Comments (3)
I see. Apparently I would need to loop through output names, in addition to losses (though: are many losses a typical thing?).
To do the whole thing - https://github.com/keras-team/keras/blob/master/keras/engine/training.py is a bit convolved.
If you want to give it a try, you are welcome (feel free to change this piece of code a lot - as I said, didn't test it so don't be afraid of a complete rewrite of this part).
from livelossplot.
@jonahweissman I admit I didn't test livelossplot
with multiple losses. I wrote based on my understanding on how does Keras deal with multiple losses.
Could you show me the line with model.compile
and the result of model.loss
, model.output_names
(and possibly, what is in logs
)?
from livelossplot.
Here's my line with model.compile
(I'm using the functional API):
model = Model(inputs=[weather_layers[0], day_layers[0], date_layers[0]], outputs=[usage_out,clients_out,sessions_out])
model.compile(loss='mean_absolute_percentage_error',
optimizer=Adam(0.0001))
In [1]: model.loss
Out[1]: 'mean_absolute_percentage_error'
In [2]: model.output_names
Out[2]: ['usage', 'clients', 'sessions']
In [3]: model.losses
Out[3]: []
I didn't specify loss functions for each output, so I believe it uses model.loss
for each.
from livelossplot.
Related Issues (20)
- log scale HOT 2
- KeyError : 'metrics' Please Help HOT 7
- How to plot live loss XGBOOST training? HOT 1
- Bug with latest keras HOT 3
- Bokeh vis not working in Colab HOT 2
- Can't pass arguments to PlotLossesKerasTF (figsize, fig_path) HOT 1
- Custom Message (Batch Size, etc) HOT 2
- How to plot multiple validation sets HOT 4
- Setup outputs as str HOT 6
- Make xlabel customizable HOT 4
- Sudden error that wasn't happen before - index 0 is out of bounds for axis 0 with size 0 HOT 1
- Positioning of legends HOT 1
- sliding start of epochs HOT 2
- WARNING : tensorflow:Callback method `on_train_batch_end` is slow compared to the batch time HOT 2
- PlotLossesKeras stops if tensorflow.keras is used without installing traditional keras HOT 2
- No plots showing for utils.Sequence Generator model HOT 3
- how to plot by batches?
- 'Plot2d' object has no attribute 'set_output_mode' HOT 1
- Ability to pass `figsize` for matplotlib plots
- ImageDataGenerator incompatible
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 livelossplot.