stanfordnlp / wge Goto Github PK
View Code? Open in Web Editor NEWWorkflow-Guided Exploration: sample-efficient RL agent for web tasks
Home Page: https://stanfordnlp.github.io/wge/
License: Other
Workflow-Guided Exploration: sample-efficient RL agent for web tasks
Home Page: https://stanfordnlp.github.io/wge/
License: Other
hi:
when trying to reproduce your work, this line failed:
git clone https://github.com/stanfordnlp/miniwob-demos.git $REPO_DIR/third-party/miniwob-demos export RL_DEMO_DIR=$REPO_DIR/third-party/miniwob-demos/
after inspection it's not public available. Will you release it?
Hi,
Thanks for the great repo.
I trained a model on the task "login-user" and save the checkpoints.
I want to test the model, but the documentation doesn't explain the test.
Is there a test program?
Or please help me any guide and tip for testing the model.
Thanks.
SeungKwon
hi:
when running pytest, the following error occurred, without changing any single line of code/data:
========================== test session starts ===========================
platform darwin -- Python 2.7.10, pytest-3.5.0, py-1.5.3, pluggy-0.6.0
rootdir: /Users/wge/wge, inifile:
collected 9 items
wge/tests/miniwob/test_environment.py BASE URL: http://localhost:8765/
.BASE URL: http://localhost:8765/
========================================
[u'Click the button.', u'Click the button.', u'Click the button.']
[dummy: 'dummy', dummy: 'dummy', dummy: 'dummy']
FBASE URL: http://localhost:8765/
Iteration 1 / 50
Iteration 2 / 50
Iteration 3 / 50
Iteration 4 / 50
Iteration 5 / 50
Iteration 6 / 50
Iteration 7 / 50
Iteration 8 / 50
Iteration 9 / 50
Iteration 10 / 50
Iteration 11 / 50
Iteration 12 / 50
Iteration 13 / 50
Iteration 14 / 50
Iteration 15 / 50
Iteration 16 / 50
Iteration 17 / 50
Iteration 18 / 50
Iteration 19 / 50
Iteration 20 / 50
Iteration 21 / 50
Iteration 22 / 50
Iteration 23 / 50
Iteration 24 / 50
Iteration 25 / 50
Iteration 26 / 50
Iteration 27 / 50
Iteration 28 / 50
Iteration 29 / 50
Iteration 30 / 50
Iteration 31 / 50
Iteration 32 / 50
Iteration 33 / 50
Iteration 34 / 50
Iteration 35 / 50
Iteration 36 / 50
Iteration 37 / 50
Iteration 38 / 50
Iteration 39 / 50
Iteration 40 / 50
Iteration 41 / 50
Iteration 42 / 50
Iteration 43 / 50
Iteration 44 / 50
Iteration 45 / 50
Iteration 46 / 50
Iteration 47 / 50
Iteration 48 / 50
Iteration 49 / 50
Iteration 50 / 50
Average time: 0.0230975866318
SD: 0.000102856725524
.BASE URL: http://localhost:8765/
========================================
Clicking with click([4] button @ (61.0, 74.0) text=u'Click Me!' classes=[NO_CLASS])
{'n': [{u'reason': None, 'elapsed': 0.0477290153503418, u'done': False, u'raw_reward': 0, u'env_reward': 0}, {'elapsed': 0.34470105171203613, u'done': True, u'raw_reward': 1, u'env_reward': 0.9676}, {u'reason': None, 'elapsed': 0.3376748561859131, u'done': False, u'raw_reward': 0, u'env_reward': 0}]}
{'n': [{u'reason': None, 'elapsed': 0.10628294944763184, u'done': False, u'raw_reward': 0, u'env_reward': 0}, {'elapsed': 0.36610984802246094, u'done': True, u'raw_reward': 1, u'env_reward': 0.9676}, {u'reason': None, 'elapsed': 0.39337682723999023, u'done': False, u'raw_reward': 0, u'env_reward': 0}]}
{'n': [{u'reason': None, 'elapsed': 0.029836177825927734, u'done': False, u'raw_reward': 0, u'env_reward': 0}, {u'reason': None, 'elapsed': 0.05690813064575195, u'done': False, u'raw_reward': 0, u'env_reward': 0}, {u'reason': None, 'elapsed': 0.045066118240356445, u'done': False, u'raw_reward': 0, u'env_reward': 0}]}
