paperspace / dinoruntutorial Goto Github PK

Unable to use chromedriver in paperspace, i have uploaded the chromedriver in paperspace and i use a macos. Please help
from selenium import webdriver
driver = webdriver.Chrome('chromedriver')

Thanks for this article. I didn’t understand how did you know Runner is for checking the state like current score, gamer running or not, crashed or not, resume, start, …

Is that present in every canvas game? Mean did it work only for chrome://dino ? How can I find out Runner kind of variable to check the game state in other websites?

I start the code in a virtual environment of python and i get the following error:
How can I fix the permission conflict?

`(ENV) te@te-ThinkPad-T460s:~/Programming/Python/DinoRunTutorial$ python3 Main.py
Using TensorFlow backend.
Traceback (most recent call last):
File "/home/te/Programming/Python/DinoRunTutorial/ENV/lib/python3.6/site-packages/selenium/webdriver/common/service.py", line 76, in start
stdin=PIPE)
File "/usr/lib/python3.6/subprocess.py", line 729, in init
restore_signals, start_new_session)
File "/usr/lib/python3.6/subprocess.py", line 1364, in _execute_child
raise child_exception_type(errno_num, err_msg, err_filename)
PermissionError: [Errno 13] Permission denied: '/usr/bin'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "Main.py", line 372, in
playGame(observe=False);
File "Main.py", line 362, in playGame
game = Game()
File "Main.py", line 66, in init
self._driver = webdriver.Chrome(executable_path = chrome_driver_path,chrome_options=chrome_options)
File "/home/te/Programming/Python/DinoRunTutorial/ENV/lib/python3.6/site-packages/selenium/webdriver/chrome/webdriver.py", line 73, in init
self.service.start()
File "/home/te/Programming/Python/DinoRunTutorial/ENV/lib/python3.6/site-packages/selenium/webdriver/common/service.py", line 88, in start
os.path.basename(self.path), self.start_error_message)
selenium.common.exceptions.WebDriverException: Message: 'bin' executable may have wrong permissions. Please see https://sites.google.com/a/chromium.org/chromedriver/home`

The 3 layers of conv with proposed values of stride , pooling .ect. leads the feature map to be small too fast ( supposed 80*80 input). is there any other settings I missed ?

Thanks a lot

I am experiencing the above the error when I run the command, I copied the objects folder to the directory already. I am running it on windows 10 and the chrome browser did pop up and the game started but in the command prompt shows the error below.

`C:\Users\Tom\Desktop\Chrome-Dino-Reinforcement-Learning-master\DinoRunTutorial-master>jupyter nbconvert --execute "Reinforcement Learning Dino Run.ipynb"
[NbConvertApp] Converting notebook Reinforcement Learning Dino Run.ipynb to html
[NbConvertApp] Executing notebook with kernel: python3

