TensorBoard.dev

Easily host, track, and share your ML experiments for free.

What is TensorBoard.dev?

A managed TensorBoard experience that lets you upload and share your ML experiment results with anyone.

Get started Example Colab
What is TensorBoard?

View this experiment

Why TensorBoard.dev?

Zero setup, free storage

Get started easily with no deployment. Free storage up to 10 million data points.

Familiar TensorBoard experience

The TensorFlow visualization toolkit you know and love.

Public, easy sharing

Instantly share your TensorBoard ML experiment results with anyone, for publications, troubleshooting, and team collaboration.

Get started

Use a simple command to upload and share your TensorBoard.

Note: Uploaded TensorBoards are public and visible to everyone. Do not upload sensitive data.

Prepare your TensorBoard logs

(or download a sample from here).

Upload the logs

Install the latest version of TensorBoard to use the uploader.


                    $ pip install -U tensorboard
                    

                    

                    # For help, run "tensorboard dev --help" or "tensorboard dev COMMAND --help"
                    

                    

                    # Upload an experiment:
                    

                    $ tensorboard dev upload --logdir logs \
                    

                        --name "(optional) My latest experiment" \
                    

                        --description "(optional) Simple comparison of several hyperparameters"
                    

                    

                    ***** TensorBoard Uploader *****
                    

                    

                    This TensorBoard will be visible to everyone. Do not upload sensitive
                    data.
                    

                    

                    Continue? (yes/NO)
                    

                    

                    Please visit this URL to authorize this application:
                    https://accounts.google.com/o/oauth2/auth...
                    

                    

                    Uploading to TensorBoard.dev at
                    
                      https://tensorboard.dev/experiment/QFRIzZJpTZCNRzi8N7zomA

View your experiment on TensorBoard.dev.

Follow the link provided to view your experiment, or share it with others. Make sure you keep track of it as it's the easiest way to access the experiment (for now). If you have any questions, reach out to tensorboard.dev-support@google.com.

Sign in to TensorBoard.dev.

Featured Experiments

Here are a few awesome TensorBoard.dev examples that people have uploaded and shared with us.

If you want your project to be included here, contact us.

Thumbnail screenshot of the Scalars dashboard for the experiment.

Vision Transformer

An experiment from this paper. The paper shows that a pure transformer applied directly to sequences of image patches can perform very well on image classification tasks.

Calibration of Prediction-time Batch Norm on ImageNet

Analysis from this paper showing how normalization techniques can improve model calibration across increasing levels of data shift. Shows values for the Brier Score and Expected Calibration Error uncertainty calibration metrics on ImageNet-C, organized by image shift type.

FAQ

What is TensorBoard?

TensorBoard is TensorFlow’s visualization toolkit, enabling you to track metrics like loss and accuracy, visualize the model graph, view histograms of weights, biases, or other tensors as they change over time, and much more. It is an open source tool that is part of the TensorFlow ecosystem. Learn more at tensorflow.org/tensorboard .

What TensorBoard functionality is available?

In this Preview, the Scalars, Graphs, Histograms, Distributions, and HParams dashboards are currently available. Additional TensorBoard dashboards will be added over time.

I want to see the experiments I have uploaded to TensorBoard.dev. Can I get a copy of my data?

Yes. Run the command tensorboard dev export --outdir OUTPUT_PATH.

How do I delete an experiment I've uploaded to TensorBoard.dev?

Run the command tensorboard dev delete --experiment_id EXPERIMENT_ID.

Do I need to install TensorBoard?

You do not need to install anything to view experiments uploaded to TensorBoard.dev. To upload, you need to install TensorBoard .

Is it free to use TensorBoard.dev?

Yes, you can view and upload TensorBoard logs for free. There are limits on how much can be stored. You can store up to:

100M scalars
1GB of tensor data
1GB of binary object data

Is my data public?

Any data uploaded to TensorBoard.dev will be visible to anyone with a link. Do not use it for sensitive data.

Do I need to create an account?

You need to sign in with your Google Account (or create one) to upload an experiment, so you can delete it if you want. You do not need to sign in to view an experiment.

How do I add a name and description to my experiment?

Use the --name and --description flags in the upload command. To change the name and description of an existing experiment, run the command tensorboard dev update-metadata --experiment_id EXPERIMENT_ID --name "New name" --description "New description".