Merge branch 'zdy'

experiment_screenshot_a11y_tree.py

@@ -44,6 +44,7 @@ logger.addHandler(sdebug_handler)
 logger = logging.getLogger("desktopenv.experiment")
 
 PATH_TO_VM = r"C:\Users\tianbaox\Documents\Virtual Machines\Ubuntu\Ubuntu.vmx"
+#PATH_TO_VM = "../../../../大文件/镜像/Ubuntu-1218/Ubuntu/Ubuntu.vmx"
 
 
 def run_one_example(example, agent, max_steps=10, example_trajectory_dir="exp_trajectory", recording=True):
@@ -142,6 +143,9 @@ def run_one_example(example, agent, max_steps=10, example_trajectory_dir="exp_tr
 
 def main(example_class, example_id):
     action_space = "pyautogui"
+    #example_class = "libreoffice_calc"
+    #example_id = "7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3"
+    #example_id = "01b269ae-2111-4a07-81fd-3fcd711993b0"
     gpt4_model = "gpt-4-vision-preview"
     gemini_model = "gemini-pro-vision"
 
@@ -152,6 +156,8 @@ def main(example_class, example_id):
     with open(f"evaluation_examples/examples/{example_class}/{example_id}.json", "r", encoding="utf-8") as f:
         example = json.load(f)
     example["snapshot"] = "exp_chrome"
+    #example["snapshot"] = "exp_setup4"
+    #example["snapshot"] = "Snapshot 30"
 
     api_key = os.environ.get("OPENAI_API_KEY")
     agent = GPT4v_Agent(api_key=api_key, model=gpt4_model, instruction=example['instruction'],