DevTools listening on ws://127.0.0.1:64177/devtools/browser/b0ad5ad8-8ca7-44f6-a4fa-7a1de1a2553e
[NbConvertApp] ERROR | Error while converting 'Reinforcement Learning Dino Run.ipynb'
Traceback (most recent call last):
File "c:\users\tom\appdata\local\programs\python\python36\lib\site-packages\nbconvert\nbconvertapp.py", line 407, in export_single_notebook
output, resources = self.exporter.from_filename(notebook_filename, resources=resources)
File "c:\users\tom\appdata\local\programs\python\python36\lib\site-packages\nbconvert\exporters\exporter.py", line 178, in from_filename
return self.from_file(f, resources=resources, **kw)
File "c:\users\tom\appdata\local\programs\python\python36\lib\site-packages\nbconvert\exporters\exporter.py", line 196, in from_file
return self.from_notebook_node(nbformat.read(file_stream, as_version=4), resources=resources, **kw)
File "c:\users\tom\appdata\local\programs\python\python36\lib\site-packages\nbconvert\exporters\html.py", line 95, in from_notebook_node
output, resources = super(HTMLExporter, self).from_notebook_node(nb, resources, **kw)
File "c:\users\tom\appdata\local\programs\python\python36\lib\site-packages\nbconvert\exporters\templateexporter.py", line 300, in from_notebook_node
nb_copy, resources = super(TemplateExporter, self).from_notebook_node(nb, resources, **kw)
File "c:\users\tom\appdata\local\programs\python\python36\lib\site-packages\nbconvert\exporters\exporter.py", line 138, in from_notebook_node
nb_copy, resources = self._preprocess(nb_copy, resources)
File "c:\users\tom\appdata\local\programs\python\python36\lib\site-packages\nbconvert\exporters\exporter.py", line 315, in _preprocess
nbc, resc = preprocessor(nbc, resc)
File "c:\users\tom\appdata\local\programs\python\python36\lib\site-packages\nbconvert\preprocessors\base.py", line 47, in call
return self.preprocess(nb, resources)
File "c:\users\tom\appdata\local\programs\python\python36\lib\site-packages\nbconvert\preprocessors\execute.py", line 361, in preprocess
nb, resources = super(ExecutePreprocessor, self).preprocess(nb, resources)
File "c:\users\tom\appdata\local\programs\python\python36\lib\site-packages\nbconvert\preprocessors\base.py", line 69, in preprocess
nb.cells[index], resources = self.preprocess_cell(cell, resources, index)
File "c:\users\tom\appdata\local\programs\python\python36\lib\site-packages\nbconvert\preprocessors\execute.py", line 385, in preprocess_cell
raise CellExecutionError.from_cell_and_msg(cell, out)
nbconvert.preprocessors.execute.CellExecutionError: An error occurred while executing the following cell:

playGame(observe=False);

�[1;31m---------------------------------------------------------------------------�[0m
�[1;31mFileNotFoundError�[0m Traceback (most recent call last)
�[1;32m�[0m in �[0;36m�[1;34m�[0m
�[1;32m----> 1�[1;33m �[0mplayGame�[0m�[1;33m(�[0m�[0mobserve�[0m�[1;33m=�[0m�[1;32mFalse�[0m�[1;33m)�[0m�[1;33m;�[0m�[1;33m�[0m�[0m
�[0m
�[1;32m�[0m in �[0;36mplayGame�[1;34m(observe)�[0m
�[0;32m 6�[0m �[0mmodel�[0m �[1;33m=�[0m �[0mbuildmodel�[0m�[1;33m(�[0m�[1;33m)�[0m�[1;33m�[0m�[0m
�[0;32m 7�[0m �[1;32mtry�[0m�[1;33m:�[0m�[1;33m�[0m�[0m
�[1;32m----> 8�[1;33m �[0mtrainNetwork�[0m�[1;33m(�[0m�[0mmodel�[0m�[1;33m,�[0m�[0mgame_state�[0m�[1;33m,�[0m�[0mobserve�[0m�[1;33m=�[0m�[0mobserve�[0m�[1;33m)�[0m�[1;33m�[0m�[0m
�[0m�[0;32m 9�[0m �[1;32mexcept�[0m �[0mStopIteration�[0m�[1;33m:�[0m�[1;33m�[0m�[0m
�[0;32m 10�[0m �[0mgame�[0m�[1;33m.�[0m�[0mend�[0m�[1;33m(�[0m�[1;33m)�[0m�[1;33m�[0m�[0m

�[1;32m�[0m in �[0;36mtrainNetwork�[1;34m(model, game_state, observe)�[0m
�[0;32m 9�[0m �[0mlast_time�[0m �[1;33m=�[0m �[0mtime�[0m�[1;33m.�[0m�[0mtime�[0m�[1;33m(�[0m�[1;33m)�[0m�[1;33m�[0m�[0m
�[0;32m 10�[0m �[1;31m# store the previous observations in replay memory�[0m�[1;33m�[0m�[1;33m�[0m�[0m
�[1;32m---> 11�[1;33m �[0mD�[0m �[1;33m=�[0m �[0mload_obj�[0m�[1;33m(�[0m�[1;34m"D"�[0m�[1;33m)�[0m �[1;31m#load from file system�[0m�[1;33m�[0m�[0m
�[0m�[0;32m 12�[0m �[1;31m# get the first state by doing nothing�[0m�[1;33m�[0m�[1;33m�[0m�[0m
�[0;32m 13�[0m �[0mdo_nothing�[0m �[1;33m=�[0m �[0mnp�[0m�[1;33m.�[0m�[0mzeros�[0m�[1;33m(�[0m�[0mACTIONS�[0m�[1;33m)�[0m�[1;33m�[0m�[0m

