354 lines
13 KiB
Python
354 lines
13 KiB
Python
import datetime
|
|
import json
|
|
import logging
|
|
import os
|
|
import sys
|
|
|
|
import func_timeout
|
|
|
|
from desktop_env.envs.desktop_env import DesktopEnv
|
|
from mm_agents.gpt_4v_agent import GPT4v_Agent
|
|
|
|
# Logger Configs {{{ #
|
|
logger = logging.getLogger()
|
|
logger.setLevel(logging.DEBUG)
|
|
|
|
datetime_str: str = datetime.datetime.now().strftime("%Y%m%d@%H%M%S")
|
|
|
|
file_handler = logging.FileHandler(os.path.join("logs", "normal-{:}.log".format(datetime_str)), encoding="utf-8")
|
|
debug_handler = logging.FileHandler(os.path.join("logs", "debug-{:}.log".format(datetime_str)), encoding="utf-8")
|
|
stdout_handler = logging.StreamHandler(sys.stdout)
|
|
sdebug_handler = logging.FileHandler(os.path.join("logs", "sdebug-{:}.log".format(datetime_str)), encoding="utf-8")
|
|
|
|
file_handler.setLevel(logging.INFO)
|
|
debug_handler.setLevel(logging.DEBUG)
|
|
stdout_handler.setLevel(logging.INFO)
|
|
sdebug_handler.setLevel(logging.DEBUG)
|
|
|
|
formatter = logging.Formatter(
|
|
fmt="\x1b[1;33m[%(asctime)s \x1b[31m%(levelname)s \x1b[32m%(module)s/%(lineno)d-%(processName)s\x1b[1;33m] \x1b[0m%(message)s")
|
|
file_handler.setFormatter(formatter)
|
|
debug_handler.setFormatter(formatter)
|
|
stdout_handler.setFormatter(formatter)
|
|
sdebug_handler.setFormatter(formatter)
|
|
|
|
stdout_handler.addFilter(logging.Filter("desktopenv"))
|
|
sdebug_handler.addFilter(logging.Filter("desktopenv"))
|
|
|
|
logger.addHandler(file_handler)
|
|
logger.addHandler(debug_handler)
|
|
logger.addHandler(stdout_handler)
|
|
logger.addHandler(sdebug_handler)
|
|
# }}} Logger Configs #
|
|
|
|
logger = logging.getLogger("desktopenv.experiment")
|
|
|
|
PATH_TO_VM = r"C:\Users\tianbaox\Documents\Virtual Machines\Ubuntu\Ubuntu.vmx"
|
|
|
|
|
|
def run_one_example(example, agent, max_steps=10, example_trajectory_dir="exp_trajectory", recording=True):
|
|
trajectory_recording_path = os.path.join(example_trajectory_dir, "trajectory.json")
|
|
env = DesktopEnv(
|
|
path_to_vm=PATH_TO_VM,
|
|
action_space=agent.action_space,
|
|
task_config=example
|
|
)
|
|
# reset the environment to certain snapshot
|
|
observation = env.reset()
|
|
done = False
|
|
step_num = 0
|
|
|
|
if recording:
|
|
# send a request to the server to start recording
|
|
env.controller.start_recording()
|
|
|
|
while not done and step_num < max_steps:
|
|
actions = agent.predict(observation)
|
|
step_num += 1
|
|
for action in actions:
|
|
# Capture the timestamp before executing the action
|
|
action_timestamp = datetime.datetime.now().strftime("%Y%m%d@%H%M%S")
|
|
logger.info("Step %d: %s", step_num, action)
|
|
|
|
observation, reward, done, info = env.step(action)
|
|
|
|
logger.info("Reward: %.2f", reward)
|
|
logger.info("Done: %s", done)
|
|
logger.info("Info: %s", info)
|
|
|
|
# Save screenshot and trajectory information
|
|
with open(os.path.join(example_trajectory_dir, f"step_{step_num}_{action_timestamp}.png"), "wb") as _f:
|
|
with open(observation['screenshot'], "rb") as __f:
|
|
screenshot = __f.read()
|
|
_f.write(screenshot)
|
|
|
|
with open(trajectory_recording_path, "a") as f:
|
|
f.write(json.dumps({
|
|
"step_num": step_num,
|
|
"action_timestamp": action_timestamp,
|
|
"action": action,
|
|
"reward": reward,
|
|
"done": done,
|
|
"info": info,
|
|
"screenshot_file": f"step_{step_num}_{action_timestamp}.png"
|
|
}))
|
|
f.write("\n")
|
|
|
|
if done:
|
|
logger.info("The episode is done.")
