diff --git a/GTSRB/03-Tracking-and-visualizing.ipynb b/GTSRB/03-Tracking-and-visualizing.ipynb index 7fefed30805f8439f2fb7a6afda740517fd8b498..0959101392736e55ca96650f533b4d613fc39c5b 100644 --- a/GTSRB/03-Tracking-and-visualizing.ipynb +++ b/GTSRB/03-Tracking-and-visualizing.ipynb @@ -302,9 +302,17 @@ "## Step 5 - Prepare callbacks \n", "We will add 2 callbacks : \n", " - **TensorBoard** \n", - "Training logs, which can be visualised with Tensorboard. \n", - "`# tensorboard --logdir ./run/logs` \n", - "IMPORTANT : Relaunch tensorboard on every run\n", + " Training logs, which can be visualised using Tensorboard tool. \n", + " Launch a terminal directly through the Jupyter interface (click on Menu button "File -> New -> Terminal").\n" + " CheGo to directory \n", + " # cd \n", + " Then launch \n", + " - `# tensorboard_launch --logdir ./run/logs` if using a Gricad node\n", + " - `# tensorboard --logdir ./run/logs` if using your own workstation\n", + " The Tensorboard visualization is available through a browser at : \n", + " - http://localhost:6007 (when running training using a Gricad node)\n", + " - http://localhost:6006 (when running training using your own workstation)\n", + " IMPORTANT : Relaunch tensorboard on every run\n", " - **Model backup** \n", " It is possible to save the model each xx epoch or at each improvement. \n", " The model can be saved completely or partially (weight). \n",