�[1;32m�[0m in �[0;36mload_obj�[1;34m(name)�[0m
�[0;32m 3�[0m �[0mpickle�[0m�[1;33m.�[0m�[0mdump�[0m�[1;33m(�[0m�[0mobj�[0m�[1;33m,�[0m �[0mf�[0m�[1;33m,�[0m �[0mpickle�[0m�[1;33m.�[0m�[0mHIGHEST_PROTOCOL�[0m�[1;33m)�[0m�[1;33m�[0m�[0m
�[0;32m 4�[0m �[1;32mdef�[0m �[0mload_obj�[0m�[1;33m(�[0m�[0mname�[0m �[1;33m)�[0m�[1;33m:�[0m�[1;33m�[0m�[0m
�[1;32m----> 5�[1;33m �[1;32mwith�[0m �[0mopen�[0m�[1;33m(�[0m�[1;34m'objects/'�[0m �[1;33m+�[0m �[0mname�[0m �[1;33m+�[0m �[1;34m'.pkl'�[0m�[1;33m,�[0m �[1;34m'rb'�[0m�[1;33m)�[0m �[1;32mas�[0m �[0mf�[0m�[1;33m:�[0m�[1;33m�[0m�[0m
�[0m�[0;32m 6�[0m �[1;32mreturn�[0m �[0mpickle�[0m�[1;33m.�[0m�[0mload�[0m�[1;33m(�[0m�[0mf�[0m�[1;33m)�[0m�[1;33m�[0m�[0m
�[0;32m 7�[0m �[1;33m�[0m�[0m

�[1;31mFileNotFoundError�[0m: [Errno 2] No such file or directory: 'objects/D.pkl'
FileNotFoundError: [Errno 2] No such file or directory: 'objects/D.pkl'`

I rise the batch_size to 64, will want change reward method to up the score.
but before that, want to consult any advice upgrade score, thank you!

Hi, While trying to open 'chrome://dino' url in selenium, it is throwing the following error:

WebDriverException Traceback (most recent call last)
in
----> 1 driver.get("chrome://dino/")

F:\Anaconda\envs\opencv\lib\site-packages\selenium\webdriver\remote\webdriver.py in get(self, url)
331 Loads a web page in the current browser session.
332 """
--> 333 self.execute(Command.GET, {'url': url})
334
335 @Property

F:\Anaconda\envs\opencv\lib\site-packages\selenium\webdriver\remote\webdriver.py in execute(self, driver_command, params)
319 response = self.command_executor.execute(driver_command, params)
320 if response:
--> 321 self.error_handler.check_response(response)
322 response['value'] = self._unwrap_value(
323 response.get('value', None))

F:\Anaconda\envs\opencv\lib\site-packages\selenium\webdriver\remote\errorhandler.py in check_response(self, response)
240 alert_text = value['alert'].get('text')
241 raise exception_class(message, screen, stacktrace, alert_text)
--> 242 raise exception_class(message, screen, stacktrace)
243
244 def _value_or_default(self, obj, key, default):

WebDriverException: Message: unknown error: net::ERR_INTERNET_DISCONNECTED

i tried googling for a solution but, couldn't find any that fixed the issue.
Kindly help me resolve this.

I set up the ML-in-a-Box, machine on Paperspace.
Unfortunately when I run init_cache() get the following error:

FileNotFoundError: [Errno 2] No such file or directory: 'objects/epsilon.pkl

Hi, I managed to get the code running and have used CPU only to train it. Below are the runtime result. How long do I have to run it for to observe any improvement in training?
FYI, I ran this code on my surface pro 3 i5 for about 20 hours or so.

Hi! I was looking through the code, and I realized that there's no way for the dino to duck during the game. There's a duck method for the DinoAgent class, but there's nothing in the Game class to support it.

I added in the functionality, and I was wondering if I could make a pull request.