{
  "id": 157525,
  "title": "Questions about load pre-trained model in Spyder",
  "url": "/competitions/jigsaw-multilingual-toxic-comment-classification/discussion/157525",
  "author_name": "",
  "post_date": "2020-06-11T01:40:36.244918800Z",
  "votes": null,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hey you guys. I try to run some experiments on my local machine. And when I use</p>\n\n<blockquote>\n  <p>tokenizer = AutoTokenizer.from_pretrained('jplu/tf-xlm-roberta-large') </p>\n</blockquote>\n\n<p>to import a pre-trained tokenizer I got an error message.</p>\n\n<blockquote>\n  <p>ImportError: FloatProgress not found. Please update jupyter and ipywidgets. See <a href=\"https://ipywidgets.readthedocs.io/en/stable/user_install.html\">https://ipywidgets.readthedocs.io/en/stable/user_install.html</a></p>\n</blockquote>\n\n<p>So I updated jupyter and ipywidgets. \nBut the error is unsolved. I recognized that it has something to do with tqdm. And Spyder may not show progress bar properly. So I rerun this code in JupyterNotebook on my local machine. And the problem solved. No error message and the tokenizer imported properly.\nMy question is how to make it work on Spyder. I assume this AutoTokenizer class won't just work in notebook-style development environment, right?</p>",
  "messages": [
    {
      "id": "881387",
      "postDate": "06/11/2020 01:40:36",
      "content": "<p>Hey you guys. I try to run some experiments on my local machine. And when I use</p>\n\n<blockquote>\n  <p>tokenizer = AutoTokenizer.from_pretrained('jplu/tf-xlm-roberta-large') </p>\n</blockquote>\n\n<p>to import a pre-trained tokenizer I got an error message.</p>\n\n<blockquote>\n  <p>ImportError: FloatProgress not found. Please update jupyter and ipywidgets. See <a href=\"https://ipywidgets.readthedocs.io/en/stable/user_install.html\">https://ipywidgets.readthedocs.io/en/stable/user_install.html</a></p>\n</blockquote>\n\n<p>So I updated jupyter and ipywidgets. \nBut the error is unsolved. I recognized that it has something to do with tqdm. And Spyder may not show progress bar properly. So I rerun this code in JupyterNotebook on my local machine. And the problem solved. No error message and the tokenizer imported properly.\nMy question is how to make it work on Spyder. I assume this AutoTokenizer class won't just work in notebook-style development environment, right?</p>",
      "rawMarkdown": "Hey you guys. I try to run some experiments on my local machine. And when I use\n\n&gt; tokenizer = AutoTokenizer.from_pretrained('jplu/tf-xlm-roberta-large') \n\nto import a pre-trained tokenizer I got an error message.\n\n&gt; ImportError: FloatProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n\nSo I updated jupyter and ipywidgets. \nBut the error is unsolved. I recognized that it has something to do with tqdm. And Spyder may not show progress bar properly. So I rerun this code in JupyterNotebook on my local machine. And the problem solved. No error message and the tokenizer imported properly.\nMy question is how to make it work on Spyder. I assume this AutoTokenizer class won't just work in notebook-style development environment, right?",
      "votes": null
    },
    {
      "id": "883096",
      "postDate": "06/12/2020 11:16:42",
      "content": "<p>AutoTokenizer works very well in notebook-style development environment, you probably have two different environments in spyder and jupyter (check sys.path sys.version in both ...)</p>",
      "rawMarkdown": "AutoTokenizer works very well in notebook-style development environment, you probably have two different environments in spyder and jupyter (check sys.path sys.version in both ...)",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 883096,
      "author_name": "alexis1024",
      "author_url": "",
      "post_date": "06/12/2020 11:16:42",
      "content": "<p>AutoTokenizer works very well in notebook-style development environment, you probably have two different environments in spyder and jupyter (check sys.path sys.version in both ...)</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "881387": "Hey you guys. I try to run some experiments on my local machine. And when I use\n\n&gt; tokenizer = AutoTokenizer.from_pretrained('jplu/tf-xlm-roberta-large') \n\nto import a pre-trained tokenizer I got an error message.\n\n&gt; ImportError: FloatProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n\nSo I updated jupyter and ipywidgets. \nBut the error is unsolved. I recognized that it has something to do with tqdm. And Spyder may not show progress bar properly. So I rerun this code in JupyterNotebook on my local machine. And the problem solved. No error message and the tokenizer imported properly.\nMy question is how to make it work on Spyder. I assume this AutoTokenizer class won't just work in notebook-style development environment, right?",
    "883096": "AutoTokenizer works very well in notebook-style development environment, you probably have two different environments in spyder and jupyter (check sys.path sys.version in both ...)"
  },
  "source": "meta"
}