Clicking with click([4] button @ (16.0, 97.0) text=u'Click Me!' classes=[NO_CLASS])
Clicking with click([4] button @ (34.0, 52.0) text=u'Click Me!' classes=[NO_CLASS])
{'n': [{'elapsed': 0.06305098533630371, u'done': True, u'raw_reward': 1, u'env_reward': 0.9937}, {'elapsed': 0.0776369571685791, u'done': True, u'raw_reward': 1, u'env_reward': 0.992}, {u'reason': None, 'elapsed': 0.06498408317565918, u'done': False, u'raw_reward': 0, u'env_reward': 0}]}
.BASE URL: http://localhost:8765/
========================================
.BASE URL: http://localhost:8765/
========================================
.BASE URL: http://localhost:8765/
========================================
- [1] body @ (0.0, 0.0) classes=[NO_CLASS] children=1
|- [2] div @ (0.0, 0.0) classes=[NO_CLASS] children=1
|- [3] div @ (0.0, 50.0) classes=[NO_CLASS] children=9
|- [4] span @ (2.0, 52.0) text=u'diam a elementum,:' classes=[NO_CLASS]
|- [5] input_text @ (2.0, 63.0) value= classes=[NO_CLASS]
|- [6] button @ (2.0, 82.0) text=u'cancel' classes=[NO_CLASS]
|- [7] span @ (2.0, 100.0) text=u'sed feugiat quisque:' classes=[NO_CLASS]
|- [8] input_text @ (2.0, 111.0) value= classes=[NO_CLASS]
|- [9] input_text @ (2.0, 130.0) value= classes=[NO_CLASS]
|- [10] input_text @ (2.0, 149.0) value= classes=[NO_CLASS]
|- [11] span @ (2.0, 168.0) text=u'pharetra pellentesqu...' classes=[NO_CLASS]
|- [12] input_text @ (2.0, 179.0) value= classes=[NO_CLASS]
Clicking with click([5] input_text @ (2.0, 63.0) value= classes=[NO_CLASS])
Clicking with click([8] input_text @ (78.14, 92.0) value= classes=[NO_CLASS])
Clicking with click([5] input_text @ (2.0, 63.0) value= classes=[NO_CLASS])
Clicking with click([6] button @ (2.0, 82.0) text=u'cancel' classes=[NO_CLASS])
Clicking with click([9] button @ (2.0, 111.0) text=u'ok' classes=[NO_CLASS])
Clicking with click([6] button @ (2.0, 82.0) text=u'cancel' classes=[NO_CLASS])
.BASE URL: http://localhost:8765/
========================================
Clicking with click([4] button @ (20.0, 75.0) text=u'ONE' classes=[NO_CLASS])
Clicking with click([5] button @ (26.0, 87.0) text=u'TWO' classes=[NO_CLASS])
Clicking with click([4] button @ (64.0, 101.0) text=u'ONE' classes=[NO_CLASS])
Clicking with click([4] button @ (20.0, 113.0) text=u'ONE' classes=[NO_CLASS])
Clicking with click([5] button @ (16.0, 83.0) text=u'TWO' classes=[NO_CLASS])
Clicking with click([4] button @ (56.0, 164.0) text=u'ONE' classes=[NO_CLASS])
Clicking with click([4] button @ (82.0, 83.0) text=u'ONE' classes=[NO_CLASS])
Clicking with click([5] button @ (59.0, 109.0) text=u'TWO' classes=[NO_CLASS])
Clicking with click([4] button @ (115.0, 107.0) text=u'ONE' classes=[NO_CLASS])
Clicking with click([4] button @ (30.0, 163.0) text=u'ONE' classes=[NO_CLASS])
Clicking with click([5] button @ (113.0, 151.0) text=u'TWO' classes=[NO_CLASS])
Clicking with click([4] button @ (7.0, 166.0) text=u'ONE' classes=[NO_CLASS])
.BASE URL: http://localhost:8765/
========================================
Forward to Cathrine the email from Evy.
by: u'Evy'
to: u'Cathrine'
Send Bettine the information Lidia sent to you.
by: u'Lidia'
to: u'Bettine'
Please find the message by Patrizia, then send it to Hestia.
