Merge remote-tracking branch 'origin/master' into favyen/marine-infra

Author: favyen2

ai2_docs/landsat_vessels/api_use.md

@@ -5,9 +5,9 @@ The Landsat Vessel Detection API provides a way to apply the Landsat scenes for
 
 ## Overview
 - **Model Name**: Landsat Vessel Detection
-- **Model Version**: `v0.0.2`
-- **Tag**: `landsat_vessels_v0.0.2`
-- **Last Updated**: `2025-02-10`
+- **Model Version**: `v0.0.3`
+- **Tag**: `landsat_vessels_v0.0.3`
+- **Last Updated**: `2025-02-14`
 
 
 ## Setting Up the Environment
@@ -51,7 +51,7 @@ Prebuilt Docker images are available on GHCR. Use the following steps to pull an
 1. Pull the image from GHCR.
 
     ```bash
-    docker pull ghcr.io/allenai/landsat-vessel-detection:v0.0.2
+    docker pull ghcr.io/allenai/landsat-vessel-detection:v0.0.3
     ```
 
 2. Run the container. Note that you need to replace the `<port_number>` and `<path_to_service_account_key>` with the actual `LANDSAT_PORT` (if you use the default port, set it to `5555`) and path to your local service account key file, and keep the other arguments unchanged.
@@ -64,7 +64,7 @@ Prebuilt Docker images are available on GHCR. Use the following steps to pull an
     --env-file .env \
     --shm-size=15g \
     --gpus all \
-    ghcr.io/allenai/landsat-vessel-detection:v0.0.2
+    ghcr.io/allenai/landsat-vessel-detection:v0.0.3
     ```
 
 ## Making Requests to the API

ai2_docs/landsat_vessels/model_summary.md

@@ -2,9 +2,9 @@
 
 ## Overview
 - **Model Name**: Landsat Vessel Detection
-- **Model Version**: `v0.0.2`
-- **Tag**: `landsat_vessels_v0.0.2`
-- **Last Updated**: `2025-02-10`
+- **Model Version**: `v0.0.3`
+- **Tag**: `landsat_vessels_v0.0.3`
+- **Last Updated**: `2025-02-14`
 
 ---
 
@@ -58,3 +58,4 @@ Below is an example of the missed vessels, a lot of them are only visible in the
 ## Changelog
 - **`v0.0.1`**: Initial model release. Offline evaluation metrics reported.
 - **`v0.0.2`**: Improved pansharpening, added error message to LandsatResponse.
+- **`v0.0.3`**: Increase crop size.

rslp/landsat_vessels/config.py

@@ -22,7 +22,7 @@
 # Model config
 DETECT_MODEL_CONFIG = "data/landsat_vessels/config_detector.yaml"
 CLASSIFY_MODEL_CONFIG = "data/landsat_vessels/config_classifier.yaml"
-CLASSIFY_WINDOW_SIZE = 64
+CLASSIFY_WINDOW_SIZE = 128
 
 # Filter config
 INFRA_THRESHOLD_KM = 0.03  # max-distance between marine infra and prediction