|
|
break
|
|
|
|
def stop_recording():
|
|
try:
|
|
env.controller.end_recording(os.path.join(example_trajectory_dir, "recording.mp4"))
|
|
except Exception as e:
|
|
print(f"An error occurred while stopping the recording: {e}")
|
|
|
|
try:
|
|
func_timeout.func_timeout(30, stop_recording)
|
|
except func_timeout.exceptions.FunctionTimedOut:
|
|
logger.info("Recording timed out.")
|
|
|
|
result = env.evaluate()
|
|
logger.info("Result: %.2f", result)
|
|
|
|
with open(trajectory_recording_path, "a") as f:
|
|
f.write(json.dumps({
|
|
"result": result
|
|
}))
|
|
f.write("\n")
|
|
|
|
# env.close()
|
|
logger.info("Environment closed.")
|
|
|
|
|
|
def main(example_class, example_id, gpt4_model="gpt-4-0125-preview"):
|
|
action_space = "pyautogui"
|
|
gemini_model = "gemini-pro-vision"
|
|
|
|
logger.info("Running example %s/%s", example_class, example_id)
|
|
logger.info("Using model %s", gpt4_model)
|
|
# logger.info("Using model %s", gemini_model)
|
|
|
|
with open(f"evaluation_examples/examples/{example_class}/{example_id}.json", "r", encoding="utf-8") as f:
|
|
example = json.load(f)
|
|
example["snapshot"] = "exp_v5"
|
|
|
|
api_key = os.environ.get("OPENAI_API_KEY")
|
|
agent = GPT4v_Agent(api_key=api_key, model=gpt4_model, instruction=example['instruction'], max_tokens=1000,
|
|
action_space=action_space, exp="a11y_tree")
|
|
|
|
# api_key = os.environ.get("GENAI_API_KEY")
|
|
# agent = GeminiPro_Agent(api_key=api_key, model=gemini_model, instruction=example['instruction'], action_space=action_space, exp="a11y_tree")
|
|
|
|
root_trajectory_dir = "exp_trajectory"
|
|
|
|
example_trajectory_dir = os.path.join(root_trajectory_dir, "a11y_tree", example_class, gpt4_model, example_id)
|
|
# example_trajectory_dir = os.path.join(root_trajectory_dir, "a11y_tree", example_class, gemini_model, example_id)
|
|
|
|
os.makedirs(example_trajectory_dir, exist_ok=True)
|
|
|
|
run_one_example(example, agent, 15, example_trajectory_dir)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
os_list = [
|
|
"94d95f96-9699-4208-98ba-3c3119edf9c2",
|
|
"bedcedc4-4d72-425e-ad62-21960b11fe0d",
|
|
"43c2d64c-bab5-4dcb-a30c-b888321c319a",
|
|
"7688b85f-87a4-4e4a-b2f8-f3d6c3f29b82",
|
|
"ec4e3f68-9ea4-4c18-a5c9-69f89d1178b3",
|
|
"f9be0997-4b7c-45c5-b05c-4612b44a6118",
|
|
"28cc3b7e-b194-4bc9-8353-d04c0f4d56d2",
|
|