by: u'Patrizia'
to: u'Hestia'
Get Sharyl email and then forward it to Roz please.
dummy: 'dummy'
F
================================ FAILURES ================================
____________________ TestMiniWoBEnvironment.test_run _____________________
self = <wge.tests.miniwob.test_environment.TestMiniWoBEnvironment object at 0x104a17490>
env = <wge.miniwob.environment.MiniWoBEnvironment object at 0x104a173d0>
def test_run(self, env):
"""Test reset and step."""
print '=' * 40
states = env.reset()
print [x.utterance for x in states]
assert all(x.utterance == 'Click the button.' for x in states)
print [x.fields for x in states]
> assert all(not x.fields for x in states)
E assert False
E + where False = all(<generator object <genexpr> at 0x1048aebe0>)
wge/tests/miniwob/test_environment.py:66: AssertionError
_____________________ TestMiniWoBFields.test_fields ______________________
self = <wge.tests.miniwob.test_environment.TestMiniWoBFields object at 0x104dbf090>
env = <wge.miniwob.environment.MiniWoBEnvironment object at 0x104d5ae50>
def test_fields(self, env):
print '=' * 40
# Training time
states = env.reset()
for state in states:
print state.utterance
print state.fields
assert 'by' in state.fields.keys
assert 'to' in state.fields.keys
assert state.fields['by'] in state.utterance
assert state.fields['to'] in state.utterance
# Test time
states = env.reset(mode='test')
for state in states:
print state.utterance
print state.fields
> assert not state.fields.keys
E AssertionError: assert not ['dummy']
E + where ['dummy'] = dummy: 'dummy'.keys
E + where dummy: 'dummy' = MiniWoBState(utterance: u'Get Sharyl email and then forward it to Roz please.').fields
wge/tests/miniwob/test_environment.py:321: AssertionError
================== 2 failed, 7 passed in 42.99 seconds ===================
any idea what goes wrong?
hi:
when running python main.py configs/default-base.txt --task click-tab-2
the following error occurred, without changing any single line of code / data:
TrainingRun configuration:
gamma = 1.0
discount_negative_reward = false
train {
max_control_steps = 50000
learning_rate = 0.001
behavioral_cloning = false
replay = 5
replay_steps = 30
reinforce_program = true
reinforce_neural = false
}
explore {
program = 1
neural = 10
best_first_search = 10
max_steps_per_episode = 10
best_first_beam_size = 10
}
log {
episodes_to_evaluate_small = 20
episodes_to_evaluate_big = 500
evaluate = 100
evaluate_big = 500
explore = 10
replay = 10
trace_evaluate = 1000
trace_explore = 1000
trace_replay = 1000
save = 1000000000
visualize_attention = 100000
record_screenshots = false
}
replay_buffer {
size = 1000
min_size = 100
}
policy {
query_type = "structured"
episodes_to_replay = 5
update_rule = "use-whole-episode"
baseline = 0.1
use_critic = true
attn_dim = 64
context_embed_dim = 96
dom_attention_for_state = true
scoring_batch_size = 64
utterance_embedder {
type = "glove"
vocab_size = 100000
lstm_dim = 64
}
dom_embedder {
tag_embed_dim = 16
value_embed_dim = 16
tampered_embed_dim = 8
classes_embed_dim = 16
}
}
program_policy {
type = "program"
parameterization = "softmax"
weight_init = 1.0
learning_rate = 0.8
alpha = 0.1
init_v = 0.0
max_programs = 50
}
env {
domain = "miniwob"
num_instances = 6
subdomain = "click-tab-2"
return_image = false
headless = false
wait_ms = 0
block_on_reset = true
refresh_freq = 50
reward_processor {
type = "time_independent"
}
}
demonstrations {
min_raw_reward = 1.0
base_dir = "2017-10-16_second-turk"
parser = "chunk-shortcut"
max_to_use = 1000000000000
}
LOADING DEMOS FROM: /Users/wge/third-party/miniwob-demos/2017-10-16_second-turk/click-tab-2
Loading demonstrations: 100%|█████████████| 32/32 [00:00<00:00, 74.19it/s]
Loading GloVe embeddings: 100%|█▉| 99608/100000 [00:10<00:00, 9878.71it/s]No GPUs detected. Sticking with CPUs.
