Comments (5)
-
Do you mean the 'excluded' layers not restored from the checkpoint would have a faster learning rate? I don't think there will be a faster learning rate for these layers, since restoring from checkpoint mean there is simply a nicer set of weights that perform better than random weights. Otherwise, the variables are either trainable or non-trainable, and if they're trainable I guess they take the same amount of time. I'm not very sure if it is possible to set a different learning for different layers, or if there's a good rationale behind doing this.
-
The arg_scope is useful when you want to set certain parameters consistently throughout the model without having to repeat writing the same code again. The
arg_scope
is found here: https://github.com/tensorflow/models/blob/master/slim/nets/inception_resnet_v2.py
from transfer_learning_tutorial.
Hello,
Thank you very much for your responds. I agree with you. The reason I am wondering whether we can set different learning rate is because the layers restored from pre-trained model already has a nice set of parameters while the layers excluded (not restored from the checkpoint) do not. Thus, I suspect that the "excluded layers" need more training than the restored layers.
from transfer_learning_tutorial.
Yes indeed. The excluded layers will require some training before you can customize the model to your own use. However, I'm not sure if the excluded layers themselves each require a different learning rate.
from transfer_learning_tutorial.
Thanks a lot!
from transfer_learning_tutorial.
No problem :D
from transfer_learning_tutorial.
Related Issues (20)
- Number of Steps per Epoch not int HOT 1
- why other dataset 's result is zero? Final Accuracy: 0.0 HOT 8
- Negative Dimension Size HOT 3
- Inconstant Performance with Adam HOT 14
- Use my own data to finetune a model to predict? HOT 1
- Can you show me the example of labels.txt file? HOT 1
- Do we need to normalize the image range to [0,1]? HOT 1
- loss HOT 2
- How to write the labels.txt? HOT 1
- Input and output of the trained model HOT 2
- How can I use the files that are the output of this tutorial to classify a single image? HOT 1
- UnknownError: Input/Output Error HOT 1
- eval by use is_trainning=True HOT 1
- about labels HOT 1
- tf.train.import_meta_graph HOT 1
- After train my new add layer, how to fine turn with InceptionResnetV2 together next??
- labels of tfrecords parsed not correctly every now and then
- NotFoundError (see above for traceback): Key BatchNormalization/moving_mean not found in checkpoint
- HELP NEEDED!!!
- ckpt file
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 transfer_learning_tutorial.