TensorBoard

TensorBoard is the open-source visualization toolkit for machine learning: track experiment metrics, visualize model graphs, and debug training runs.

TensorBoard is your essential dashboard for ML workflow analysis, providing the measurements and visualizations needed to optimize models. It tracks key experiment metrics like loss and accuracy over time using the Scalars dashboard, helping you spot issues like overfitting immediately. You can visualize the complete model graph to understand data flow and debug architecture errors (e.g., with Keras models). Furthermore, it offers tools like the Histograms dashboard for examining weight and bias distributions, the Embedding Projector for dimensionality reduction (e.g., visualizing high-dimensional word embeddings), and full support across both the TensorFlow and PyTorch ecosystems.

https://www.tensorflow.org/tensorboard/