"5ea617a3-0e86-4ba6-aab2-dac9aa2e8d57",
|
|
"e0df059f-28a6-4169-924f-b9623e7184cc",
|
|
"ddc75b62-7311-4af8-bfb3-859558542b36",
|
|
"b6781586-6346-41cd-935a-a6b1487918fc",
|
|
"3ce045a0-877b-42aa-8d2c-b4a863336ab8",
|
|
"a4d98375-215b-4a4d-aee9-3d4370fccc41",
|
|
"13584542-872b-42d8-b299-866967b5c3ef",
|
|
"23393935-50c7-4a86-aeea-2b78fd089c5c"
|
|
]
|
|
|
|
# for example_id in os_list:
|
|
# try:
|
|
# main("os", example_id, gpt4_model="gpt-3.5-turbo-16k")
|
|
# except Exception as e:
|
|
# logger.error("An error occurred while running the example: %s", e)
|
|
# continue
|
|
|
|
vlc_list = [
|
|
"8ba5ae7a-5ae5-4eab-9fcc-5dd4fe3abf89",
|
|
"8ba5ae7a-5ae5-4eab-9fcc-5dd4fe3abf89",
|
|
"8f080098-ddb1-424c-b438-4e96e5e4786e",
|
|
"bba3381f-b5eb-4439-bd9e-80c22218d5a7",
|
|
"fba2c100-79e8-42df-ae74-b592418d54f4",
|
|
"efcf0d81-0835-4880-b2fd-d866e8bc2294",
|
|
"8d9fd4e2-6fdb-46b0-b9b9-02f06495c62f",
|
|
"aa4b5023-aef6-4ed9-bdc9-705f59ab9ad6",
|
|
"386dbd0e-0241-4a0a-b6a2-6704fba26b1c",
|
|
"9195653c-f4aa-453d-aa95-787f6ccfaae9",
|
|
"d06f0d4d-2cd5-4ede-8de9-598629438c6e",
|
|
"a5bbbcd5-b398-4c91-83d4-55e1e31bbb81",
|
|
"f3977615-2b45-4ac5-8bba-80c17dbe2a37",
|
|
"215dfd39-f493-4bc3-a027-8a97d72c61bf"
|
|
]
|
|
|
|
chrome_list = [
|
|
"bb5e4c0d-f964-439c-97b6-bdb9747de3f4",
|
|
"7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3",
|
|
"06fe7178-4491-4589-810f-2e2bc9502122",
|
|
"e1e75309-3ddb-4d09-92ec-de869c928143",
|
|
"35253b65-1c19-4304-8aa4-6884b8218fc0",
|
|
"2ad9387a-65d8-4e33-ad5b-7580065a27ca",
|
|
"7a5a7856-f1b6-42a4-ade9-1ca81ca0f263",
|
|
"44ee5668-ecd5-4366-a6ce-c1c9b8d4e938",
|
|
"2ae9ba84-3a0d-4d4c-8338-3a1478dc5fe3",
|
|
"480bcfea-d68f-4aaa-a0a9-2589ef319381",
|
|
"af630914-714e-4a24-a7bb-f9af687d3b91"
|
|
]
|
|
|
|
calc_list = [
|
|
"eb03d19a-b88d-4de4-8a64-ca0ac66f426b",
|
|
"0bf05a7d-b28b-44d2-955a-50b41e24012a",
|
|
"7a4e4bc8-922c-4c84-865c-25ba34136be1",
|
|
"2bd59342-0664-4ccb-ba87-79379096cc08",
|
|
"ecb0df7a-4e8d-4a03-b162-053391d3afaf",
|
|
"7efeb4b1-3d19-4762-b163-63328d66303b",
|
|
"4e6fcf72-daf3-439f-a232-c434ce416af6",
|
|
"6054afcb-5bab-4702-90a0-b259b5d3217c",
|
|
"abed40dc-063f-4598-8ba5-9fe749c0615d",
|
|
"01b269ae-2111-4a07-81fd-3fcd711993b0",
|
|
"8b1ce5f2-59d2-4dcc-b0b0-666a714b9a14",
|
|
"0cecd4f3-74de-457b-ba94-29ad6b5dafb6",
|
|
"4188d3a4-077d-46b7-9c86-23e1a036f6c1",
|
|
"51b11269-2ca8-4b2a-9163-f21758420e78",
