{
  "id": 301583,
  "title": "How you install TF 1.15 and dependencies to run RL Stable Baselines offline",
  "url": "/competitions/g-research-crypto-forecasting/discussion/301583",
  "author_name": "Kirderf",
  "post_date": "2022-01-18T13:47:06.321000",
  "votes": 4,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Just started the competition and checked some of the public codes, a good starting kernel is always a quick start if one is late to the party, parallel to the own tries.</p>\n<p>Ran into this RL notebook <br>\n<a href=\"https://www.kaggle.com/yamqwe/g-research-reinforcement-learning-starter\" target=\"_blank\">https://www.kaggle.com/yamqwe/g-research-reinforcement-learning-starter</a><br>\nCredit to <a href=\"https://www.kaggle.com/yamqwe\" target=\"_blank\">@yamqwe</a> who creates awesome notebooks and with a superior speed.</p>\n<p>I saw that the RL notebook didn’t had the setup to run offline, so if one wants to further develop/use that kernel here is how you run it offline.<br>\nIt's an updated version (working datasets etc) of the NB <a href=\"https://www.kaggle.com/computerguy/tensorflow-gpu-1-15-offline-installation-usage\" target=\"_blank\">https://www.kaggle.com/computerguy/tensorflow-gpu-1-15-offline-installation-usage</a></p>\n<pre><code>!cp -r ../input/gast022/gast-0.2.2 ./\n%cd gast-0.2.2\n!python3 setup.py install &gt;&gt; /dev/null\n%cd /kaggle/working\n\n!pip3 install -qq ../input/tf115offlineinstall/astor-0.8.1-py2.py3-none-any.whl\n!pip3 install -qq ../input/tf115offlineinstall/Keras_Applications-1.0.8-py3-none-any.whl\n!pip3 install -qq ../input/tf115offlineinstall/tensorboard-1.15.0-py3-none-any.whl\n!pip3 install -qq ../input/tf115offlineinstall/tensorflow_estimator-1.15.1-py2.py3-none-any.whl\n!pip3 install -qq --no-deps ../input/tf115offlineinstall/tensorflow-1.15.5-cp37-cp37m-manylinux2010_x86_64.whl\n\nimport sys\nsys.path.append('../input/stablebaselineoffline/stable-baselines-master')\n</code></pre>\n<p>Have collected and saved the needed packages below</p>\n<p><a href=\"https://www.kaggle.com/kirderf/stablebaselineoffline\" target=\"_blank\">https://www.kaggle.com/kirderf/stablebaselineoffline</a><br>\n<a href=\"https://www.kaggle.com/kirderf/gast022\" target=\"_blank\">https://www.kaggle.com/kirderf/gast022</a><br>\n<a href=\"https://www.kaggle.com/kirderf/tf115offlineinstall\" target=\"_blank\">https://www.kaggle.com/kirderf/tf115offlineinstall</a></p>",
  "messages": [
    {
      "id": 1654420,
      "postDate": "2022-01-18T13:47:06.320Z",
      "content": "<p>Just started the competition and checked some of the public codes, a good starting kernel is always a quick start if one is late to the party, parallel to the own tries.</p>\n<p>Ran into this RL notebook <br>\n<a href=\"https://www.kaggle.com/yamqwe/g-research-reinforcement-learning-starter\" target=\"_blank\">https://www.kaggle.com/yamqwe/g-research-reinforcement-learning-starter</a><br>\nCredit to <a href=\"https://www.kaggle.com/yamqwe\" target=\"_blank\">@yamqwe</a> who creates awesome notebooks and with a superior speed.</p>\n<p>I saw that the RL notebook didn’t had the setup to run offline, so if one wants to further develop/use that kernel here is how you run it offline.<br>\nIt's an updated version (working datasets etc) of the NB <a href=\"https://www.kaggle.com/computerguy/tensorflow-gpu-1-15-offline-installation-usage\" target=\"_blank\">https://www.kaggle.com/computerguy/tensorflow-gpu-1-15-offline-installation-usage</a></p>\n<pre><code>!cp -r ../input/gast022/gast-0.2.2 ./\n%cd gast-0.2.2\n!python3 setup.py install &gt;&gt; /dev/null\n%cd /kaggle/working\n\n!pip3 install -qq ../input/tf115offlineinstall/astor-0.8.1-py2.py3-none-any.whl\n!pip3 install -qq ../input/tf115offlineinstall/Keras_Applications-1.0.8-py3-none-any.whl\n!pip3 install -qq ../input/tf115offlineinstall/tensorboard-1.15.0-py3-none-any.whl\n!pip3 install -qq ../input/tf115offlineinstall/tensorflow_estimator-1.15.1-py2.py3-none-any.whl\n!pip3 install -qq --no-deps ../input/tf115offlineinstall/tensorflow-1.15.5-cp37-cp37m-manylinux2010_x86_64.whl\n\nimport sys\nsys.path.append('../input/stablebaselineoffline/stable-baselines-master')\n</code></pre>\n<p>Have collected and saved the needed packages below</p>\n<p><a href=\"https://www.kaggle.com/kirderf/stablebaselineoffline\" target=\"_blank\">https://www.kaggle.com/kirderf/stablebaselineoffline</a><br>\n<a href=\"https://www.kaggle.com/kirderf/gast022\" target=\"_blank\">https://www.kaggle.com/kirderf/gast022</a><br>\n<a href=\"https://www.kaggle.com/kirderf/tf115offlineinstall\" target=\"_blank\">https://www.kaggle.com/kirderf/tf115offlineinstall</a></p>",
      "rawMarkdown": "Just started the competition and checked some of the public codes, a good starting kernel is always a quick start if one is late to the party, parallel to the own tries.\n\nRan into this RL notebook \nhttps://www.kaggle.com/yamqwe/g-research-reinforcement-learning-starter\nCredit to @yamqwe who creates awesome notebooks and with a superior speed.\n\nI saw that the RL notebook didn’t had the setup to run offline, so if one wants to further develop/use that kernel here is how you run it offline.\nIt's an updated version (working datasets etc) of the NB https://www.kaggle.com/computerguy/tensorflow-gpu-1-15-offline-installation-usage\n\n```\n!cp -r ../input/gast022/gast-0.2.2 ./\n%cd gast-0.2.2\n!python3 setup.py install >> /dev/null\n%cd /kaggle/working\n\n!pip3 install -qq ../input/tf115offlineinstall/astor-0.8.1-py2.py3-none-any.whl\n!pip3 install -qq ../input/tf115offlineinstall/Keras_Applications-1.0.8-py3-none-any.whl\n!pip3 install -qq ../input/tf115offlineinstall/tensorboard-1.15.0-py3-none-any.whl\n!pip3 install -qq ../input/tf115offlineinstall/tensorflow_estimator-1.15.1-py2.py3-none-any.whl\n!pip3 install -qq --no-deps ../input/tf115offlineinstall/tensorflow-1.15.5-cp37-cp37m-manylinux2010_x86_64.whl\n\nimport sys\nsys.path.append('../input/stablebaselineoffline/stable-baselines-master')\n```\n\nHave collected and saved the needed packages below\n\nhttps://www.kaggle.com/kirderf/stablebaselineoffline\nhttps://www.kaggle.com/kirderf/gast022\nhttps://www.kaggle.com/kirderf/tf115offlineinstall\n\n",
      "votes": 4
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "1654420": "Just started the competition and checked some of the public codes, a good starting kernel is always a quick start if one is late to the party, parallel to the own tries.\n\nRan into this RL notebook \nhttps://www.kaggle.com/yamqwe/g-research-reinforcement-learning-starter\nCredit to @yamqwe who creates awesome notebooks and with a superior speed.\n\nI saw that the RL notebook didn’t had the setup to run offline, so if one wants to further develop/use that kernel here is how you run it offline.\nIt's an updated version (working datasets etc) of the NB https://www.kaggle.com/computerguy/tensorflow-gpu-1-15-offline-installation-usage\n\n```\n!cp -r ../input/gast022/gast-0.2.2 ./\n%cd gast-0.2.2\n!python3 setup.py install >> /dev/null\n%cd /kaggle/working\n\n!pip3 install -qq ../input/tf115offlineinstall/astor-0.8.1-py2.py3-none-any.whl\n!pip3 install -qq ../input/tf115offlineinstall/Keras_Applications-1.0.8-py3-none-any.whl\n!pip3 install -qq ../input/tf115offlineinstall/tensorboard-1.15.0-py3-none-any.whl\n!pip3 install -qq ../input/tf115offlineinstall/tensorflow_estimator-1.15.1-py2.py3-none-any.whl\n!pip3 install -qq --no-deps ../input/tf115offlineinstall/tensorflow-1.15.5-cp37-cp37m-manylinux2010_x86_64.whl\n\nimport sys\nsys.path.append('../input/stablebaselineoffline/stable-baselines-master')\n```\n\nHave collected and saved the needed packages below\n\nhttps://www.kaggle.com/kirderf/stablebaselineoffline\nhttps://www.kaggle.com/kirderf/gast022\nhttps://www.kaggle.com/kirderf/tf115offlineinstall\n\n"
  }
}