Repository files navigation

Don't train deep learning models blindfolded! Be impatient and look at each epoch of your training!

(RECENT CHANGES,EXAMPLES IN COLAB,API LOOKUP,CODE)

A live training loss plot inJupyter Notebook forKeras,PyTorch and other frameworks. An open-source Python package byPiotr Migdał,Bartłomiej Olechno andothers.Open for collaboration! (Some tasks are as simple as writing code docstrings, so - no excuses! :))

fromlivelossplotimportPlotLossesKerasmodel.fit(X_train,Y_train,epochs=10,validation_data=(X_test,Y_test),callbacks=[PlotLossesKeras()],verbose=0)

• (The most FA)Q: Why not TensorBoard?
• A: Jupyter Notebook compatibility (for exploration and teaching). The simplicity of use.

To installthis version from PyPI, type:

pip install livelossplot

To get the newest one from this repo (note that we are in the alpha stage, so there may be frequent updates), type:

pip install git+git://github.com/stared/livelossplot.git

Look at notebook files with full workingexamples:

• keras.ipynb - a Keras callback
• minimal.ipynb - a bare API, to use anywhere
• script.py - to be run as a script,python script.py
• bokeh.ipynb - a bare API, plots with Bokeh (open it in Colab to see the plots)
• pytorch.ipynb - a bare API, as applied to PyTorch
• 2d_prediction_maps.ipynb - example of custom plots - 2d prediction maps (0.4.1+)
• poutyne.ipynb - a Poutyne callback (Poutyne is a Keras-like framework for PyTorch)
• torchbearer.ipynb - an example using the built in functionality from torchbearer (torchbearer is a model fitting library for PyTorch)
• neptune.py andneptune.ipynb - aNeptune.AI
• matplotlib.ipynb - a Matplotlib output example
• various_options.ipynb - an extended API for metrics grouping and custom outputs

Yourun examples in Colab.

Text logs are easy, but it's easy to miss the most crucial information: is it learning, doing nothing or overfitting?Visual feedback allows us to keep track of the training process. Now there is one for Jupyter.

If you want to get serious - useTensorBoard, .But what if you just want to train a small model in Jupyter Notebook? Here is a way to do so, usinglivelossplot as a plug&play component

PlotLosses for a generic API.

plotlosses = PlotLosses()plotlosses.update({'acc': 0.7, 'val_acc': 0.4, 'loss': 0.9, 'val_loss': 1.1})plot.send()  # draw, update logs, etc

There are callbacks for common libraries and frameworks:PlotLossesKeras,PlotLossesKerasTF,PlotLossesPoutyne,PlotLossesIgnite.

Feel invited to write, and contribute, your adapter.If you want to use a bare logger, there isMainLogger.

Plots:MatplotlibPlot,BokehPlot.

Loggers:ExtremaPrinter (to standard output),TensorboardLogger,TensorboardTFLogger,NeptuneLogger.

To use them, initialize PlotLosses with some outputs:

plotlosses = PlotLosses(outputs=[MatplotlibPlot(), TensorboardLogger()])

There are custommatplotlib plots inlivelossplot.outputs.matplotlib_subplots you can pass inMatplotlibPlot arguments.

If you like to plot withBokeh instead ofmatplotlib, use

plotlosses = PlotLosses(outputs=[BokehPlot()])

This project supported byJacek Migdał,Marek Cichy,Casper da Costa-Luis, andPiotr Zientara.Join the sponsors - show your ❤️ and support, and appear on the list! It will give me time and energy to work on this project.

This project is also supported by a European programProgram Operacyjny Inteligentny Rozwój forGearShift - building the engine of behavior of wheeled motor vehicles and map’s generation based on artificial intelligence algorithms implemented on the Unreal Engine platform lead by ECC Games (NCBR grant GameINN).

It started asthis gist. Since it went popular, I decided to rewrite it as a package.

Oh, and I am in general interested in data vis, seeSimple diagrams of convoluted neural networks (and overview of deep learning architecture diagrams):

A good diagram is worth a thousand equations — let’s create more of these!

...ormy other data vis projects.

If you want more functionality - open anIssue or even better - prepare aPull Request.