|
|
"7e429b8d-a3f0-4ed0-9b58-08957d00b127",
|
|
"347ef137-7eeb-4c80-a3bb-0951f26a8aff",
|
|
"6e99a1ad-07d2-4b66-a1ce-ece6d99c20a5",
|
|
"3aaa4e37-dc91-482e-99af-132a612d40f3",
|
|
"37608790-6147-45d0-9f20-1137bb35703d",
|
|
"f9584479-3d0d-4c79-affa-9ad7afdd8850",
|
|
"d681960f-7bc3-4286-9913-a8812ba3261a",
|
|
"21df9241-f8d7-4509-b7f1-37e501a823f7",
|
|
"1334ca3e-f9e3-4db8-9ca7-b4c653be7d17",
|
|
"357ef137-7eeb-4c80-a3bb-0951f26a8aff",
|
|
"aa3a8974-2e85-438b-b29e-a64df44deb4b",
|
|
"a01fbce3-2793-461f-ab86-43680ccbae25",
|
|
"4f07fbe9-70de-4927-a4d5-bb28bc12c52c",
|
|
]
|
|
|
|
# for example_id in calc_list:
|
|
# main("libreoffice_calc", example_id)
|
|
|
|
impress_list = [
|
|
# "5d901039-a89c-4bfb-967b-bf66f4df075e",
|
|
# "550ce7e7-747b-495f-b122-acdc4d0b8e54",
|
|
# "455d3c66-7dc6-4537-a39a-36d3e9119df7",
|
|
# "af23762e-2bfd-4a1d-aada-20fa8de9ce07",
|
|
# "c59742c0-4323-4b9d-8a02-723c251deaa0",
|
|
# "ef9d12bd-bcee-4ba0-a40e-918400f43ddf",
|
|
# "9ec204e4-f0a3-42f8-8458-b772a6797cab",
|
|
# "0f84bef9-9790-432e-92b7-eece357603fb",
|
|
# "ce88f674-ab7a-43da-9201-468d38539e4a",
|
|
# "3b27600c-3668-4abd-8f84-7bcdebbccbdb",
|
|
# "a097acff-6266-4291-9fbd-137af7ecd439",
|
|
# "bf4e9888-f10f-47af-8dba-76413038b73c",
|
|
"21760ecb-8f62-40d2-8d85-0cee5725cb72"
|
|
]
|
|
# for example_id in impress_list:
|
|
# main("libreoffice_impress", example_id)
|
|
|
|
thunderbird_list = [
|
|
# "bb5e4c0d-f964-439c-97b6-bdb9747de3f4",
|
|
# "7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3",
|
|
"12086550-11c0-466b-b367-1d9e75b3910e",
|
|
"06fe7178-4491-4589-810f-2e2bc9502122",
|
|
"6766f2b8-8a72-417f-a9e5-56fcaa735837",
|
|
"e1e75309-3ddb-4d09-92ec-de869c928143",
|
|
"3d1682a7-0fb0-49ae-a4dc-a73afd2d06d5",
|
|
"35253b65-1c19-4304-8aa4-6884b8218fc0",
|
|
"d088f539-cab4-4f9a-ac92-9999fc3a656e",
|
|
"2ad9387a-65d8-4e33-ad5b-7580065a27ca",
|
|
"480bcfea-d68f-4aaa-a0a9-2589ef319381",
|
|
"030eeff7-b492-4218-b312-701ec99ee0cc",
|
|
"94760984-3ff5-41ee-8347-cf1af709fea0",
|
|
"99146c54-4f37-4ab8-9327-5f3291665e1e",
|
|
"c9e7eaf2-b1a1-4efc-a982-721972fa9f02"
|
|
]
|
|
# for example_id in thunderbird_list:
|
|
# main("thunderbird", example_id)
|
|
|
|
gimp_list = [
|
|
"7a4deb26-d57d-4ea9-9a73-630f66a7b568",
|
|
"554785e9-4523-4e7a-b8e1-8016f565f56a",
|
|
"77b8ab4d-994f-43ac-8930-8ca087d7c4b4",
|
|
"f4aec372-4fb0-4df5-a52b-79e0e2a5d6ce",