No checkpoint to reload. Initializing fresh.
No uncommitted changes.
New TrainingRun created at: /Users/data/experiments/2_unnamed
ERROR:root:############################################################/s]
ERROR:root:=== SOMETHING WRONG HAPPENED !!! === (Retry attempt 1 / 5)
Traceback (most recent call last):
File "/Users/wge/wge/episode_generator.py", line 62, in __call__
seeds, record_screenshots)
File "/Users/wge/wge/episode_generator.py", line 93, in _get_episodes
actions = policy.act(states, test_policy)
File "/Users/wge/wge/wob_policy.py", line 425, in act
action_scores_batch = self.score_actions(states)
File "/Users/wge/wge/wob_policy.py", line 192, in score_actions
states, force_dom_attn, force_type_values)
File "/Users/wge/wge/wob_policy.py", line 221, in _score_actions
dom_embeds, dom_elems = self._dom_embeds(states)
File "/Users/wge/wge/wob_policy.py", line 502, in _dom_embeds
dom_elems, aligned_dom_embeds)
File "/Users/env/lib/python2.7/site-packages/torch/nn/modules/module.py", line 325, in __call__
result = self.forward(*input, **kwargs)
File "/Users/wge/wge/miniwob/embeddings.py", line 406, in forward
pixel_neighbor_embeds, allow_empty=True)
File "/Users/wge/gtd/ml/torch/seq_batch.py", line 174, in reduce_mean
weights = mask / sums.expand(*mask.size())
RuntimeError: The expanded size of the tensor (9) must match the existing size (96) at non-singleton dimension 1. at /Users/soumith/code/builder/wheel/pytorch-src/torch/lib/TH/generic/THTensor.c:309
ERROR:root:Will restart the environment and try again ...
ERROR:root:############################################################
ERROR:root:############################################################
ERROR:root:=== SOMETHING WRONG HAPPENED !!! === (Retry attempt 2 / 5)
Traceback (most recent call last):
File "/Users/wge/wge/episode_generator.py", line 62, in __call__
seeds, record_screenshots)
File "/Users/wge/wge/episode_generator.py", line 93, in _get_episodes
actions = policy.act(states, test_policy)
File "/Users/wge/wge/wob_policy.py", line 425, in act
action_scores_batch = self.score_actions(states)
File "/Users/wge/wge/wob_policy.py", line 192, in score_actions
states, force_dom_attn, force_type_values)
File "/Users/wge/wge/wob_policy.py", line 221, in _score_actions
dom_embeds, dom_elems = self._dom_embeds(states)
File "/Users/wge/wge/wob_policy.py", line 502, in _dom_embeds
dom_elems, aligned_dom_embeds)
File "/Users/env/lib/python2.7/site-packages/torch/nn/modules/module.py", line 325, in __call__
result = self.forward(*input, **kwargs)
File "/Users/wge/wge/miniwob/embeddings.py", line 406, in forward
pixel_neighbor_embeds, allow_empty=True)
File "/Users/wge/gtd/ml/torch/seq_batch.py", line 174, in reduce_mean
weights = mask / sums.expand(*mask.size())
RuntimeError: The expanded size of the tensor (7) must match the existing size (90) at non-singleton dimension 1. at /Users/soumith/code/builder/wheel/pytorch-src/torch/lib/TH/generic/THTensor.c:309
ERROR:root:Will restart the environment and try again ...
ERROR:root:############################################################
ERROR:root:############################################################
ERROR:root:=== SOMETHING WRONG HAPPENED !!! === (Retry attempt 3 / 5)
Traceback (most recent call last):
File "/Users/wge/wge/episode_generator.py", line 62, in __call__
seeds, record_screenshots)
File "/Users/wge/wge/episode_generator.py", line 93, in _get_episodes
actions = policy.act(states, test_policy)
File "/Users/wge/wge/wob_policy.py", line 425, in act
action_scores_batch = self.score_actions(states)
File "/Users/wge/wge/wob_policy.py", line 192, in score_actions
states, force_dom_attn, force_type_values)
File "/Users/wge/wge/wob_policy.py", line 221, in _score_actions
dom_embeds, dom_elems = self._dom_embeds(states)
File "/Users/wge/wge/wob_policy.py", line 502, in _dom_embeds
dom_elems, aligned_dom_embeds)
File "/Users/env/lib/python2.7/site-packages/torch/nn/modules/module.py", line 325, in __call__
result = self.forward(*input, **kwargs)
File "/Users/wge/wge/miniwob/embeddings.py", line 406, in forward
pixel_neighbor_embeds, allow_empty=True)
File "/Users/wge/gtd/ml/torch/seq_batch.py", line 174, in reduce_mean
weights = mask / sums.expand(*mask.size())
RuntimeError: The expanded size of the tensor (6) must match the existing size (90) at non-singleton dimension 1. at /Users/soumith/code/builder/wheel/pytorch-src/torch/lib/TH/generic/THTensor.c:309
ERROR:root:Will restart the environment and try again ...
