprised that the performance will be affected!
Thanks for your sharing anyway.
BTW,
for the Global_Average_Pooling
I use tf.reduce_mean(input_tensor=x, axis=[1, 2], keep_dims=True)
What do you think~
from densenet-tensorflow.
Oh good idea.
Also, using reduce_mean is global_average_pooling.
from densenet-tensorflow.
Related Issues (20)
- A bug in transition layer HOT 29
- An question
- About pretrained model for transfer learning
- Hellow,I'm a beginner of DL
- why throws a ResourceExhaustedError after a 30 epochs training process?
- growing filter
- Testing from a Saved checkpoint
- shuffling data
- does not converge
- how to standardize a single image in testing phase?
- freeze densnet ckpt to pb problems.
- The graph couldn't be sorted in topological order.
- The inputs of all 1*1 layers in a dense block include the output of the transition layer?
- Model compilation failing with ValueError: Variable dense_1_bottleN_0_batch1/beta already exists, disallowed HOT 1
- pretrained weight for accuracy verification
- weights for the models provided HOT 4
- A bug in dense_block HOT 1
- Why the axis of concat layer is 3 HOT 2
- Data preprocessing HOT 1
- Implementation without compression or bottleneck layers
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 densenet-tensorflow.