|
|
"d52d6308-ec58-42b7-a2c9-de80e4837b2b",
|
|
"2a729ded-3296-423d-aec4-7dd55ed5fbb3",
|
|
"b148e375-fe0b-4bec-90e7-38632b0d73c2",
|
|
"a746add2-cab0-4740-ac36-c3769d9bfb46",
|
|
"7b7617bd-57cc-468e-9c91-40c4ec2bcb3d",
|
|
"d16c99dc-2a1e-46f2-b350-d97c86c85c15",
|
|
"06ca5602-62ca-47f6-ad4f-da151cde54cc",
|
|
"e2dd0213-26db-4349-abe5-d5667bfd725c",
|
|
"f723c744-e62c-4ae6-98d1-750d3cd7d79d",
|
|
"72f83cdc-bf76-4531-9a1b-eb893a13f8aa",
|
|
"7767eef2-56a3-4cea-8c9f-48c070c7d65b",
|
|
"734d6579-c07d-47a8-9ae2-13339795476b"
|
|
]
|
|
|
|
# for example_id in gimp_list:
|
|
# try:
|
|
# main("gimp", example_id)
|
|
# except Exception as e:
|
|
# logger.error("An error occurred while running the example: %s", e)
|
|
# continue
|
|
|
|
vs_code_list = [
|
|
"0ed39f63-6049-43d4-ba4d-5fa2fe04a951",
|
|
"53ad5833-3455-407b-bbc6-45b4c79ab8fb",
|
|
"eabc805a-bfcf-4460-b250-ac92135819f6",
|
|
"982d12a5-beab-424f-8d38-d2a48429e511",
|
|
"4e60007a-f5be-4bfc-9723-c39affa0a6d3",
|
|
"e2b5e914-ffe1-44d2-8e92-58f8c5d92bb2",
|
|
"9439a27b-18ae-42d8-9778-5f68f891805e",
|
|
"ea98c5d7-3cf9-4f9b-8ad3-366b58e0fcae",
|
|
"930fdb3b-11a8-46fe-9bac-577332e2640e",
|
|
"276cc624-87ea-4f08-ab93-f770e3790175",
|
|
"9d425400-e9b2-4424-9a4b-d4c7abac4140"
|
|
]
|
|
|
|
# for example_id in vs_code_list:
|
|
# try:
|
|
# main("vs_code", example_id)
|
|
# except Exception as e:
|
|
# logger.error("An error occurred while running the example: %s", e)
|
|
# continue
|
|
|
|
multiple_list = [
|
|
"f8cfa149-d1c1-4215-8dac-4a0932bad3c2",
|
|
"897e3b53-5d4d-444b-85cb-2cdc8a97d903",
|
|
"4e9f0faf-2ecc-4ae8-a804-28c9a75d1ddc",
|
|
"b52b40a5-ad70-4c53-b5b0-5650a8387052",
|
|
"46407397-a7d5-4c6b-92c6-dbe038b1457b",
|
|
"2b9493d7-49b8-493a-a71b-56cd1f4d6908",
|
|
"51f5801c-18b3-4f25-b0c3-02f85507a078",
|
|
"2c9fc0de-3ee7-45e1-a5df-c86206ad78b5",
|
|
"510f64c8-9bcc-4be1-8d30-638705850618",
|
|
"937087b6-f668-4ba6-9110-60682ee33441",
|
|
"ee9a3c83-f437-4879-8918-be5efbb9fac7",
|
|
"3680a5ee-6870-426a-a997-eba929a0d25c",
|
|
"e135df7c-7687-4ac0-a5f0-76b74438b53e",
|
|
"58565672-7bfe-48ab-b828-db349231de6b",
|
|
"2fe4b718-3bd7-46ec-bdce-b184f5653624"
|
|
]
|
|
|
|
for example_id in multiple_list:
|
|
try:
|
|
main("multi_apps", example_id)
|
|
except Exception as e:
|
|
logger.error("An error occurred while running the example: %s", e)
|
|
continue
|
|
|