ERROR:root:############################################################
ERROR:root:############################################################
ERROR:root:=== SOMETHING WRONG HAPPENED !!! === (Retry attempt 4 / 5)
Traceback (most recent call last):
File "/Users/wge/wge/episode_generator.py", line 62, in __call__
seeds, record_screenshots)
File "/Users/wge/wge/episode_generator.py", line 93, in _get_episodes
actions = policy.act(states, test_policy)
File "/Users/wge/wge/wob_policy.py", line 425, in act
action_scores_batch = self.score_actions(states)
File "/Users/wge/wge/wob_policy.py", line 192, in score_actions
states, force_dom_attn, force_type_values)
File "/Users/wge/wge/wob_policy.py", line 221, in _score_actions
dom_embeds, dom_elems = self._dom_embeds(states)
File "/Users/wge/wge/wob_policy.py", line 502, in _dom_embeds
dom_elems, aligned_dom_embeds)
File "/Users/env/lib/python2.7/site-packages/torch/nn/modules/module.py", line 325, in __call__
result = self.forward(*input, **kwargs)
File "/Users/wge/wge/miniwob/embeddings.py", line 406, in forward
pixel_neighbor_embeds, allow_empty=True)
File "/Users/wge/gtd/ml/torch/seq_batch.py", line 174, in reduce_mean
weights = mask / sums.expand(*mask.size())
RuntimeError: The expanded size of the tensor (7) must match the existing size (96) at non-singleton dimension 1. at /Users/soumith/code/builder/wheel/pytorch-src/torch/lib/TH/generic/THTensor.c:309
ERROR:root:Will restart the environment and try again ...
ERROR:root:############################################################
ERROR:root:############################################################
ERROR:root:=== SOMETHING WRONG HAPPENED !!! === (Retry attempt 5 / 5)
Traceback (most recent call last):
File "/Users/wge/wge/episode_generator.py", line 62, in __call__
seeds, record_screenshots)
File "/Users/wge/wge/episode_generator.py", line 93, in _get_episodes
actions = policy.act(states, test_policy)
File "/Users/wge/wge/wob_policy.py", line 425, in act
action_scores_batch = self.score_actions(states)
File "/Users/wge/wge/wob_policy.py", line 192, in score_actions
states, force_dom_attn, force_type_values)
File "/Users/wge/wge/wob_policy.py", line 221, in _score_actions
dom_embeds, dom_elems = self._dom_embeds(states)
File "/Users/wge/wge/wob_policy.py", line 502, in _dom_embeds
dom_elems, aligned_dom_embeds)
File "/Users/env/lib/python2.7/site-packages/torch/nn/modules/module.py", line 325, in __call__
result = self.forward(*input, **kwargs)
File "/Users/wge/wge/miniwob/embeddings.py", line 406, in forward
pixel_neighbor_embeds, allow_empty=True)
File "/Users/wge/gtd/ml/torch/seq_batch.py", line 174, in reduce_mean
weights = mask / sums.expand(*mask.size())
RuntimeError: The expanded size of the tensor (7) must match the existing size (108) at non-singleton dimension 1. at /Users/soumith/code/builder/wheel/pytorch-src/torch/lib/TH/generic/THTensor.c:309
ERROR:root:Will restart the environment and try again ...
