Updated documentation

Signed-off-by: Nicolas de Lima <[email protected]>
ekumenlabs · Sep 25, 2024 · 8bd8b3b · 8bd8b3b
1 parent 1a56bf7
commit 8bd8b3b
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 2 deletions.
diff --git a/README.md b/README.md
@@ -132,11 +132,17 @@ After the training ends, a `model.pth` file will be available inside `model`. Ad
 docker compose -f docker/docker-compose.yml --profile training_test up
 ```
 
-This will evaluate every image in the `DATASET_NAME` and generate annotated images in the `model` folder.
+This will evaluate every image in the `DATASET_NAME` and generate annotated images in the `model/test_output` folder.
 
 ### Training logs visualization
 
-The logs generated when training a model are stored in the `training_ws/runs` folder and they can be visualized using the profile `training_vis`. This profile runs Tensorboard over `localhost:6006`, and can be accessed via a web browser.
+The logs generated when training a model are stored in the `model/runs` folder and they can be visualized using the profile `training_vis`. This profile runs Tensorboard over `localhost:6006`, and can be accessed via a web browser. To run the Tensorboard server, execute:
+
+```bash
+docker compose -f docker/docker-compose.yml --profile training_vis up
+```
+
+![Tensorboard dashboard](./doc/tensorboard.png)
 
 ## Run
 

diff --git a/doc/tensorboard.png b/doc/tensorboard.png