Comments (3)
Hi JunqiZhao ! In keras you can just use the callback named ModelCheckpoint to checkpoint the model and saving the weights while monitoring a quantity eg-val_loss, val_acc, etc. Later you can load the weights saved in .hdf5 format using function load_weights and sending in the path of the weights as an argument for it.
from lstm-human-activity-recognition.
Hi @deadskull7 ,
Thanks for your reply and suggestion, I will give it a try!
By the way, through recording the best performance obtained each time I train the model, the best performance varies from time to time, e,g, accuracy=[0.91, 0.92, 0.89....]. Right now, I am using the average of these accuracy values to evaluate different Network Architectures, I was wondering how would you suggest to quantify the model performance under such a situation?
Best,
Junqi
from lstm-human-activity-recognition.
I usually have a habit of evaluating the model performance by first plotting the learning graph and each time I plot the graph I try to see one of the following matching to the plot
- Underfitting – Validation and training error high
- Overfitting – Validation error is high, training error low
3. Good fit – Validation error low, slightly higher than the training error - Unknown fit - Validation error low, training error 'high'
The 4th one is quite different which says that your model is more good at testing the data which your model hasn't even seen which is quite suspicious. So this takes you to re-evaluate your data splitting method earlier. I hope I answered you.
from lstm-human-activity-recognition.
Related Issues (20)
- Why not change correct_pred to exempt one-hot?
- How to set up number of Epoch
- live recognition activity HOT 2
- How to know the values of all kind of weights
- fixed-width sliding windows of 2.56 sec and 50% overlap (128 readings/window). could you please explain it little bit more what does it mean and why you want to use it ?
- Validation on Saved Checkpoint HOT 1
- Clean pipeline using Neuraxle
- when I run the train_and_save.py,I got this error HOT 3
- How did you decide the number of hidden layers to be 32. Can you please explain this? HOT 1
- Can I use any smartphone sensors to test it?
- How to account for empty/null value readings for some of the sensors HOT 2
- IndexError: index 3 is out of bounds for axis 0 with size 3
- Something about the coordinate of IMU
- LSTM + KNN HOT 2
- Model application in android
- Creating chunks of segments HOT 1
- LSTM model is giving an ValueError while predicting based on X_test data HOT 1
- issue with builiding of nueral network on the current version of tensorflow HOT 2
- Lstm, generate .pkl. RuntimeError: cuDNN error: CUDNN_STATUS_MAPPING_ERROR HOT 1
- Can I use this method? I have the coordinates of several key points on the body of a rat, collected using a camera at 30 frames per second. The output is a label for the behavior category. HOT 1
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 lstm-human-activity-recognition.