ERROR:root:############################################################
ERROR:root:############################################################
ERROR:root:=== SOMETHING WRONG HAPPENED !!! === (Retry attempt 6 / 5)
Traceback (most recent call last):
File "/Users/wge/wge/episode_generator.py", line 62, in __call__
seeds, record_screenshots)
File "/Users/wge/wge/episode_generator.py", line 93, in _get_episodes
actions = policy.act(states, test_policy)
File "/Users/wge/wge/wob_policy.py", line 425, in act
action_scores_batch = self.score_actions(states)
File "/Users/wge/wge/wob_policy.py", line 192, in score_actions
states, force_dom_attn, force_type_values)
File "/Users/wge/wge/wob_policy.py", line 221, in _score_actions
dom_embeds, dom_elems = self._dom_embeds(states)
File "/Users/wge/wge/wob_policy.py", line 502, in _dom_embeds
dom_elems, aligned_dom_embeds)
File "/Users/env/lib/python2.7/site-packages/torch/nn/modules/module.py", line 325, in __call__
result = self.forward(*input, **kwargs)
File "/Users/wge/wge/miniwob/embeddings.py", line 406, in forward
pixel_neighbor_embeds, allow_empty=True)
File "/Users/wge/gtd/ml/torch/seq_batch.py", line 174, in reduce_mean
weights = mask / sums.expand(*mask.size())
RuntimeError: The expanded size of the tensor (7) must match the existing size (102) at non-singleton dimension 1. at /Users/soumith/code/builder/wheel/pytorch-src/torch/lib/TH/generic/THTensor.c:309
ERROR:root:Will restart the environment and try again ...
ERROR:root:############################################################
Traceback (most recent call last):
File "main.py", line 103, in <module>
run.train()
File "/Users/wge/wge/training_run.py", line 209, in train
control_step)
File "/Users/wge/wge/training_run.py", line 306, in _explore
test_policy=False)
File "/Users/wge/wge/episode_generator.py", line 73, in __call__
raise RuntimeError('Envionment died too many times!')
RuntimeError: Envionment died too many times!
the root cause seems to be
File "/Users/wge/gtd/ml/torch/seq_batch.py", line 174, in reduce_mean weights = mask / sums.expand(*mask.size()) RuntimeError: The expanded size of the tensor (7) must match the existing size (108) at non-singleton dimension 1. at /Users/soumith/code/builder/wheel/pytorch-src/torch/lib/TH/generic/THTensor.c:309
but I'm not sure what wrong from here.
any idea what's wrong?
When checking a run, KeyError of KeyError: 'dirty_repo' encountered.
Commands:
runs = MiniWoBTrainingRuns()
run = runs[1]
PS C:\Users\Dhaval\Downloads\uds-master> python3 uds.py push ~\Desktop\ffmpeg.exe
Traceback (most recent call last):
File "uds.py", line 534, in
main()
File "uds.py", line 452, in main
uds = UDS()
File "uds.py", line 46, in init
self.api = GoogleAPI()
File "C:\Users\Dhaval\Downloads\uds-master\api.py", line 19, in init
self.reauth()
File "C:\Users\Dhaval\Downloads\uds-master\api.py", line 25, in reauth
credentials = store.get()
File "C:\Users\Dhaval\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.7_qbz5n2kfra8p0\LocalCache\local-packages\Python37\site-packages\oauth2client\client.py", line 407, in get
return self.locked_get()
File "C:\Users\Dhaval\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.7_qbz5n2kfra8p0\LocalCache\local-packages\Python37\site-packages\oauth2client\file.py", line 54, in locked_get
credentials = client.Credentials.new_from_json(content)
File "C:\Users\Dhaval\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.7_qbz5n2kfra8p0\LocalCache\local-packages\Python37\site-packages\oauth2client\client.py", line 302, in new_from_json
module_name = data['_module']
KeyError: '_module'
help me please reply me please
Loading demonstrations: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:00<00:00, 78.51it/s]
Loading GloVe embeddings: 99%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████ | 99323/100000 [00:05<00:00, 16902.70it/s]
No GPUs detected. Sticking with CPUs.
No checkpoint to reload. Initializing fresh.
Inducing programs: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:03<00:00, 9.69it/s]
No uncommitted changes.
