opensource/Agent-S
3
0
Fork 0
mirror of https://github.com/simular-ai/Agent-S.git synced 2026-08-29 02:03:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add grounding model height option

Browse Source
This commit is contained in:
DaWe
2025-05-23 22:03:46 +02:00
parent 63a4350185
commit 00727e1294
2 changed files with 24 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
gui_agents/s2/cli_app.py
+12 -3
View File
@@ -185,6 +185,12 @@ def main():
default=1366,
help="Width of screenshot image after processor rescaling",
)
parser.add_argument(
"--grounding_model_resize_height",
type=int,
default=None,
help="Height of screenshot image after processor rescaling",
)
# Grounding model config option 2: Self-hosted endpoint based
parser.add_argument(
@@ -233,13 +239,16 @@ def main():
"api_key": args.endpoint_api_key,
}
else:
grounding_height = args.grounding_model_resize_height
# If not provided, use the aspect ratio of the screen to compute the height
if grounding_height is None:
grounding_height = screen_height * args.grounding_model_resize_width / screen_width
engine_params_for_grounding = {
"engine_type": args.grounding_model_provider,
"model": args.grounding_model,
"grounding_width": args.grounding_model_resize_width,
"grounding_height": screen_height
* args.grounding_model_resize_width
/ screen_width,
"grounding_height": grounding_height,
}
grounding_agent = OSWorldACI(
osworld_setup/s2/run.py
+12 -3
View File
@@ -133,6 +133,12 @@ def config() -> argparse.Namespace:
default=1366,
help="Width of screenshot image after processor rescaling",
)
parser.add_argument(
"--grounding_model_resize_height",
type=int,
default=None,
help="Height of screenshot image after processor rescaling",
)
# Configuration 2
parser.add_argument("--endpoint_provider", type=str, default="")
@@ -190,13 +196,16 @@ def test(args: argparse.Namespace, test_all_meta: dict) -> None:
"api_key": args.endpoint_api_key,
}
else:
grounding_height = args.grounding_model_resize_height
# If not provided, use the aspect ratio of the screen to compute the height
if grounding_height is None:
grounding_height = args.screen_height * args.grounding_model_resize_width / args.screen_width
engine_params_for_grounding = {
"engine_type": args.grounding_model_provider,
"model": args.grounding_model,
"grounding_width": args.grounding_model_resize_width,
"grounding_height": args.screen_height
* args.grounding_model_resize_width
/ args.screen_width,
"grounding_height": grounding_height,
}
# NEW!