{
  "id": 20093,
  "title": "Team?",
  "url": "/competitions/state-farm-distracted-driver-detection/discussion/20093",
  "author_name": "",
  "post_date": "2016-04-12T18:44:57.713Z",
  "votes": null,
  "comment_count": 3,
  "views": 557,
  "content": "<p>I have a good amount of experience with using neural nets for image recognition.  I'd like to try to do this in torch. </p>\n\n<p>I've been experimenting with md-rnn's and spatial-attention models, and I'd like to explore the possibilities.  </p>\n\n<p>I have a Titan X GPU.</p>",
  "messages": [
    {
      "id": "114658",
      "postDate": "04/12/2016 18:44:57",
      "content": "<p>I have a good amount of experience with using neural nets for image recognition.  I'd like to try to do this in torch. </p>\n\n<p>I've been experimenting with md-rnn's and spatial-attention models, and I'd like to explore the possibilities.  </p>\n\n<p>I have a Titan X GPU.</p>",
      "rawMarkdown": "I have a good amount of experience with using neural nets for image recognition.  I'd like to try to do this in torch. \r\n\r\nI've been experimenting with md-rnn's and spatial-attention models, and I'd like to explore the possibilities.  \r\n\r\nI have a Titan X GPU.",
      "votes": null
    },
    {
      "id": "121015",
      "postDate": "05/22/2016 21:33:14",
      "content": "<p>Hi Amos, </p>\n\n<p>Are you still up for trying this out? I've been working on a Torch solution that I made public. The backbone of the implementation is there, along with some simple VGG models. At this point it would be easy to come in and add new models. I'd be very much interested in working on recurrent neural nets and attention models. </p>",
      "rawMarkdown": "Hi Amos, \r\n\r\nAre you still up for trying this out? I've been working on a Torch solution that I made public. The backbone of the implementation is there, along with some simple VGG models. At this point it would be easy to come in and add new models. I'd be very much interested in working on recurrent neural nets and attention models.",
      "votes": null
    },
    {
      "id": "121019",
      "postDate": "05/23/2016 01:06:13",
      "content": "<p>I'm definitely interested -- what's your google or skype id?</p>",
      "rawMarkdown": "I'm definitely interested -- what's your google or skype id?",
      "votes": null
    },
    {
      "id": "121023",
      "postDate": "05/23/2016 01:49:22",
      "content": "<p>Great! You can reach my on hangouts, my gmail id is luciionita, you can reach me there. </p>",
      "rawMarkdown": "Great! You can reach my on hangouts, my gmail id is luciionita, you can reach me there.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 121015,
      "author_name": "ilucian",
      "author_url": "",
      "post_date": "05/22/2016 21:33:14",
      "content": "<p>Hi Amos, </p>\n\n<p>Are you still up for trying this out? I've been working on a Torch solution that I made public. The backbone of the implementation is there, along with some simple VGG models. At this point it would be easy to come in and add new models. I'd be very much interested in working on recurrent neural nets and attention models. </p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 121019,
      "author_name": "abeabe",
      "author_url": "",
      "post_date": "05/23/2016 01:06:13",
      "content": "<p>I'm definitely interested -- what's your google or skype id?</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 121023,
      "author_name": "ilucian",
      "author_url": "",
      "post_date": "05/23/2016 01:49:22",
      "content": "<p>Great! You can reach my on hangouts, my gmail id is luciionita, you can reach me there. </p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "114658": "I have a good amount of experience with using neural nets for image recognition.  I'd like to try to do this in torch. \r\n\r\nI've been experimenting with md-rnn's and spatial-attention models, and I'd like to explore the possibilities.  \r\n\r\nI have a Titan X GPU.",
    "121015": "Hi Amos, \r\n\r\nAre you still up for trying this out? I've been working on a Torch solution that I made public. The backbone of the implementation is there, along with some simple VGG models. At this point it would be easy to come in and add new models. I'd be very much interested in working on recurrent neural nets and attention models.",
    "121019": "I'm definitely interested -- what's your google or skype id?",
    "121023": "Great! You can reach my on hangouts, my gmail id is luciionita, you can reach me there."
  },
  "source": "meta"
}