New TrainingRun created at: /folder/data/experiments/1_unnamed
Outer training loop: 0%| | 0/50000 [00:00<?, ?it/s]ERROR:root:############################################################
ERROR:root:=== SOMETHING WRONG HAPPENED !!! === (Retry attempt 1 / 5)
Traceback (most recent call last):
File "/folder/wge/episode_generator.py", line 62, in call
seeds, record_screenshots)
File "/folder/wge/episode_generator.py", line 93, in _get_episodes
actions = policy.act(states, test_policy)
File "/folder/wge/wob_policy.py", line 425, in act
action_scores_batch = self.score_actions(states)
File "/folder/wge/wob_policy.py", line 192, in score_actions
states, force_dom_attn, force_type_values)
File "/folder/wge/wob_policy.py", line 221, in _score_actions
dom_embeds, dom_elems = self._dom_embeds(states)
File "/folder/wge/wob_policy.py", line 502, in _dom_embeds
dom_elems, aligned_dom_embeds)
File "/Users/user/homebrew/anaconda3/envs/miniwob/lib/python2.7/site-packages/torch/nn/modules/module.py", line 357, in call
result = self.forward(*input, **kwargs)
File "/folder/wge/miniwob/embeddings.py", line 406, in forward
pixel_neighbor_embeds, allow_empty=True)
File "/folder/gtd/ml/torch/seq_batch.py", line 174, in reduce_mean
weights = mask / sums.expand(*mask.size())
RuntimeError: The expanded size of the tensor (9) must match the existing size (96) at non-singleton dimension 1. at /Users/soumith/minicondabuild3/conda-bld/pytorch_1518371252923/work/torch/lib/TH/generic/THTensor.c:309
ERROR:root:Will restart the environment and try again ...
After training a model via the command:
python main.py configs/default-base.txt --task click-tab-2
Where does the trained model and how do I deploy the model to do the task that I want it to do?
PS C:\Users\Dhaval\Downloads\uds-master> python3 uds.py push ~\Desktop\ffmpeg.exe
Traceback (most recent call last):
File "uds.py", line 534, in
main()
File "uds.py", line 452, in main
uds = UDS()
File "uds.py", line 46, in init
self.api = GoogleAPI()
File "C:\Users\Dhaval\Downloads\uds-master\api.py", line 19, in init
self.reauth()
File "C:\Users\Dhaval\Downloads\uds-master\api.py", line 25, in reauth
credentials = store.get()
File "C:\Users\Dhaval\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.7_qbz5n2kfra8p0\LocalCache\local-packages\Python37\site-packages\oauth2client\client.py", line 407, in get
return self.locked_get()
File "C:\Users\Dhaval\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.7_qbz5n2kfra8p0\LocalCache\local-packages\Python37\site-packages\oauth2client\file.py", line 54, in locked_get
credentials = client.Credentials.new_from_json(content)
File "C:\Users\Dhaval\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.7_qbz5n2kfra8p0\LocalCache\local-packages\Python37\site-packages\oauth2client\client.py", line 302, in new_from_json
module_name = data['_module']
KeyError: '_module'
reply me fast, help me out
First of all, many thanks for all the work you put into making sure your work is reproducible! 🥇
It seems that ever since Pytorch==0.2.0 it is assumed that keepdim=False
for reduction functions such as tensor.sum(). This assumption breaks a bunch of the code here... so it may be wise to specify a version in the Readme.
why below folder are duplicated?
miniwob-sandbox/
third-party/miniwob-sandbox/
Hello!
First of all, thank you for sharing your codes! I just have a few question regarding adding and creating a new web tasks:
third-party/html
using the custom html files (just like how flight tasks are defined)?common/core.js
) be reused to define the custom tasks?Thank you.
hi:
I looked into the Alaska flight booking template and didn't see any natural language instructions. How is reward defined in Alaska case? Does it reward whenever the 'find flights' button is clicked with all fields filled out? Any other constraint? I can see no date is included in the constraint (or is much more loosely given, ex: always in March 2017), given the success rate of [choose date] is .52 and Alaska flight booking has .86, not sure if any constraint included.
This may not be an actual issue...
line 7 in launch_jobs.py (in the root of wge directory) seems to reference methods that are not defined in script_tools.py.
from script_tools import bash_string, upload_code, create_worksheet, task_lists, \ upload_demos
however, upload_code, create_worksheet, and upload_demos are included. Either they were left out b/c its very specific to the university blah blah blah. but it would be useful to have more context.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.